docs: v0.31 release -- UI polish + deployment hardening (#74)

Co-authored-by: Nathan Esquenazi <nesquena@gmail.com>

.dockerignore

@@ -0,0 +1,7 @@
+.git
+.pytest_cache
+__pycache__
+*.pyc
+*.pyo
+tests/
+.env*

.github/workflows/release.yml

@@ -0,0 +1,56 @@
+name: Release & Docker
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write   # required: create GitHub Release
+      packages: write   # required: push to ghcr.io
+
+    steps:
+      - uses: actions/checkout@v4
+
+      # Create GitHub Release from tag with auto-generated notes
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v2
+        with:
+          generate_release_notes: true
+
+      # Set up multi-arch build (QEMU + Buildx)
+      - uses: docker/setup-qemu-action@v3
+      - uses: docker/setup-buildx-action@v3
+
+      # Log in to GitHub Container Registry
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      # Extract tags from the git ref (supports vX.Y and vX.Y.Z formats)
+      - name: Extract metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ghcr.io/${{ github.repository }}
+          tags: |
+            type=match,pattern=v(\d+\.\d+(?:\.\d+)?),group=1
+            type=raw,value=latest
+
+      # Build and push multi-arch image (amd64 + arm64)
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

ARCHITECTURE.md

@@ -18,7 +18,7 @@ a central chat area, and a right panel for workspace file browsing.
 
 The design philosophy is deliberately minimal. There is no build step, no bundler, no
 frontend framework. The Python server is split into a routing shell (server.py) and
-business logic modules (api/). The frontend is six vanilla JS modules loaded from static/.
+business logic modules (api/). The frontend is seven vanilla JS modules loaded from static/.
 This makes the code easy to modify from a terminal or by an agent.
 
 ---
@@ -26,38 +26,44 @@ This makes the code easy to modify from a terminal or by an agent.
 ## 2. File Inventory
 
     <repo>/
-    server.py              Thin routing shell + HTTP Handler. ~76 lines. Pure Python.
+    server.py              Thin routing shell + HTTP Handler + auth middleware. ~81 lines.
                            Delegates all route handling to api/routes.py.
     start.sh               Discovery script: finds agent dir, Python, starts server.
+    Dockerfile             python:3.12-slim container image (~23 lines)
+    docker-compose.yml     Compose config with named volume and optional auth (~22 lines)
+    .dockerignore          Excludes .git, tests/, .env* from Docker builds
     api/
       __init__.py          Package marker
-      routes.py            All GET + POST route handlers (~802 lines)
-      config.py            Shared configuration, constants, global state, model discovery (~453 lines)
-      helpers.py           HTTP helpers: j(), bad(), require(), safe_resolve() (~57 lines)
-      models.py            Session model + CRUD (~114 lines)
+      auth.py              Optional password authentication, signed cookies (~149 lines)
+      config.py            Discovery, globals, model detection, reloadable config (~701 lines)
+      helpers.py           HTTP helpers: j(), bad(), require(), safe_resolve(), security headers (~71 lines)
+      models.py            Session model + CRUD, per-session profile tracking (~137 lines)
+      profiles.py          Profile state management, hermes_cli wrapper (~246 lines)
+      routes.py            All GET + POST route handlers (~1180 lines)
+      streaming.py         SSE engine, run_agent, cancel, HERMES_HOME save/restore (~236 lines)
+      upload.py            Multipart parser, file upload handler (~78 lines)
       workspace.py         File ops: list_dir, read_file_content, workspace helpers (~77 lines)
-      upload.py            Multipart parser, file upload handler (~77 lines)
-      streaming.py         SSE engine, run_agent integration, cancel support (~218 lines)
     static/
-      index.html           HTML template (served from disk)
-      style.css            All CSS
-      ui.js                DOM helpers, renderMd, tool cards, model dropdown (~671 lines)
-      workspace.js         File tree, preview, file ops (~168 lines)
-      sessions.js          Session CRUD, list rendering, search (~206 lines)
-      messages.js          send(), SSE event handlers, approval, transcript (~310 lines)
-      panels.js            Cron, skills, memory, workspace, todo, switchPanel (~600 lines)
-      boot.js              Event wiring + boot IIFE (~154 lines)
+      index.html           HTML template (~364 lines)
+      style.css            All CSS incl. mobile responsive (~670 lines)
+      ui.js                DOM helpers, renderMd, tool cards, model dropdown, file tree (~977 lines)
+      workspace.js         File preview, file ops, loadDir, clearPreview (~185 lines)
+      sessions.js          Session CRUD, list rendering, search, SVG icons, overlay actions (~533 lines)
+      messages.js          send(), SSE event handlers, approval, transcript (~297 lines)
+      panels.js            Cron, skills, memory, workspace, profiles, todo, settings (~974 lines)
+      commands.js          Slash command registry, parser, autocomplete dropdown (~156 lines)
+      boot.js              Event wiring, mobile nav, voice input, boot IIFE (~338 lines)
     tests/
       conftest.py          Isolated test server (port 8788, separate HERMES_HOME) (~240 lines)
-      test_sprint1-11.py   Feature tests per sprint (13 files)
-      test_regressions.py  Permanent regression gate
+      test_sprint{1-20b}.py Feature tests per sprint (21 files, 415 test functions)
+      test_regressions.py  Permanent regression gate (23 tests)
     AGENTS.md              Instruction file for agents working in this directory.
     ROADMAP.md             Feature and product roadmap document.
     SPRINTS.md             Forward sprint plan with CLI + Claude parity targets.
     ARCHITECTURE.md        THIS FILE.
     TESTING.md             Manual browser test plan and automated coverage reference.
     CHANGELOG.md           Release notes per sprint.
-    PORTABILITY.md         Portability design spec for download-and-run installs.
+    BUGS.md                Bug backlog and fixed items tracker.
     requirements.txt       Python dependencies.
     .env.example           Sample environment variable overrides.
 
@@ -67,7 +73,8 @@ State directory (runtime data, separate from source):
     sessions/          One JSON file per session: {session_id}.json
     workspaces.json    Registered workspaces list
     last_workspace.txt Last-used workspace path
-    settings.json      (future) User settings
+    settings.json      User settings (default model, workspace, send key, password hash)
+    projects.json      Session project groups (name, color, id)
 
 Log file:
 
@@ -91,6 +98,8 @@ Environment variables controlling behavior:
     HERMES_WEBUI_STATE_DIR         Where sessions/ folder lives
     HERMES_CONFIG_PATH             Path to ~/.hermes/config.yaml
     HERMES_WEBUI_DEFAULT_MODEL     Default LLM model string
+    HERMES_WEBUI_PASSWORD          Optional: enable password auth (off by default)
+    HERMES_HOME                    Base directory for Hermes state (~/.hermes by default)
 
 Test isolation environment variables (set by conftest.py):
 
@@ -109,6 +118,8 @@ Per-request environment variables (set by chat handler, restored after):
     HERMES_EXEC_ASK      Set to "1" to enable approval gate for dangerous commands.
     HERMES_SESSION_KEY   Set to session_id. The approval tool keys pending entries
                          by this value, enabling per-session approval state.
+    HERMES_HOME          Set to the active profile's directory before running agent.
+                         Saved and restored around each agent run.
 
 WARNING: These env vars are process-global. Two concurrent chat requests will clobber
 each other. This is safe only for single-user, single-concurrent-request use.
@@ -151,10 +162,14 @@ Session is a plain Python class (not a dataclass, not SQLAlchemy):
       session_id    hex string, 12 chars (uuid4().hex[:12])
       title         string, auto-set from first user message
       workspace     absolute path string, resolved at creation
-      model         OpenRouter model ID string (e.g. "anthropic/claude-sonnet-4.6")
+      model         model ID string (e.g. "anthropic/claude-sonnet-4.6")
       messages      list of OpenAI-format message dicts
       created_at    float Unix timestamp
       updated_at    float Unix timestamp, updated on every save()
+      pinned        bool, default False (Sprint 12)
+      archived      bool, default False (Sprint 14)
+      project_id    string or null, FK to projects.json (Sprint 15)
+      tool_calls    list of tool call dicts (Sprint 10)
 
     Key methods:
       path (property)  Returns SESSION_DIR/{session_id}.json
@@ -326,16 +341,20 @@ read_file_content(workspace, rel):
 ### 5.1 Structure
 
 The frontend is served from static/ as separate files: one HTML template, one CSS file,
-and six JavaScript modules (~2,025 lines total). External dependency: Prism.js from CDN
-(syntax highlighting, loaded async/deferred).
+and six JavaScript modules (~2,786 lines total). External dependencies: Prism.js (syntax
+highlighting) and Mermaid.js (diagrams) from CDN, both loaded async/deferred with SRI hashes.
 
 Six JS modules loaded in order at end of <body>:
-  1. ui.js       (~589 lines) DOM helpers, renderMd, tool card rendering, global state
-  2. workspace.js (~168 lines) File tree, preview, file operations
-  3. sessions.js  (~206 lines) Session CRUD, list rendering, search
-  4. messages.js  (~310 lines) send(), SSE event handlers, approval, transcript
-  5. panels.js    (~600 lines) Cron, skills, memory, workspace, todo, switchPanel
-  6. boot.js      (~152 lines) Event wiring + boot IIFE
+  1. ui.js       (~846 lines) DOM helpers, renderMd, tool card rendering, global state
+  2. workspace.js (~169 lines) File tree, preview, file operations
+  3. sessions.js  (~532 lines) Session CRUD, list rendering, search, SVG icons, overlay actions, project picker
+  4. messages.js  (~293 lines) send(), SSE event handlers, approval, transcript
+  5. panels.js    (~771 lines) Cron, skills, memory, workspace, todo, switchPanel
+  6. boot.js      (~175 lines) Event wiring + boot IIFE
+
+sessions.js defines an `ICONS` constant at module level with hardcoded SVG strings for all
+session action buttons (pin, unpin, folder, archive, unarchive, duplicate, trash). All icons
+inherit `currentColor` for consistent theming.
 
 Three-panel layout (in static/index.html):
 
@@ -406,25 +425,43 @@ Boot IIFE:
 
 ### 5.4 Markdown Renderer (renderMd)
 
-A hand-rolled regex chain. Processes in this order:
-1. Code blocks (``` lang ... ```) -> <pre><code> with language header
-2. Inline code (`...`) -> <code>
-3. Bold+italic (***..***) -> <strong><em>
-4. Bold (**...**) -> <strong>
-5. Italic (*...*) -> <em>
-6. Headings (# ## ###) -> <h1> <h2> <h3>
-7. Horizontal rules (---+) -> <hr>
-8. Blockquotes (> ...) -> <blockquote>
-9. Unordered lists (- or * or + at line start) -> <ul><li>
-10. Ordered lists (N. at line start) -> <ol><li>
-11. Links ([text](https://...)) -> <a href target=_blank>
-12. Paragraph wrapping: remaining double-newline-separated blocks -> <p>
+A hand-rolled regex chain with HTML safety. Processes in this order:
+
+Pre-pass (v0.18.1):
+0a. Stash fenced code blocks and backtick spans (fence_stash array)
+0b. Convert safe HTML tags to markdown equivalents:
+    <strong>/<b> -> **text**, <em>/<i> -> *text*, <code> -> `text`, <br> -> newline
+0c. Restore stashed code blocks
+
+Pipeline:
+1. Mermaid blocks (```mermaid ... ```) -> <div class="mermaid-block">
+2. Code blocks (``` lang ... ```) -> <pre><code> with language header
+3. Inline code (`...`) -> <code>
+4. Bold+italic (***..***) -> <strong><em>
+5. Bold (**...**) -> <strong>
+6. Italic (*...*) -> <em>
+7. Headings (# ## ###) -> <h1> <h2> <h3> (uses inlineMd() for content)
+8. Horizontal rules (---+) -> <hr>
+9. Blockquotes (> ...) -> <blockquote> (uses inlineMd() for content)
+10. Unordered lists (- or * or + at line start) -> <ul><li> (uses inlineMd())
+11. Ordered lists (N. at line start) -> <ol><li> (uses inlineMd())
+12. Links ([text](https://...)) -> <a href target=_blank>
+13. Tables (| col | col |) -> <table>
+14. Safety net: escape any HTML tag not in SAFE_TAGS allowlist via esc()
+15. Paragraph wrapping: remaining double-newline-separated blocks -> <p>
+
+inlineMd() helper (v0.18.1):
+    Processes inline bold/italic/code/links within list items, blockquotes,
+    and headings. Escapes unknown tags via SAFE_INLINE allowlist. Replaces
+    the old direct esc() calls which would double-escape pre-pass output.
+
+SAFE_TAGS allowlist:
+    strong, em, code, pre, h1-6, ul, ol, li, table, thead, tbody, tr, th,
+    td, hr, blockquote, p, br, a, div. Everything else is escaped.
 
 Known gaps:
-- Tables: not supported, render as plain text
 - Nested lists: single regex pass, multi-level indentation not handled
 - Mixed bold+link in same line: may produce garbled output
-- Inline HTML: not sanitized (esc() only runs on code content)
 
 ### 5.5 Model Chip Label (Fixed in Sprint 1)
 
@@ -604,26 +641,27 @@ Split server.py into a proper package. Completed across Sprints 4-10.
 Current structure:
 
     <repo>/
-      server.py               Entry point + HTTP Handler routing (~704 lines)
+      server.py               Entry point + HTTP Handler dispatch (~76 lines)
       api/
         __init__.py
-        config.py             Configuration, constants, global state (~273 lines)
+        routes.py             All GET + POST route handlers (~1016 lines)
+        config.py             Configuration, constants, global state, model discovery (~640 lines)
         helpers.py            HTTP helpers: j(), bad(), require(), safe_resolve() (~57 lines)
-        models.py             Session model + CRUD (~114 lines)
+        models.py             Session model + CRUD (~132 lines)
         workspace.py          File ops, workspace management (~77 lines)
         upload.py             Multipart parser, file upload handler (~77 lines)
-        streaming.py          SSE engine, run_agent, cancel support (~218 lines)
+        streaming.py          SSE engine, run_agent, cancel support (~222 lines)
       static/
         index.html            HTML document (served from disk)
-        style.css             All CSS
+        style.css             All CSS (~560 lines)
         ui.js, workspace.js, sessions.js, messages.js, panels.js, boot.js
       tests/
         conftest.py           Isolated test server on port 8788
-        test_sprint1-10.py    Feature tests per sprint (12 files)
+        test_sprint1-16.py    Feature tests per sprint (14 files)
         test_regressions.py   Permanent regression gate
 
-Remaining: server.py still has all 49 route handlers in one do_GET/do_POST class.
-Sprint 11 plans extracting these to api/routes.py, making server.py a ~50-line shell.
+Route extraction to api/routes.py completed in Sprint 11. server.py is now a ~76-line
+thin shell: Handler class with structured logging, dispatch to routes, and main().
 
 ### Phase B: Thread-Safe Request Context (Priority: Critical, Effort: Medium)
 
@@ -718,10 +756,10 @@ Optional password gate for non-SSH-tunnel deployments.
 
 ### Phase I: Test Infrastructure -- COMPLETE
 
-190 tests across 12 test files + regression gate. Isolated test server on port 8788
+289 tests across 14 test files + regression gate. Isolated test server on port 8788
 with separate HERMES_HOME, wiped per run. Production data never touched.
 
-Test files: `test_sprint1.py` through `test_sprint10.py`, `test_regressions.py`.
+Test files: `test_sprint1.py` through `test_sprint11.py`, `test_sprint16.py`, `test_regressions.py`.
 Fixtures in `conftest.py`: auto-cleanup, cron isolation, workspace reset.
 
 Remaining: no CI (GitHub Actions), no frontend tests (browser-based).

BUGS.md

@@ -1,18 +1,40 @@
 # Bugs Backlog
 
-This file tracks UI bugs and polish items to address in a future sprint.
+This file tracks UI bugs and polish items. Fixed items are kept for reference.
 
-## ~~Conversation list title truncation / hover actions~~ — Fixed (Sprint 16)
+---
+
+## Open Bugs
+
+*No open bugs at this time.*
+
+---
+
+## Fixed
+
+### ~~Session title truncation / hover actions~~ -- Fixed (Sprint 16)
 
 - **Was:** Action icons reserved ~30px of space even when invisible, truncating titles.
 - **Fix:** Wrapped all action buttons in a `.session-actions` overlay container with `position:absolute`. Titles now use full available width. Actions appear on hover with a gradient fade from the right edge.
 
-## ~~Folder/project assignment interaction feels sticky~~ — Fixed (Sprint 16)
+### ~~Folder/project assignment interaction feels sticky~~ -- Fixed (Sprint 16)
 
 - **Was:** Folder icon stayed permanently visible (blue, 60% opacity) when a session belonged to a project.
 - **Fix:** Replaced `.has-project` persistent button with a colored left border matching the project color. The folder button now only appears in the hover overlay like all other actions.
 
+### ~~Project picker clipping and width~~ -- Fixed (v0.17.3)
+
+- **Was:** Picker was clipped by `overflow:hidden` on `.session-item` ancestors. With `position:fixed`, no containing block constrained width -- picker stretched to full viewport.
+- **Fix:** Dynamic width calculation (min 160px, max 220px). Event listener reordering. Cleanup sequence corrected. (PR #25)
+
+### ~~NameError crash in model discovery~~ -- Fixed (v0.17.3)
+
+- **Was:** `logger.debug()` called in custom endpoint `except` block, but `logger` was never imported in `config.py`. Every failed endpoint fetch crashed with `NameError`.
+- **Fix:** Replaced with silent `pass` -- unreachable endpoints are expected when no local LLM is configured. (PR #24)
+
+---
+
 ## Notes
 
-- Both issues resolved in Sprint 16 (Session Sidebar Visual Polish).
-- Icons replaced from inconsistent emoji HTML entities to monochrome SVG line icons.
+- Sprint 16 replaced all emoji HTML entities with monochrome SVG line icons (`ICONS` constant in `sessions.js`).
+- All session action buttons now use the overlay pattern for consistent UX.

CHANGELOG.md

@@ -5,6 +5,595 @@
 
 ---
 
+## [v0.31] UI Polish + Deployment Hardening
+*April 4, 2026 | 424 tests*
+
+### Bug Fixes
+- **Profile dropdown overlaps chat messages.** `.topbar` had no stacking context,
+  causing the dropdown to paint over `.messages`. Added `position:relative;z-index:10`
+  to `.topbar`. (#71)
+- **Workspace dropdown clipped by sidebar.** `.sidebar overflow:hidden` swallowed
+  the upward-opening workspace dropdown entirely. Changed to `overflow:visible`
+  (scroll lives on `.session-list`); added `position:relative;z-index:10` to
+  `.sidebar-bottom`. (#71)
+- **Slash-command autocomplete behind tool cards.** `.composer-wrap` had
+  `position:relative` but no `z-index`, letting tool cards bleed over it.
+  Added `z-index:10`. (#71)
+- **Skill picker clipped inside Settings modal.** `.settings-panel overflow-y:auto`
+  clipped the absolute-positioned skill picker. Moved scroll to `.settings-body`,
+  set panel to `overflow:visible`, raised skill picker to `z-index:1100`. (#71)
+- **CLI session badge blocks action buttons on hover.** Added
+  `.session-item.cli-session:hover::after { display:none }` so the gold "cli"
+  label hides on hover, making archive/delete/pin fully reachable. (#71)
+- **Workspace dropdown name and path crowded on same line.** `.ws-opt` was a plain
+  block with inline spans. Added `flex-direction:column;gap:4px` so name and path
+  stack cleanly. (#71)
+- **Both servers sharing same state directory.** `api/config.py` and `start.sh`
+  both defaulted to `~/.hermes/webui-mvp` (an internal dev name). Changed default
+  to `~/.hermes/webui` -- generic, appropriate for any deployment. Override with
+  `HERMES_WEBUI_STATE_DIR`. (#72, #73)
+
+---
+
+## [v0.30.1] CLI Session Bridge Fixes
+*April 4, 2026 | 424 tests*
+
+### Bug Fixes
+- **CLI sessions not appearing in sidebar.** Three frontend gaps: `sessions.js`
+  wasn't rendering CLI sessions (missing `is_cli_session` check in render loop),
+  sidebar click handler didn't trigger import, and the "cli" badge CSS selector
+  wasn't matching the rendered DOM structure. (#58)
+- **CLI bridge read wrong profile's state.db.** `get_cli_sessions()` resolved
+  `HERMES_HOME` at server launch time, not at call time. After a profile switch,
+  it kept reading the original profile's database. Now resolves dynamically via
+  `get_active_hermes_home()`. (#59)
+- **Silent SQL error swallowed all CLI sessions.** The `sessions` table in
+  `state.db` has no `profile` column — the query referenced `s.profile` which
+  caused a silent `OperationalError`. The `except Exception: return []` handler
+  swallowed it, returning zero CLI sessions. Removed the column reference and
+  added explicit column-existence checks. (#60)
+
+### Features
+- **"Show CLI sessions" toggle in Settings.** New checkbox in the Settings panel
+  to show/hide CLI sessions in the sidebar. Persisted server-side in
+  `settings.json` (`show_cli_sessions`, default `true`). When disabled, CLI
+  sessions are excluded from `/api/sessions` responses. (#61)
+
+---
+
+## [v0.30] CLI Session Bridge (Community: @thadreber-web)
+*April 4, 2026 | 424 tests*
+
+### Features
+- **CLI session bridge.** The WebUI now reads sessions from the hermes-agent's
+  SQLite store (`state.db`). CLI sessions appear in the sidebar with a gold
+  "cli" indicator badge. Click to import into the WebUI store with full message
+  history — replies then work through the normal agent pipeline.
+- **`/api/session/import_cli` endpoint.** Imports a CLI session into the WebUI
+  JSON store. Idempotent — returns existing session if already imported.
+  Derives title from first message, inherits active profile and workspace.
+- **`/api/sessions` merges CLI sessions.** Sidebar shows both WebUI and CLI
+  sessions sorted by last activity. Deduplication ensures WebUI sessions take
+  priority when the same session_id exists in both stores.
+- **CLI session fallback on `/api/session`.** If a session_id isn't found in
+  the WebUI store, falls back to reading from the CLI SQLite store.
+
+### Architecture
+- `api/models.py`: `get_cli_sessions()`, `get_cli_session_messages()`,
+  `import_cli_session()`. All use parameterized SQL queries and `with` for
+  connection management. Graceful fallback on missing sqlite3 or state.db.
+- `api/routes.py`: CLI fallback in GET `/api/session`, merged list in
+  GET `/api/sessions`, POST `/api/session/import_cli`.
+- `static/style.css`: `.cli-session` indicator styles (gold border + badge).
+
+---
+
+## [v0.29] Sprint 23: Agentic Transparency + Polish
+*April 4, 2026 | 424 tests*
+
+### Features
+
+- **Token/cost display.** Agent usage (input tokens, output tokens, estimated
+  cost) is now read after each conversation and persisted on the session.
+  A muted badge appears below the last assistant message when enabled.
+  Off by default — toggle via the Settings panel checkbox or `/usage` slash
+  command. Persists server-side across refreshes.
+
+- **Subagent delegation cards.** `subagent_progress` events now render with
+  a 🔀 icon and a blue indented left border to visually distinguish child
+  tool activity from parent tool calls. `delegate_task` cards display as
+  "Delegate task" with cleaner formatting.
+
+- **Skill picker in cron create form.** The "New Job" form now has a search
+  input + tag chip picker for attaching skills to cron jobs. Skills fetched
+  from `/api/skills`, filtered on keyup, added/removed as tag chips.
+  `submitCronCreate()` sends `skills` array in the POST body. Backend already
+  supported the field — this was a pure frontend gap.
+
+- **Skill linked files viewer.** Skill preview panel now renders a "Linked
+  Files" section below SKILL.md content when a skill has `references/`,
+  `templates/`, `scripts/`, or `assets/` subdirectories. Clicking a file
+  loads it in the preview panel with syntax highlighting.
+  New `file` query param on `GET /api/skills/content` serves linked files
+  with path traversal protection.
+
+- **Workspace tree state persists across refreshes.** Expanded directory
+  paths are saved to `localStorage` keyed by workspace path
+  (`hermes-webui-expanded:{path}`). On every root load (page refresh,
+  session switch), the saved state is restored and previously-expanded
+  directories are pre-fetched so the tree renders fully on first paint.
+
+- **Timestamps fixed.** `api/streaming.py` now stamps `timestamp` on every
+  message that lacks one at conversation completion. The `done` SSE event
+  also stamps `_ts` on the last assistant message immediately. Timestamps
+  were already rendered in the UI (Sprint 14, hover-to-reveal) but most
+  messages had no timestamp field, so nothing ever showed.
+
+- **`/usage` slash command.** Instant toggle for token usage display.
+  Shows a toast, persists to server, updates the Settings checkbox if open,
+  re-renders immediately.
+
+### Bug Fixes
+
+- **XSS via inline onclick + esc().** Skill names and file paths embedded in
+  `onclick` HTML attributes used `esc()` for encoding. `esc()` converts `'`
+  to `'` (HTML-safe) but browsers decode it back before executing JS,
+  allowing skill names with apostrophes to break out of string literals.
+  Fixed by switching to `data-*` attributes + `addEventListener`.
+
+- **rglob wildcard injection.** The `name` query param for
+  `/api/skills/content?file=` was passed directly to `SKILLS_DIR.rglob()`,
+  which accepts glob patterns. `name=*` would match an arbitrary directory
+  and use it as the trust base for path traversal checking.
+  Fixed by rejecting names containing `* ? [ ]` metacharacters with 400.
+
+- **`_fmtTokens(null)` returned "null".** `String(null)` = `"null"` would
+  appear in the usage badge for sessions missing fields. Fixed with a
+  `!n || n < 0` guard returning `'0'`.
+
+- **Usage badge on wrong row.** Badge used `:last-child` which could target
+  a user message row. Fixed by adding `data-role` to message rows and
+  scanning backwards for the last `assistant` row.
+
+- **Tool name resolution.** Tool call entries in session JSON sometimes
+  stored the literal string `"tool"` as the name when the call ID couldn't
+  be resolved. Fixed: defaults to empty string and skips unresolvable entries.
+
+- **Inline import inside loop.** `import json as _j2` inside the done-handler
+  loop in `streaming.py` moved to module-level.
+
+### Session Model
+
+- Added `input_tokens`, `output_tokens`, `estimated_cost` fields to Session
+  (defaults: 0, 0, None). Included in `compact()`, session JSON, and all
+  API responses. Backward-compatible via `**kwargs`.
+
+- Added `args` capture to `tool_calls` session JSON entries (truncated
+  snapshot of tool inputs, up to 6 keys / 120 chars each).
+
+### Settings
+
+- New `show_token_usage` boolean setting (default: `false`). Stored in
+  `settings.json`, loaded on boot alongside `send_key`.
+
+### Tests
+
+- Renamed `test_sprint24.py` → `test_sprint23.py`.
+- Strengthened session usage assertions (explicit field presence checks).
+- Added: path traversal rejection test, wildcard name rejection test,
+  cron create with skills array test.
+- Total: 424 tests (up from 415).
+
+---
+
+## [v0.28.1] CI Pipeline + Multi-Arch Docker Builds
+*April 3, 2026 | 426 tests*
+
+### Features
+- **GitHub Actions CI.** New workflow triggers on tag push (`v*`). Builds
+  multi-arch Docker images (linux/amd64 + linux/arm64), pushes to
+  `ghcr.io/nesquena/hermes-webui`, and creates a GitHub Release with
+  auto-generated release notes. Uses GHA layer caching for fast rebuilds.
+- **Pre-built container images.** Users can now `docker pull ghcr.io/nesquena/hermes-webui:latest`
+  instead of building locally.
+
+---
+
+## [v0.27] Profile Creation Fallback for Docker (Issue #44)
+*April 3, 2026 | 426 tests*
+
+### Bug Fixes
+- **Profile creation works without hermes-agent.** In Docker containers where
+  `hermes_cli` is not importable, profile creation now falls back to a local
+  implementation that creates the directory structure and optionally clones
+  config files. Previously returned `RuntimeError` with "hermes-agent required".
+- **Name validation uses `fullmatch()`.** Prevents trailing-newline bypass of
+  the `$` anchor in `re.match()`. Not reachable from the web UI (name is
+  stripped), but fixed for defense-in-depth.
+- **`clone_from` validated in `create_profile_api()`.** Defense-in-depth:
+  prevents path traversal if called by a non-HTTP client.
+- **Fallback return uses full 9-key schema.** Previously returned only 2 keys
+  (`name`, `path`), inconsistent with the normal response shape.
+- **Atomic directory creation.** `mkdir(exist_ok=False)` prevents TOCTOU race
+  on concurrent profile creates.
+
+### Architecture
+- `api/profiles.py`: `_validate_profile_name()`, `_create_profile_fallback()`,
+  `_PROFILE_ID_RE`, `_PROFILE_DIRS`, `_CLONE_CONFIG_FILES` constants matching
+  upstream `hermes_cli.profiles`.
+- `docker-compose.yml`: Removed `:ro` from `~/.hermes` mount (required for
+  profile writes). Localhost-only binding preserved.
+
+---
+
+## [v0.26] Profile System Polish -- 10 Post-Sprint-23 Fixes
+*April 3, 2026 | 426 tests*
+
+### Bug Fixes
+- **Profile switch base dir bug.** When `HERMES_HOME` was mutated to a
+  `profiles/` subdir at startup, `switch_profile()` doubled the path
+  (e.g. `~/.hermes/profiles/X/profiles/X`). New `_resolve_base_hermes_home()`
+  detects profile subdirs and walks up to the actual base.
+- **Cross-provider model routing.** Picking a model from a different provider
+  than the config's default now routes through OpenRouter instead of trying
+  a direct API call to a provider whose key may not exist.
+- **Legacy sessions missing profile tag.** `all_sessions()` now backfills
+  `profile='default'` for pre-Sprint-22 sessions so the profile filter works.
+- **Workspace list cleanup.** Stale paths, test artifacts, and cross-profile
+  entries are now cleaned on load. Legacy global workspace file migrated
+  once for the default profile.
+- **API error messages.** `api()` helper now parses JSON error bodies and
+  surfaces the human-readable message instead of raw JSON.
+- **Workspace dropdown moved to sidebar.** The workspace picker now opens
+  upward from the sidebar bottom instead of clipping behind the topbar.
+
+### Features
+- **Rate limit error display.** Rate limit errors (429) now show a distinct
+  card with a rate limit icon and hint, instead of the generic error message.
+- **SSE `apperror`/`warning` events.** Server can send typed error events
+  that the frontend handles with appropriate UX (rate limit card, fallback
+  notice, etc.).
+- **Smart model resolver.** `_findModelInDropdown()` handles name mismatches
+  between config model IDs and dropdown values (e.g. `claude-sonnet-4-6` vs
+  `anthropic/claude-sonnet-4.6`).
+- **Profile switch starts new session.** When the current session has messages,
+  switching profiles automatically starts a fresh session to prevent
+  cross-profile tagging.
+- **Per-profile toolsets.** Agent now reads `platform_toolsets.cli` from the
+  active profile's config at call time, not the boot-time snapshot.
+- **Per-profile fallback model.** `fallback_model` config is read from the
+  active profile and passed to AIAgent.
+
+### Architecture
+- `api/profiles.py`: `_resolve_base_hermes_home()` replaces naive env var read.
+- `api/workspace.py`: `_clean_workspace_list()`, `_migrate_global_workspaces()`.
+- `api/streaming.py`: Per-profile toolsets and fallback model at call time.
+- `api/models.py`: `all_sessions()` backfills `profile='default'`.
+- `static/ui.js`: `_findModelInDropdown()`, `_applyModelToDropdown()`.
+- `static/messages.js`: `apperror` and `warning` SSE event handlers.
+
+---
+
+## [v0.25] Sprint 23 -- Profile/Workspace/Model Coherence
+*April 3, 2026 | 423 tests*
+
+### Features
+- **Profile-local workspace storage.** Each named profile now stores its own
+  `workspaces.json` and `last_workspace.txt` under `{profile_home}/webui_state/`.
+  Default profile continues using the global STATE_DIR for backward compat.
+- **Profile switch returns defaults.** `POST /api/profile/switch` response now
+  includes `default_model` and `default_workspace` from the new profile's
+  config.yaml, enabling one-round-trip state sync.
+- **Session profile filter.** Session sidebar filters to the active profile by
+  default. "Show N from other profiles" toggle reveals sessions from all
+  profiles, modeled on the existing archived toggle. Resets on profile switch.
+
+### Bug Fixes
+- **Model picker ignores profile on switch.** `switchToProfile()` now clears
+  the `hermes-webui-model` localStorage key so the profile's default model
+  applies instead of a stale preference from another profile.
+- **Workspace list was global.** Switching profiles no longer shows the wrong
+  profile's workspaces.
+- **`DEFAULT_WORKSPACE` was a boot-time singleton.** Now resolved dynamically
+  through `_profile_default_workspace()`.
+- **Session list showed all profiles.** Now filtered to active profile.
+- **`switchToProfile()` didn't refresh workspaces or sessions.** Now refreshes
+  workspace list, session list, and resets profile filter on switch.
+
+### Architecture
+- `api/workspace.py` rewritten with profile-aware path resolution.
+- `api/profiles.py`: `switch_profile()` returns `default_model` and
+  `default_workspace`.
+- `static/sessions.js`: Profile filter with toggle UI.
+- `static/panels.js`: Full cascade refresh on profile switch.
+- 8 new tests in `test_sprint23.py`.
+
+---
+
+## [v0.24] Sprint 22 -- Multi-Profile Support (Issue #28)
+*April 3, 2026 | 415 tests*
+
+### Features
+- **Profile picker (topbar).** Purple-accented chip with SVG user icon. Click
+  to open dropdown listing all profiles with gateway status dots (green =
+  running), model info, and skill count. Click any profile to switch; "Manage
+  profiles" link opens the sidebar panel.
+- **Profiles management panel.** New sidebar tab with full CRUD UI. Profile
+  cards show name, model/provider, skill count, API key status, and gateway
+  status badge. "Use" button switches profile, delete button removes non-default
+  profiles (with confirmation).
+- **Profile creation.** "+ New profile" form with name validation (`[a-z0-9_-]`),
+  optional "clone config from active" checkbox. Wraps the CLI's
+  `hermes_cli.profiles.create_profile()`.
+- **Profile deletion.** Confirm dialog. Auto-switches to default if deleting
+  the active profile. Blocked while agent is running.
+- **Seamless profile switching.** No server restart. Profile switch updates
+  `HERMES_HOME`, patches module-level caches in hermes-agent's `skills_tool`
+  and `cron/jobs`, reloads `.env` API keys and `config.yaml`, refreshes the
+  model dropdown, skills, memory, and cron panels.
+- **Per-session profile tracking.** `profile` field on Session records which
+  profile was active at creation. Backward-compatible (`null` for old sessions).
+
+### Bug Fixes
+- **Hardcoded `~/.hermes` paths.** Memory read/write and model discovery used
+  hardcoded paths. Now resolved through `get_active_hermes_home()`.
+- **Module-level path caching.** hermes-agent modules snapshot `HERMES_HOME`
+  at import time. Profile switch now monkey-patches `SKILLS_DIR`, `CRON_DIR`,
+  `JOBS_FILE`, `OUTPUT_DIR` so they track the active profile.
+
+### Architecture
+- New `api/profiles.py`: profile state management wrapping `hermes_cli.profiles`.
+  Thread-safe (`_profile_lock`). Lazy imports avoid circular deps.
+- `api/config.py`: module-level `cfg` replaced with reloadable `get_config()`
+  / `reload_config()`. Dynamic `_get_config_path()` resolves through profile.
+- `api/streaming.py`: `HERMES_HOME` added to env save/restore block.
+- Profile switch blocked while agent streams are active.
+- 5 new API endpoints: `GET /api/profiles`, `GET /api/profile/active`,
+  `POST /api/profile/switch`, `POST /api/profile/create`,
+  `POST /api/profile/delete`.
+- Zero modifications to hermes-agent code.
+
+---
+
+## [v0.23] Sprint 21 -- Mobile Responsive + Docker
+*April 3, 2026 | 415 tests*
+
+### Features
+- **Mobile responsive layout (Issue #21).** Full mobile experience with
+  hamburger sidebar (slide-in overlay), bottom navigation bar (5-tab iOS
+  pattern), and files slide-over panel. Touch targets minimum 44px. Composer
+  positioned above bottom nav. Session clicks auto-close sidebar. Desktop
+  layout completely unchanged — all mobile elements hidden via `@media`.
+- **Docker support (Issue #7).** Dockerfile (`python:3.12-slim`), docker-compose.yml
+  with named volume for state persistence, optional `~/.hermes` mount for
+  agent features. Binds to `127.0.0.1` by default for security.
+
+### Bug Fixes (from review)
+- **CSS cascade broke mobile slide-in.** `position:relative` rules after the
+  media query overrode `position:fixed` on mobile. Wrapped in `@media(min-width:641px)`.
+- **mobileSwitchPanel() always reopened sidebar.** Chat tab now closes sidebar
+  instead of reopening it over the main chat area.
+- **Dockerfile missing pip install.** Added `pip install -r requirements.txt`.
+- **No .dockerignore.** Added exclusions for `.git`, `tests/`, `.env*`.
+- **docker-compose tilde expansion.** Changed `~/.hermes` default to
+  `${HOME}/.hermes` (Docker Compose doesn't shell-expand `~`).
+
+### Architecture
+- Mobile navigation functions in `boot.js`: `toggleMobileSidebar()`,
+  `closeMobileSidebar()`, `toggleMobileFiles()`, `mobileSwitchPanel()`.
+- `sessions.js`: `closeMobileSidebar()` called after session click.
+- 69 new CSS lines in `@media(max-width:640px)` block.
+- New files: `Dockerfile`, `docker-compose.yml`, `.dockerignore`.
+
+---
+
+## [v0.22] Sprint 20 -- Voice Input + Send Button Polish
+*April 3, 2026 | 415 tests*
+
+### Features
+- **Voice input via Web Speech API.** Microphone button in the composer.
+  Tap to start recording, tap again (or send) to stop. Live interim
+  transcription appears in the textarea. Auto-stops after ~2s of silence.
+  Final text stays editable before sending. Appends to existing textarea
+  content rather than replacing it. Button hidden when browser doesn't
+  support Web Speech API. No API keys, no external libraries, no server
+  changes. Works in Chrome, Edge, Safari (partial). Firefox unsupported
+  (button stays hidden).
+- **Send button polish.** Send button redesigned as a 34px icon-only circle
+  with upward arrow SVG. Hidden by default — appears with pop-in spring
+  animation when textarea has content or files are attached. Disappears
+  on send or when content is cleared. Hidden while agent is responding.
+  Blue fill (#7cb9ff) with glow, scale hover/active for tactile feedback.
+
+### Architecture
+- Voice input IIFE in `boot.js`: SpeechRecognition lifecycle with
+  `continuous=false`, `interimResults=true`, error handling via `showToast()`.
+- `_prefix` variable snapshots existing textarea content on recording start
+  so dictation appends rather than overwrites.
+- `btnSend.onclick` stops active recognition before sending (send guard).
+- CSS: `.mic-btn`, `.mic-btn.recording` (red pulse), `.mic-status`,
+  `.mic-dot`, `@keyframes mic-pulse`.
+- `updateSendBtn()` in `ui.js` tracks textarea content, pending files,
+  and busy state. Hooked into `setBusy()`, `renderTray()`, `autoResize()`,
+  and input event listener.
+- CSS: `.send-btn` redesigned (circle, glow), `.send-btn.visible` +
+  `@keyframes send-pop-in` (spring animation).
+
+### Tests
+- 52 new tests in `test_sprint20.py`: voice input HTML, CSS, JS, append
+  behaviour, error handling, regressions.
+- 33 new tests in `test_sprint20b.py`: send button HTML, CSS, JS,
+  animation, visibility logic, regressions. Total: **415 tests**.
+
+---
+
+## [v0.21] Sprint 19 -- Auth + Security Hardening
+*April 3, 2026 | 328 tests*
+
+### Features
+- **Password authentication (Issue #23).** Optional password auth, off by default.
+  Enable via `HERMES_WEBUI_PASSWORD` env var or Settings panel. Password-only
+  (single-user app). Signed HMAC HTTP-only cookie with 24h TTL. Minimal dark-themed
+  login page at `/login`. API calls without auth return 401; page loads redirect.
+  New `api/auth.py` module with hashing, verification, session management.
+- **Security headers.** All responses now include `X-Content-Type-Options: nosniff`,
+  `X-Frame-Options: DENY`, `Referrer-Policy: same-origin`.
+- **POST body size limit.** Non-upload POST bodies capped at 20MB via `read_body()`.
+- **Settings panel additions.** "Access Password" field and "Sign Out" button
+  (only visible when auth is active).
+
+### Architecture
+- New `api/auth.py`: password hashing (SHA-256 + STATE_DIR salt), signed cookies,
+  auth middleware, public path allowlist.
+- Auth check in `server.py` do_GET/do_POST before routing.
+- `password_hash` added to `_SETTINGS_DEFAULTS`.
+
+### Tests
+- 10 new tests in `test_sprint19.py`: auth status, login flow, security headers,
+  cache-control, settings password field, request size limit. Total: **328 tests (328 passing)**.
+
+---
+
+## [v0.20] Sprint 18 -- File Preview Auto-Close + Thinking Display + Workspace Tree
+*April 3, 2026 | 318 tests*
+
+### Features
+- **File preview auto-close on directory navigation.** When viewing a file in
+  the right panel and navigating directories (breadcrumbs, up button, folder
+  clicks), the preview now automatically closes instead of showing stale
+  content. `clearPreview()` extracted as named function and called from
+  `loadDir()`. Unsaved preview edits prompt for confirmation before discarding.
+- **Thinking/reasoning display.** Assistant messages with structured content
+  arrays containing `type:'thinking'` or `type:'reasoning'` blocks (Claude
+  extended thinking, o3 reasoning) now render as collapsible gold-themed cards
+  above the response text. Collapsed by default. Click the header to expand and
+  see the model's reasoning process. Uses `esc()` on all content for XSS safety.
+- **Workspace tree view (Issue #22).** Directories expand/collapse in-place
+  with toggle arrows. Single-click toggles a directory open/closed. Double-click
+  navigates into it (breadcrumb view). Subdirectory contents fetched lazily from
+  the API and cached in `S._dirCache`. Nesting depth shown via indentation.
+  Empty directories show "(empty)" placeholder. Breadcrumb navigation still
+  works alongside the tree view.
+
+### Bug Fixes
+- **Stale tree cache on session switch.** `S._dirCache` and `S._expandedDirs`
+  are now cleared when navigating to the root directory, preventing session B
+  from showing session A's cached file listings.
+- **clearPreview() discards unsaved edits.** Navigation now checks
+  `_previewDirty` and prompts before discarding unsaved preview changes.
+
+### Architecture
+- `clearPreview()` extracted from inline handler to named function in `boot.js`.
+- Thinking card styles added to `style.css` (gold-themed, collapsible).
+- Tree toggle and empty-directory styles added to `style.css`.
+
+---
+
+## [v0.19] Sprint 17 -- Workspace Polish + Slash Commands + Settings
+*April 3, 2026 | 318 tests*
+
+### Features
+- **Workspace breadcrumb navigation.** Clicking into subdirectories now shows a
+  breadcrumb path bar (e.g. `~ / src / components`) with clickable segments to
+  navigate back. An "up" button appears in the panel header when inside a
+  subdirectory. File operations (rename, delete, new file/folder) stay in the
+  current directory instead of jumping back to root. Foundation for Issue #22
+  (tree view).
+- **Slash commands.** Type `/` in the composer to see an autocomplete dropdown
+  of built-in commands. New `commands.js` module with command registry. Built-in
+  commands: `/help`, `/clear`, `/model <name>`, `/workspace <name>`, `/new`.
+  Arrow keys navigate, Tab/Enter select, Escape closes. Unrecognized commands
+  pass through to the agent normally.
+- **Send key setting (Issue #26).** New setting in Settings panel to choose
+  between Enter (default) and Ctrl/Cmd+Enter as the send key. Persisted to
+  `settings.json` via the existing settings API. Setting loads on boot.
+  Server-side validation ensures only valid values (`enter`, `ctrl+enter`).
+
+### Architecture
+- New `static/commands.js` module (7th JS module): command registry, parser,
+  autocomplete dropdown, and built-in command handlers.
+- `send_key` added to `_SETTINGS_DEFAULTS` in `api/config.py` with enum validation
+  (`_SETTINGS_ENUM_VALUES` rejects unknown values server-side).
+- `S.currentDir` state tracking added to `ui.js` for workspace navigation.
+
+### Tests
+- 6 new tests in `test_sprint17.py`: send_key default, round-trip save with
+  cleanup, invalid value rejection, unknown key ignored, commands.js served,
+  workspace root listing. Total: **318 passed**.
+
+---
+
+## [v0.18.1] Safe HTML Rendering + Sprint 16 Tests
+*April 2, 2026 | 289 tests*
+
+### Features
+- **Safe HTML rendering in AI responses.** AI models sometimes emit HTML tags
+  (`<strong>`, `<em>`, `<code>`, `<br>`) in their responses. Previously these
+  showed as literal escaped text. A new pre-pass in `renderMd()` converts safe
+  HTML tags to markdown equivalents before the pipeline runs. Code blocks and
+  backtick spans are stashed first so their content is never touched.
+- **`inlineMd()` helper.** New function for processing inline formatting inside
+  list items, blockquotes, and headings. The old code called `esc()` directly,
+  which escaped tags that had already been converted by the pre-pass.
+- **Safety net.** After the full pipeline, any HTML tags not in the output
+  allowlist (`SAFE_TAGS`) are escaped via `esc()`. XSS fully blocked -- 7
+  attack vectors tested.
+- **Active session gold style.** Active session uses gold/amber (`#e8a030`)
+  instead of blue, matching the logo gradient. Project border-left skipped
+  when active (gold always wins).
+
+### Tests
+- **74 new tests** in `test_sprint16.py`: static analysis (6), behavioral (10),
+  exact regression (1), XSS security (7), edge cases (51). Total: 289 passed.
+
+---
+
+## [v0.18] Sprint 16 -- Session Sidebar Visual Polish
+*April 2, 2026 | 237 tests*
+
+### Features
+- **SVG action icons.** Replaced all emoji HTML entities (star, folder, box,
+  duplicate, trash) with monochrome SVG line icons that inherit `currentColor`.
+  Consistent rendering across macOS, Linux, and Windows. Defined in a top-level
+  `ICONS` constant in `sessions.js`.
+- **Action buttons overlay.** All session action buttons (pin, move, archive,
+  duplicate, trash) wrapped in a `.session-actions` container with
+  `position:absolute`. Titles now use full available width instead of being
+  truncated by invisible buttons. Actions appear on hover with a gradient fade
+  from the right edge. Overlay auto-hides during inline rename via
+  `:has(.session-title-input)`.
+- **Pin indicator.** Small gold filled-star icon rendered inline before the
+  title only when pinned. Unpinned sessions get full title width with zero
+  space reservation.
+- **Project border indicator.** Sessions assigned to a project show a colored
+  left border matching the project color, replacing the old always-visible
+  blue folder button.
+
+### Bug Fixes
+- **Session title truncation.** Action icons reserved ~30px of space even when
+  invisible, truncating titles. Fixed by overlay container approach.
+- **Folder button felt sticky.** Replaced `.has-project` persistent blue button
+  with colored left border. Folder button now only appears in hover overlay.
+
+---
+
+## [v0.17.3] Bug Fixes
+*April 2, 2026*
+
+### Bug Fixes
+- **NameError crash in model discovery.** `logger.debug()` was called in the
+  custom endpoint `except` block in `config.py`, but `logger` was never
+  imported. Every failed custom endpoint fetch crashed with `NameError`,
+  returning HTTP 500 for `/api/models`. Replaced with silent `pass` since
+  unreachable endpoints are expected. (PR #24)
+- **Project picker clipping and width.** Picker was clipped by
+  `overflow:hidden` on ancestor elements. Width calculation improved with
+  dynamic sizing (min 160px, max 220px). Event listener `close` handler
+  moved after DOM append to fix reference-before-definition. Reordered
+  `picker.remove()` before `removeEventListener` for correct cleanup. (PR #25)
+
+---
+
 ## [v0.17.2] Model Update
 *April 2, 2026*
 
@@ -509,4 +1098,4 @@ Three-panel layout: sessions sidebar, chat area, workspace panel.
 
 ---
 
-*Last updated: v0.16.2, April 1, 2026 | Tests: 247*
+*Last updated: v0.30.1, April 4, 2026 | Tests: 424*

Dockerfile

@@ -0,0 +1,23 @@
+FROM python:3.12-slim
+
+LABEL maintainer="nesquena"
+LABEL description="Hermes Web UI — browser interface for Hermes Agent"
+
+WORKDIR /app
+
+# Copy source
+COPY . /app
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Default to binding all interfaces (required for container networking)
+ENV HERMES_WEBUI_HOST=0.0.0.0
+ENV HERMES_WEBUI_PORT=8787
+
+# State directory (mount as volume for persistence)
+ENV HERMES_WEBUI_STATE_DIR=/data
+
+EXPOSE 8787
+
+CMD ["python", "server.py"]

HERMES.md

@@ -0,0 +1,375 @@
+# Why Hermes
+
+Hermes is a persistent, autonomous AI agent that lives on your server. It remembers everything,
+schedules work while you sleep, and gets more capable the longer it runs. This document explains
+the mental model, why that matters, and how Hermes compares to every major AI tool available today.
+
+---
+
+## The Core Idea: Assistants Forget. Agents Don't.
+
+Every time you open Claude Code, Codex, or a chat window, the tool starts from zero. It does not
+know who you are, what you worked on yesterday, how your repo is structured, or what bugs you
+already fixed. You re-explain yourself every single session. The tool is powerful in the moment
+and useless the next day.
+
+Hermes fills that gap. It runs on your server, retains context across every session, and acts
+on your behalf whether or not you are at a keyboard.
+
+```
+Assistant model:  You -> [Tool] -> Answer -> Done
+                  (tool forgets everything when the window closes)
+
+Agent model:      You <-> [Hermes] <-> (memory, skills, schedule, tools)
+                  (persistent, learns your stack, acts on your behalf, runs while you're offline)
+```
+
+---
+
+## The Three Pillars
+
+### 1. Memory That Compounds
+
+Hermes has layered memory that survives every session, every reboot, every model swap:
+
+- **User profile** -- who you are, your preferences, your communication style, things you've
+  corrected Hermes on
+- **Agent memory** -- facts about your environment, your toolchain, your project conventions
+- **Skills** -- reusable procedures Hermes discovers and saves; it never has to relearn how to
+  deploy your app, run your tests, or review a PR
+- **Session history** -- every past conversation is searchable; Hermes can recall what you
+  worked on last Tuesday
+
+When you correct Hermes, it remembers. When it solves a tricky problem, it saves the approach.
+When it learns your stack, that knowledge carries into every future session.
+
+### 2. Autonomous Scheduling
+
+Hermes can run jobs without you present -- every hour, every morning, on any cron schedule.
+It fires up a fresh session, runs the task, and delivers the result to wherever you want it:
+Telegram, Discord, Slack, Signal, WhatsApp, SMS, email, and more.
+
+Things Hermes can do while you sleep:
+
+- Review new pull requests on your GitHub repo and post a full verdict comment
+- Send you a morning briefing of news, markets, or anything else you care about
+- Run your test suite and alert you if something breaks
+- Watch a competitor's blog for new posts and summarize them
+- Monitor a datasource and notify you when a threshold is crossed
+
+### 3. Reach It From Anywhere
+
+Hermes runs on your server and is reachable from every surface: terminal over SSH, the web UI
+(this project), and messaging apps including Telegram, Discord, Slack, WhatsApp, Signal, and
+Matrix. Start a task from your phone, check it from the browser on your laptop, continue it in
+a terminal on a remote server. The same agent, memory, and history follow you everywhere.
+
+---
+
+## A Framework for AI Tools
+
+There are four distinct categories of AI tool. Understanding the category tells you what a tool
+can and cannot do.
+
+### Category 1: Chat Assistants
+*Claude.ai, ChatGPT, Gemini*
+
+You open a window, ask something, get an answer. No persistent memory beyond the conversation,
+no ability to run code or touch files, no way to act on your behalf. Excellent for Q&A,
+drafting, and brainstorming. You re-explain your context every session.
+
+### Category 2: IDE Integrations
+*GitHub Copilot, Cursor, Windsurf, Zed AI*
+
+Deep inside your editor. Autocomplete, inline diffs, refactors -- all excellent. Windsurf was
+earliest with workspace-scoped memory (Cascade Memories); Copilot has been shipping repo-level
+memory since late 2025 and is catching up. Cursor has no native memory as of early 2026. None
+have scheduling or messaging access. Tied to one machine and one editor.
+
+### Category 3: Agentic CLI Tools
+*Claude Code, Codex CLI, OpenCode, Aider*
+
+The current frontier for most developers. Can use real tools -- run shell commands, read and
+write files, search the web, call APIs. Great for deep, multi-step tasks in a single terminal
+session. All are adding memory and scheduling features to varying degrees (see comparisons below),
+but the core model is still session-scoped: you invoke it, it works, it stops.
+
+### Category 4: Persistent Autonomous Agents
+*Hermes, OpenClaw (as of early 2026)*
+
+All the tool use of Category 3, plus memory that accumulates across sessions, plus always-on
+scheduling, plus multi-modal access from any device or messaging app. Gets more useful over time
+rather than resetting to zero. Hermes and OpenClaw are the two primary open-source, self-hosted
+tools in this category. OpenClaw is a gateway-centric automation platform; Hermes is a
+self-improving agent that writes and reuses its own procedures from experience.
+
+---
+
+## How Hermes Compares
+
+### vs. OpenClaw
+
+OpenClaw is the most direct comparison to Hermes and the question most people ask first.
+Both are open-source, self-hosted, always-on agents with persistent memory, cron scheduling,
+and messaging app integration. If you're evaluating Hermes, you should evaluate OpenClaw too.
+
+OpenClaw (MIT, ~347k GitHub stars) is built around a **Gateway** control plane written in
+Node.js/TypeScript. It excels at broad personal automation: native Chrome/Chromium control for
+browser automation, the widest messaging platform support in the space (WhatsApp, Telegram,
+Signal, iMessage, LINE, WeChat, Slack, Discord, Teams, Matrix, and more), voice wake words,
+and a ClawHub skill marketplace where users share pre-built automations. The community is large
+and the ecosystem is growing fast.
+
+Hermes takes a different approach. It is built in Python and centers on a **self-improving
+agent loop** rather than a gateway control plane. The core difference is in how skills work:
+OpenClaw skills are primarily human-authored plugins installed from a marketplace; Hermes
+**writes and saves its own skills automatically** as part of every session. When Hermes solves
+a problem a new way, it saves the procedure and reuses it going forward without any user effort.
+
+Beyond the skills architecture, there are two other practical differences worth knowing:
+
+**Stability.** OpenClaw's community forums and GitHub issues document a recurring pattern of
+update-breaking regressions -- for example, Telegram integration was broken across multiple
+releases in early 2026. The unofficial WhatsApp Web protocol OpenClaw uses is known to
+disconnect and requires periodic re-pairing (this is documented in OpenClaw's own FAQ).
+Hermes has had no equivalent release breakages.
+
+**Security.** ClawHub's open publishing model has been exploited repeatedly. A community audit
+identified over a thousand malicious skills in the marketplace including prompt injections and
+tool-poisoning payloads; the community-maintained awesome-openclaw-skills list tracks confirmed
+removals and flags known bad actors. Hermes has no third-party marketplace and a correspondingly
+smaller attack surface.
+
+**OpenClaw's genuine strengths** are worth stating plainly: it has broader messaging coverage
+(iMessage, LINE, WeChat, Teams -- platforms Hermes does not support), native browser and
+computer control via Chrome CDP, voice wake words on macOS and iOS, a larger community, and
+more third-party integrations than Hermes. If those capabilities matter most to you, OpenClaw
+is worth a serious look.
+
+Where Hermes is the better fit: you want an agent that self-improves from experience without
+manual plugin authoring, you work in Python and want access to the ML/data science ecosystem,
+you want a stable deployment that does not break between updates, or you want a full web chat
+UI rather than a monitoring dashboard.
+
+| | OpenClaw | Hermes |
+|---|---|---|
+| Persistent memory | Yes | Yes |
+| Scheduled jobs (cron) | Yes | Yes |
+| Messaging app access | Yes (15+ platforms, incl. iMessage/WeChat) | Yes (10+ platforms) |
+| Web UI | Gateway dashboard (monitoring only) | Full three-panel chat UI |
+| Self-hosted | Yes | Yes |
+| Open source | Yes (MIT) | Yes |
+| Self-improving skills | Partial (AI can generate skills; not the default loop) | Yes (automatic, first-class) |
+| Browser / computer control | Yes (native Chrome CDP) | Via shell / tools |
+| Voice wake words | Yes (macOS/iOS) | No |
+| Python / ML ecosystem | No (Node.js) | Yes |
+| Orchestrates Claude Code / Codex | No | Yes |
+| Multi-profile support | Via binding-rule routing | Yes (first-class named profiles) |
+| Provider-agnostic | Yes | Yes |
+| Update reliability | Moderate (documented regressions) | High |
+
+### vs. Claude Code (Anthropic)
+
+Claude Code is Anthropic's official agentic CLI and one of the best tools in Category 3.
+In a single focused session it is capable -- deep code understanding, shell access, file
+editing, multi-step reasoning.
+
+Claude Code has been adding features rapidly and the gap is narrowing:
+
+- **Hooks system** -- 13 event types (SessionStart, PreToolUse, PostToolUse, Stop, etc.) with
+  4 handler types (shell command, HTTP endpoint, LLM prompt, sub-agent); deterministic
+  non-LLM control over the agent lifecycle
+- **Plugins / Skills** -- installable via `/plugin install`, hot-reloaded from `~/.claude/skills`,
+  with a marketplace; skills and slash commands unified as of v2.1.0
+- **Scheduling** -- `/loop` (session-scoped), cloud-managed cron via `claude.ai/code/scheduled`
+  (Anthropic infrastructure, minimum interval applies), and desktop app automations
+- **Messaging channels** -- Telegram, Discord, iMessage, and webhooks via the Channels feature
+  (research preview, v2.1.80+); deep Slack integration that triggers cloud sessions and creates PRs
+- **Claude Cowork** -- a separate product for knowledge workers; connects to 38+
+  services via MCP including Slack, Gmail, Microsoft Teams, Notion, Jira, Salesforce, and more
+- **Memory** -- CLAUDE.md and MEMORY.md for project-level context; auto-memory rolling out
+
+These are real features. The key differences that remain:
+
+- Claude Code's scheduling runs on **Anthropic's cloud** (or requires the desktop app open),
+  not a self-hosted server; cloud jobs have a minimum interval and your data leaves your hardware
+- Memory is **project-file-based** (CLAUDE.md / MEMORY.md), not a knowledge graph that
+  accumulates automatically across all your work; auto-memory is still rolling out
+- **Not provider-agnostic** -- routes through Bedrock or Vertex but always hits a Claude model;
+  you cannot switch to GPT, Gemini, or a local model
+- **Not open source** -- proprietary; the CLI ships obfuscated JavaScript
+- Messaging channels are a **research preview** requiring Bun runtime; not yet production-grade
+
+Hermes can use Claude Code as a sub-agent. For large implementation tasks, Hermes can spawn
+Claude Code to handle the heavy lifting and fold the result back into its own memory and history.
+
+| | Claude Code | Hermes |
+|---|---|---|
+| Persistent memory (automatic) | Partial (CLAUDE.md / MEMORY.md, rolling out) | Yes |
+| Skills / hooks system | Yes (Hooks + Plugin/Skills marketplace) | Yes (auto-generated from experience) |
+| Scheduled jobs (self-hosted) | No (cloud or desktop-app only) | Yes |
+| Messaging access | Partial (Telegram/Discord/iMessage via research preview; Slack native) | Yes (10+ platforms, production) |
+| Cowork connectors (Slack, Gmail, etc.) | Yes (via Claude Cowork, separate product) | Via agent tool use |
+| Web UI | Yes (claude.ai/code, Anthropic-hosted) | Yes (self-hosted) |
+| Provider-agnostic | No (Claude models only, via Bedrock/Vertex) | Yes (any provider) |
+| Self-hosted scheduling | No | Yes |
+| Open source | No | Yes |
+| Runs as sub-agent of Hermes | Yes | N/A |
+
+### vs. Codex CLI (OpenAI)
+
+Codex CLI is OpenAI's open-source agentic terminal tool (Apache 2.0, ~73k GitHub stars). It
+supports 10+ providers including Anthropic, Google, Mistral, Groq, and local models via Ollama.
+It added persistent session memory in v0.100.0 with `codex resume`. The desktop app has an
+Automations feature for scheduled local tasks.
+
+The CLI itself has no native scheduling (open feature request as of early 2026). Memory is
+session-history-based rather than a living knowledge graph. No messaging app access. A strong
+tool for single-session coding; Hermes adds the always-on layer on top.
+
+| | Codex CLI | Hermes |
+|---|---|---|
+| Persistent memory | Partial (session history + AGENTS.md) | Yes (automatic, layered) |
+| Scheduled jobs | Partial (desktop app only; CLI has none) | Yes |
+| Messaging app access | No | Yes |
+| Web UI | No | Yes (self-hosted) |
+| Provider-agnostic | Yes (10+ providers) | Yes (10+ providers) |
+| Self-hosted | Yes | Yes |
+| Open source | Yes (Apache 2.0) | Yes |
+
+### vs. OpenCode
+
+OpenCode is an open-source TUI agentic coding assistant, provider-agnostic across 75+ providers.
+It has a WebUI embedded in its binary and an official desktop app. It uses SQLite for session
+history and AGENTS.md for project context.
+
+No native scheduled jobs (a community background plugin exists), no first-party messaging
+integration (community Telegram bots exist but require manual setup), and no automatic
+cross-session semantic memory. Good for interactive terminal coding sessions.
+
+| | OpenCode | Hermes |
+|---|---|---|
+| Persistent memory | Partial (session history + AGENTS.md) | Yes (automatic, layered) |
+| Scheduled jobs | No (community plugin only) | Yes |
+| Messaging app access | No (community Telegram bot only) | Yes (first-party, 10+ platforms) |
+| Web UI | Yes (embedded + desktop app) | Yes (self-hosted) |
+| Mobile access | No | Yes |
+| Skills system | No | Yes |
+| Provider-agnostic | Yes (75+ providers) | Yes |
+| Open source | Yes | Yes |
+
+### vs. Cursor / Windsurf / Copilot
+
+Category 2 tools -- exceptional at in-editor autocomplete, inline diffs, and code review.
+Not competing for the same job as Hermes, and they work well alongside it.
+
+Windsurf was earliest with workspace-scoped memory (Cascade Memories); Copilot has been
+shipping repo-level memory since late 2025. Cursor has no native cross-session memory as of
+early 2026. None have scheduling or messaging access.
+
+| | Cursor | Windsurf | Copilot | Hermes |
+|---|---|---|---|---|
+| In-editor autocomplete | Excellent | Excellent | Excellent | No |
+| Inline diff / refactor | Yes | Yes | Yes | Via shell |
+| Cross-session memory | No | Yes (workspace) | Partial (repo, early access) | Yes |
+| Scheduled background jobs | No | No | No | Yes |
+| Messaging app / mobile | No | No | No | Yes |
+| Terminal tool use | Limited | Limited | Limited | Full |
+| Self-hosted | No | No | No | Yes |
+| Provider-agnostic | Partial | Partial | No | Yes |
+| Open source | No | No | No | Yes |
+
+### vs. Claude.ai / ChatGPT
+
+Category 1. For drafting, Q&A, and brainstorming in the moment, both are excellent.
+
+Claude.ai memory has been improving -- it now generates memory from chat history, not just
+user-curated entries. Claude.ai can also execute code and read/write files in a sandboxed
+environment via Artifacts. These are real capabilities, just not the same as direct filesystem
+or shell access on your own server.
+
+| | Claude.ai / ChatGPT | Hermes |
+|---|---|---|
+| Memory across conversations | Yes (improving; auto-generated from history) | Yes (deep, automatic) |
+| Runs shell commands | No | Yes |
+| Code execution | Sandboxed (Artifacts) | Yes (full shell) |
+| Reads / writes files | Sandboxed (Artifacts) | Yes (full filesystem) |
+| Schedules background jobs | No | Yes |
+| Web UI | Yes | Yes |
+| Messaging apps | No | Yes |
+| Self-hosted | No | Yes |
+| Provider-agnostic | No | Yes |
+| Open source | No | Yes |
+
+---
+
+## The Compounding Advantage
+
+What matters most about Hermes is that it improves over time. That is the point.
+
+Every time Hermes encounters a new environment, it saves facts to memory. Every time it solves
+a problem a new way, it saves the approach as a skill. Every time you correct it, it updates its
+profile of you. Every session, every scheduled job, every tool call, the agent gets more
+calibrated to you and your workflow.
+
+A Claude Code session on day one and day one hundred are identical. A Hermes agent on day one
+and day one hundred is smarter about you -- it knows your stack, your conventions, your
+preferences, and the solutions that have worked before.
+
+---
+
+## Who Hermes Is For
+
+**Solo developers and power users** who don't want to re-explain their stack every session and
+want an AI that actually knows their environment.
+
+**Teams on a shared server** where multiple people want Claude-quality AI access without each
+paying for a separate subscription or running local tooling.
+
+**Automation-heavy workflows** where you want an AI running tasks on a schedule, delivering
+results to your phone, without babysitting it.
+
+**Privacy-conscious users** who want their conversations, memory, and files on their own
+hardware.
+
+**Multi-model users** who want to switch between OpenAI, Anthropic, Google, DeepSeek, and
+others based on cost, capability, or rate limits, without rebuilding their workflow each time.
+
+---
+
+## Scope and Limits
+
+**Hermes lives in the terminal, browser, and messaging apps.** For in-editor autocomplete and
+inline diffs, use Cursor or Windsurf alongside it -- they do that job better.
+
+**You run Hermes on your own server.** That means initial setup, but your data stays on your
+hardware and you control the schedule, the models, and the costs.
+
+**Hermes is an orchestration and memory layer.** It makes whatever model you point it at more
+useful over time. The models do the reasoning; Hermes makes sure that reasoning accumulates into
+something durable.
+
+---
+
+## Quick Reference
+
+| | OpenClaw | Claude Code | Codex CLI | OpenCode | Cursor | Claude.ai | Hermes |
+|---|---|---|---|---|---|---|---|
+| Persistent memory (auto) | Yes | Partial† | Partial | Partial | No | Yes (improving) | **Yes** |
+| Scheduled / background jobs | Yes | Partial‡ | Partial§ | No | No | No | **Yes (self-hosted)** |
+| Messaging app access | Yes (15+ platforms) | Partial (Telegram/Discord preview; Slack native) | No | No | No | No | **Yes (10+ platforms)** |
+| Web UI | Dashboard only | Yes (Anthropic cloud) | No | Yes | No | Yes | **Yes (self-hosted)** |
+| Skills system | Yes (marketplace) | Yes (Hooks + Plugins) | No | No | No | No | **Yes** |
+| Self-improving skills | Partial | No | No | No | No | No | **Yes** |
+| Browser / computer control | Yes (Chrome CDP) | No | No | No | No | No | Via shell |
+| Python / ML ecosystem | No (Node.js) | No | No | No | No | No | **Yes** |
+| In-editor autocomplete | No | No | No | No | Yes | No | No |
+| Orchestrates other agents | No | No | No | No | No | No | **Yes** |
+| Provider-agnostic | Yes | No (Claude only) | Yes | Yes | Partial | No | **Yes** |
+| Self-hosted | Yes | No | Yes | Yes | No | No | **Yes** |
+| Open source | Yes (MIT) | No | Yes | Yes | No | No | **Yes** |
+| Always-on / autonomous | Yes | No | No | No | No | No | **Yes** |
+
+† Claude Code has CLAUDE.md / MEMORY.md project context and rolling auto-memory, but not full automatic cross-session recall  
+‡ Claude Code scheduling: cloud-managed (Anthropic infrastructure) or desktop-app only; no self-hosted cron  
+§ Codex scheduling: desktop app Automations only; CLI has no native scheduling

README.md

@@ -10,9 +10,70 @@ and vanilla JS.
 Layout: three-panel Claude-style. Left sidebar for sessions and tools,
 center for chat, right for workspace file browsing.
 
-<img width="1392" height="854" alt="image" src="https://github.com/user-attachments/assets/79cd3c0d-3167-42ed-9434-447a742c25c3" />
+<img width="1392" alt="Hermes Web UI — three-panel layout" src="https://github.com/user-attachments/assets/79cd3c0d-3167-42ed-9434-447a742c25c3" />
 
-This gives you nearly **1:1 parity with Hermes CLI from a convenient web UI** which you can access securely through an SSH tunnel from your Hermes setup. Single command to start this up, and a single command to SSH tunnel for access on your computer. Every single part of the web UI leverages your existing Hermes agent, existing models, without requiring any setup.
+<table>
+  <tr>
+    <td width="50%" align="center">
+      <img alt="Workspace file browser with inline preview" src="docs/images/ui-workspace.png" />
+      <br /><sub>Workspace file browser with inline preview</sub>
+    </td>
+    <td width="50%" align="center">
+      <img alt="Session projects, tags, and tool call cards" src="docs/images/ui-sessions.png" />
+      <br /><sub>Session projects, tags, and tool call cards</sub>
+    </td>
+  </tr>
+</table>
+
+This gives you nearly **1:1 parity with Hermes CLI from a convenient web UI** which you can access securely through an SSH tunnel from your Hermes setup. Single command to start this up, and a single command to SSH tunnel for access on your computer. Every single part of the web UI uses your existing Hermes agent and existing models, without requiring any additional setup.
+
+---
+
+## Why Hermes
+
+Most AI tools reset every session. They don't know who you are, what you worked on, or what
+conventions your project follows. You re-explain yourself every time.
+
+Hermes retains context across sessions, runs scheduled jobs while you're offline, and gets
+smarter about your environment the longer it runs. It uses your existing Hermes agent setup,
+your existing models, and requires no additional configuration to start.
+
+What makes it different from other agentic tools:
+
+- **Persistent memory** — user profile, agent notes, and a skills system that saves reusable
+  procedures; Hermes learns your environment and does not have to relearn it
+- **Self-hosted scheduling** — cron jobs that fire while you're offline and deliver results to
+  Telegram, Discord, Slack, Signal, email, and more
+- **10+ messaging platforms** — the same agent available in the terminal is reachable from your phone
+- **Self-improving skills** — Hermes writes and saves its own skills automatically from experience;
+  no marketplace to browse, no plugins to install
+- **Provider-agnostic** — OpenAI, Anthropic, Google, DeepSeek, OpenRouter, and more
+- **Orchestrates other agents** — can spawn Claude Code or Codex for heavy coding tasks and bring
+  the results back into its own memory
+- **Self-hosted** — your conversations, your memory, your hardware
+
+**vs. the field** *(landscape is actively shifting — see [HERMES.md](HERMES.md) for the full breakdown)*:
+
+| | OpenClaw | Claude Code | Codex CLI | OpenCode | Hermes |
+|---|---|---|---|---|---|
+| Persistent memory (auto) | Yes | Partial† | Partial | Partial | Yes |
+| Scheduled jobs (self-hosted) | Yes | No‡ | No | No | Yes |
+| Messaging app access | Yes (15+ platforms) | Partial (Telegram/Discord preview) | No | No | Yes (10+) |
+| Web UI (self-hosted) | Dashboard only | No | No | Yes | Yes |
+| Self-improving skills | Partial | No | No | No | Yes |
+| Python / ML ecosystem | No (Node.js) | No | No | No | Yes |
+| Provider-agnostic | Yes | No (Claude only) | Yes | Yes | Yes |
+| Open source | Yes (MIT) | No | Yes | Yes | Yes |
+
+† Claude Code has CLAUDE.md / MEMORY.md project context and rolling auto-memory, but not full automatic cross-session recall  
+‡ Claude Code has cloud-managed scheduling (Anthropic infrastructure) and session-scoped `/loop`; no self-hosted cron
+
+**The closest competitor is OpenClaw** — both are always-on, self-hosted, open-source agents
+with memory, cron, and messaging. The key differences: Hermes writes and saves its own skills
+automatically as a core behavior (OpenClaw's skill system centers on a community marketplace);
+Hermes is more stable across updates (OpenClaw has documented release regressions and ClawHub
+has had security incidents involving malicious skills); and Hermes runs natively in the Python
+ecosystem. See [HERMES.md](HERMES.md) for the full side-by-side.
 
 ---
 
@@ -35,6 +96,44 @@ That is it. The script will:
 
 ---
 
+## Docker
+
+**Pre-built images** (amd64 + arm64) are published to GHCR on every release:
+
+```bash
+docker pull ghcr.io/nesquena/hermes-webui:latest
+docker run -d -p 8787:8787 -v ~/.hermes:/root/.hermes ghcr.io/nesquena/hermes-webui:latest
+```
+
+Or run with Docker Compose (recommended):
+
+```bash
+docker compose up -d
+```
+
+Or build locally:
+
+```bash
+docker build -t hermes-webui .
+docker run -d -p 8787:8787 -v ~/.hermes:/root/.hermes hermes-webui
+```
+
+Open http://localhost:8787 in your browser.
+
+To enable password protection:
+
+```bash
+docker run -d -p 8787:8787 -e HERMES_WEBUI_PASSWORD=your-secret -v ~/.hermes:/root/.hermes ghcr.io/nesquena/hermes-webui:latest
+```
+
+Session data persists in a named volume (`hermes-data`) across restarts.
+
+> **Note:** By default, Docker Compose binds to `127.0.0.1` (localhost only).
+> To expose on a network, change the port to `"8787:8787"` in `docker-compose.yml`
+> and set `HERMES_WEBUI_PASSWORD` to enable authentication.
+
+---
+
 ## What start.sh discovers automatically
 
 | Thing | How it finds it |
@@ -75,7 +174,8 @@ Full list of environment variables:
 | `HERMES_WEBUI_STATE_DIR` | `~/.hermes/webui-mvp` | Where sessions and state are stored |
 | `HERMES_WEBUI_DEFAULT_WORKSPACE` | `~/workspace` | Default workspace |
 | `HERMES_WEBUI_DEFAULT_MODEL` | `openai/gpt-5.4-mini` | Default model |
-| `HERMES_HOME` | `~/.hermes` | Base directory for Hermes state (affects all paths above) |
+| `HERMES_WEBUI_PASSWORD` | *(unset)* | Set to enable password authentication |
+| `HERMES_HOME` | `~/.hermes` | Base directory for Hermes state (affects all paths) |
 | `HERMES_CONFIG_PATH` | `~/.hermes/config.yaml` | Path to Hermes config file |
 
 ---
@@ -127,17 +227,18 @@ Tests discover the repo and the Hermes agent dynamically -- no hardcoded paths.
 
 ```bash
 cd hermes-webui
-python -m pytest tests/ -v
+pytest tests/ -v --timeout=60
 ```
 
 Or using the agent venv explicitly:
 
 ```bash
-/path/to/hermes-agent/venv/bin/python -m pytest tests/ -v   # or any Python with deps installed
+/path/to/hermes-agent/venv/bin/python -m pytest tests/ -v
 ```
 
 Tests run against an isolated server on port 8788 with a separate state directory.
-Production data and real cron jobs are never touched.
+Production data and real cron jobs are never touched. Current count: **424 tests**
+across 22 test files.
 
 ---
 
@@ -145,88 +246,150 @@ Production data and real cron jobs are never touched.
 
 ### Chat and agent
 - Streaming responses via SSE (tokens appear as they are generated)
-- Multi-provider model support -- any Hermes API provider (OpenAI, Anthropic, Google, DeepSeek, Nous Portal, OpenRouter); dynamic model dropdown populated from configured keys
+- Multi-provider model support -- any Hermes API provider (OpenAI, Anthropic, Google, DeepSeek, Nous Portal, OpenRouter, MiniMax, Z.AI); dynamic model dropdown populated from configured keys
 - Send a message while one is processing -- it queues automatically
 - Edit any past user message inline and regenerate from that point
 - Retry the last assistant response with one click
 - Cancel a running task from the activity bar
-- Tool call cards inline -- each shows the tool name, args, and result snippet
+- Tool call cards inline -- each shows the tool name, args, and result snippet; expand/collapse all toggle for multi-tool turns
+- Subagent delegation cards -- child agent activity shown with distinct icon and indented border
 - Mermaid diagram rendering inline (flowcharts, sequence diagrams, gantt charts)
+- Thinking/reasoning display -- collapsible gold-themed cards for Claude extended thinking and o3 reasoning blocks
 - Approval card for dangerous shell commands (allow once / session / always / deny)
 - SSE auto-reconnect on network blips (SSH tunnel resilience)
 - File attachments persist across page reloads
 - Message timestamps (HH:MM next to each message, full date on hover)
+- Code block copy button with "Copied!" feedback
+- Syntax highlighting via Prism.js (Python, JS, bash, JSON, SQL, and more)
+- Safe HTML rendering in AI responses (bold, italic, code converted to markdown)
 
 ### Sessions
 - Create, rename, duplicate, delete, search by title and message content
-- Pin/star sessions to the top of the sidebar
+- Pin/star sessions to the top of the sidebar (gold indicator)
 - Archive sessions (hide without deleting, toggle to show)
+- Session projects -- named groups with colors for organizing sessions
 - Session tags -- add #tag to titles for colored chips and click-to-filter
 - Grouped by Today / Yesterday / Earlier in the sidebar
 - Download as Markdown transcript, full JSON export, or import from JSON
 - Sessions persist across page reloads and SSH tunnel reconnects
 - Browser tab title reflects the active session name
+- CLI session bridge -- CLI sessions from hermes-agent's SQLite store appear in the sidebar with a gold "cli" badge; click to import with full history and reply normally
+- Token/cost display -- input tokens, output tokens, estimated cost shown per conversation (toggle in Settings or `/usage` command)
 
 ### Workspace file browser
-- Browse directory tree with type icons
+- Directory tree with expand/collapse (single-click toggles, double-click navigates)
+- Breadcrumb navigation with clickable path segments
 - Preview text, code, Markdown (rendered), and images inline
 - Edit, create, delete, and rename files; create folders
+- Binary file download (auto-detected from server)
+- File preview auto-closes on directory navigation (with unsaved-edit guard)
 - Right panel is drag-resizable
 - Syntax highlighted code preview (Prism.js)
 
+### Voice input
+- Microphone button in the composer (Web Speech API)
+- Tap to record, tap again or send to stop
+- Live interim transcription appears in the textarea
+- Auto-stops after ~2s of silence
+- Appends to existing textarea content (doesn't replace)
+- Hidden when browser doesn't support Web Speech API (Chrome, Edge, Safari)
+
+### Profiles
+- Profile picker in the topbar -- purple chip with dropdown showing all profiles
+- Gateway status dots (green = running), model info, skill count per profile
+- Profiles management panel -- create, switch, and delete profiles from the sidebar
+- Clone config from active profile on create
+- Seamless switching -- no server restart; reloads config, skills, memory, cron, models
+- Per-session profile tracking (records which profile was active at creation)
+
+### Authentication and security
+- Optional password auth -- off by default, zero friction for localhost
+- Enable via `HERMES_WEBUI_PASSWORD` env var or Settings panel
+- Signed HMAC HTTP-only cookie with 24h TTL
+- Minimal dark-themed login page at `/login`
+- Security headers on all responses (X-Content-Type-Options, X-Frame-Options, Referrer-Policy)
+- 20MB POST body size limit
+- CDN resources pinned with SRI integrity hashes
+
 ### Settings and configuration
-- Settings panel (gear icon in topbar) -- persist default model and default workspace server-side
+- Settings panel (gear icon) -- default model, default workspace, send key preference
+- Send key: Enter (default) or Ctrl/Cmd+Enter
+- Show/hide CLI sessions toggle (enabled by default)
+- Token usage display toggle (off by default, also via `/usage` command)
 - Cron completion alerts -- toast notifications and unread badge on Tasks tab
 - Background agent error alerts -- banner when a non-active session encounters an error
 
+### Slash commands
+- Type `/` in the composer for autocomplete dropdown
+- Built-in: `/help`, `/clear`, `/model <name>`, `/workspace <name>`, `/new`, `/usage`
+- Arrow keys navigate, Tab/Enter select, Escape closes
+- Unrecognized commands pass through to the agent
+
 ### Panels
-- **Chat** -- session list, search, pin, archive, new conversation
-- **Tasks** -- view, create, edit, run, pause/resume, delete cron jobs; completion alerts
-- **Skills** -- list all skills by category, search, preview, create/edit/delete
+- **Chat** -- session list, search, pin, archive, projects, new conversation
+- **Tasks** -- view, create, edit, run, pause/resume, delete cron jobs; run history; completion alerts
+- **Skills** -- list all skills by category, search, preview, create/edit/delete; linked files viewer
 - **Memory** -- view and edit MEMORY.md and USER.md inline
+- **Profiles** -- create, switch, delete agent profiles; clone config
 - **Todos** -- live task list from the current session
 - **Spaces** -- add, rename, remove workspaces; quick-switch from topbar
 
+### Mobile responsive
+- Hamburger sidebar -- slide-in overlay on mobile (<640px)
+- Bottom navigation bar -- 5-tab iOS-style fixed bar
+- Files slide-over panel from right edge
+- Touch targets minimum 44px on all interactive elements
+- Composer positioned above bottom nav
+- Desktop layout completely unchanged
+
 ---
 
 ## Architecture
 
 ```
-server.py               HTTP routing shell (~76 lines)
+server.py               HTTP routing shell + auth middleware (~81 lines)
 api/
-  routes.py             All GET + POST route handlers
-  config.py             Discovery + globals + model provider detection
-  helpers.py            HTTP helpers: j(), bad(), require(), safe_resolve()
-  models.py             Session model + CRUD
-  workspace.py          File ops: list_dir, read_file_content, workspace helpers
-  upload.py             Multipart parser, file upload handler
-  streaming.py          SSE engine, run_agent integration, cancel support
+  auth.py               Optional password authentication, signed cookies (~149 lines)
+  config.py             Discovery, globals, model detection, reloadable config (~702 lines)
+  helpers.py            HTTP helpers, security headers (~71 lines)
+  models.py             Session model + CRUD (~146 lines)
+  profiles.py           Profile state management, hermes_cli wrapper (~366 lines)
+  routes.py             All GET + POST route handlers (~1180 lines)
+  streaming.py          SSE engine, run_agent, cancel support (~272 lines)
+  upload.py             Multipart parser, file upload handler (~78 lines)
+  workspace.py          File ops, workspace helpers (~245 lines)
 static/
-  index.html            HTML template
-  style.css             All CSS
-  ui.js                 DOM helpers, renderMd, Mermaid, tool cards, file tree
-  workspace.js          File tree, preview, file ops
-  sessions.js           Session CRUD, list rendering, search, tags, archive
-  messages.js           send(), SSE event handlers, approval, transcript
-  panels.js             Cron, skills, memory, workspace, todo, switchPanel, alerts
-  boot.js               Event wiring + boot IIFE
+  index.html            HTML template (~364 lines)
+  style.css             All CSS incl. mobile responsive (~670 lines)
+  ui.js                 DOM helpers, renderMd, tool cards, file tree (~1002 lines)
+  workspace.js          File preview, file ops (~191 lines)
+  sessions.js           Session CRUD, list rendering, search (~556 lines)
+  messages.js           send(), SSE handlers, approval, transcript (~337 lines)
+  panels.js             Cron, skills, memory, profiles, settings (~1030 lines)
+  commands.js           Slash command autocomplete (~156 lines)
+  boot.js               Mobile nav, voice input, boot IIFE (~338 lines)
 tests/
-  conftest.py           Isolated test server (port 8788, separate HERMES_HOME)
-  test_sprint1-14.py    Feature tests per sprint
-  test_regressions.py   Permanent regression gate
+  conftest.py           Isolated test server (port 8788)
+  test_sprint{1-23}.py  22 test files, 426 test functions
+  test_regressions.py   Permanent regression gate (23 tests)
+Dockerfile              python:3.12-slim container image
+docker-compose.yml      Compose with named volume and optional auth
+.github/workflows/      CI: multi-arch Docker build + GitHub Release on tag
 ```
 
 State lives outside the repo at `~/.hermes/webui-mvp/` by default
-(sessions, workspaces, settings, last_workspace). Override with `HERMES_WEBUI_STATE_DIR`.
+(sessions, workspaces, settings, projects, last_workspace). Override with `HERMES_WEBUI_STATE_DIR`.
 
 ---
 
 ## Docs
 
+- `HERMES.md` -- why Hermes, mental model, and detailed comparison to Claude Code / Codex / OpenCode / Cursor
 - `ROADMAP.md` -- feature roadmap and sprint history
 - `ARCHITECTURE.md` -- system design, all API endpoints, implementation notes
 - `TESTING.md` -- manual browser test plan and automated coverage reference
-- `CHANGELOG.md` -- release notes
+- `CHANGELOG.md` -- release notes per sprint
+- `SPRINTS.md` -- forward sprint plan with CLI + Claude parity targets
 
 ## Repo
 

ROADMAP.md

@@ -3,8 +3,8 @@
 > Goal: Full 1:1 parity with the Hermes CLI experience via a clean dark web UI.
 > Everything you can do from the CLI terminal, you can do from this UI.
 >
-> Last updated: Sprint 15 / v0.17.1 (April 2, 2026)
-> Tests: 237 passing
+> Last updated: v0.29 (April 4, 2026)
+> Tests: 424 total (401 passing, 23 pre-existing failures)
 > Source: <repo>/
 
 ---
@@ -32,6 +32,14 @@
 | Sprint 13 | Alerts + polish | Cron completion alerts (polling + badge), background error banner, session duplicate, browser tab title | 221 |
 | Sprint 14 | Visual polish + workspace ops | Mermaid diagrams, message timestamps, file rename, folder create, session tags, session archive | 233 |
 | Sprint 15 | Session projects + code copy | Session projects/folders, code block copy button, tool card expand/collapse toggle | 237 |
+| Sprint 16 | Session sidebar visual polish | SVG action icons, overlay hover actions, pin indicator, project border, safe HTML rendering | 289 |
+| Sprint 17 | Workspace polish + slash commands + settings | Breadcrumb navigation, slash command autocomplete, send key setting (#26) | 318 |
+| Sprint 18 | Thinking display + workspace tree | File preview auto-close, thinking/reasoning cards, expandable directory tree (#22) | 318 |
+| Sprint 19 | Auth + security hardening | Password auth (off by default), login page, security headers, 20MB body limit (#23) | 328 |
+| Sprint 20 | Voice input + send button | Voice input (Web Speech API), send button icon-circle with pop-in animation | 415 |
+| Sprint 21 | Mobile responsive + Docker | Hamburger sidebar, bottom nav, files slide-over, Docker support (#21, #7) | 415 |
+| Sprint 22 | Multi-profile support | Profile picker, management panel, seamless switching, per-session tracking (#28) | 415 |
+| Sprint 23 | Agentic transparency | Token/cost display, subagent cards, skill picker in cron, skill linked files, workspace tree persistence, timestamp fixes | 424 |
 
 ---
 
@@ -39,10 +47,12 @@
 
 | Layer | Location | Status |
 |-------|----------|--------|
-| Python server | <repo>/server.py (~76 lines) + api/ modules (~1900 lines) | Thin shell + business logic in api/ |
-| HTML template | <repo>/static/index.html | Served from disk |
-| CSS | <repo>/static/style.css | Served from disk |
-| JavaScript | <repo>/static/{ui,workspace,sessions,messages,panels,boot}.js | 6 modules, ~2250 lines total |
+| Python server | <repo>/server.py (~81 lines) + api/ modules (~3210 lines) | Thin shell + auth middleware + business logic in api/ |
+| HTML template | <repo>/static/index.html (~364 lines) | Served from disk |
+| CSS | <repo>/static/style.css (~670 lines) | Served from disk, incl. mobile responsive |
+| JavaScript | <repo>/static/{ui,workspace,sessions,messages,panels,boot,commands}.js | 7 modules, ~3610 lines total |
+| Docker | Dockerfile, docker-compose.yml, .dockerignore | python:3.12-slim, multi-arch (amd64+arm64) |
+| CI/CD | .github/workflows/release.yml | Auto-release + GHCR publish on tag push |
 | Runtime state | ~/.hermes/webui-mvp/sessions/ | Session JSON files |
 | Test server | Port 8788, state dir ~/.hermes/webui-mvp-test/ | Isolated, wiped per run |
 | Production server | Port 8787 | SSH tunnel from Mac |
@@ -55,6 +65,7 @@
 - [x] Send messages, get SSE-streaming responses
 - [x] Switch models per session (10 models, grouped by provider)
 - [x] Multi-provider API support: use any Hermes agent API provider (OpenAI, Anthropic, Google, etc.) directly, not just OpenRouter (Sprint 11)
+- [x] Custom endpoint model discovery: auto-detect models from Ollama, LM Studio, and other local LLM servers via base_url (PR #18)
 - [x] Upload files to workspace (drag-drop, click, clipboard paste)
 - [x] File tray with remove button
 - [x] Tool progress shown in activity bar above composer
@@ -66,7 +77,7 @@
 - [x] Copy message to clipboard (hover icon on each bubble)
 - [x] Edit last user message and regenerate
 - [ ] Branch/fork conversation (Wave 3)
-- [ ] Token/cost estimate per message (Wave 3)
+- [x] Token/cost estimate per message (Sprint 23)
 
 ### Tool Visibility
 - [x] Tool progress in activity bar (moved out of composer footer)
@@ -127,7 +138,7 @@
 - [x] Edit existing cron job
 - [x] Delete cron job
 - [x] View full cron run history (expandable per job)
-- [ ] Skill picker in cron create form (Wave 3)
+- [x] Skill picker in cron create form (Sprint 23)
 
 ### Skills
 - [x] List all skills grouped by category (Skills sidebar tab)
@@ -136,7 +147,7 @@
 - [x] Create skill
 - [x] Edit skill
 - [x] Delete skill
-- [ ] View skill linked files (Wave 3)
+- [x] View skill linked files (Sprint 23)
 
 ### Memory
 - [x] View personal notes (MEMORY.md) rendered as markdown (Memory tab)
@@ -146,22 +157,48 @@
 
 ### Configuration
 - [x] Settings panel (default model, default workspace) (Sprint 12)
+- [x] Send key preference (Enter or Ctrl+Enter) (Sprint 17)
+- [x] Password authentication (Sprint 19)
 - [ ] Enable/disable toolsets per session (deferred)
 
 ### Notifications
 - [x] Cron job completion alerts (Sprint 13)
 - [x] Background agent error alerts (Sprint 13)
 
+### Workspace
+- [x] Breadcrumb navigation in subdirectories (Sprint 17)
+- [x] Workspace tree view with expand/collapse (Sprint 18, Issue #22)
+- [x] File preview auto-close on directory navigation (Sprint 18)
+
+### Slash Commands
+- [x] Command registry + autocomplete dropdown (Sprint 17)
+- [x] Built-in: /help, /clear, /model, /workspace, /new (Sprint 17)
+
+### Security
+- [x] Password auth with signed cookies (Sprint 19, Issue #23)
+- [x] Security headers (X-Content-Type-Options, X-Frame-Options) (Sprint 19)
+- [x] POST body size limit (20MB) (Sprint 19)
+
+### Thinking / Reasoning
+- [x] Collapsible thinking cards for extended-thinking models (Sprint 18)
+
+### Voice
+- [x] Voice input via Web Speech API (Sprint 20)
+
+### Mobile
+- [x] Mobile responsive layout — hamburger sidebar, bottom nav, files slide-over (Sprint 21)
+
+### Profiles
+- [x] Multi-profile support — create, switch, delete profiles (Sprint 22, Issue #28)
+
 ### Advanced / Future
-- [ ] Voice input via Whisper (Wave 6)
-- [ ] TTS playback of responses (Wave 6)
-- [ ] Subagent delegation cards (Wave 6)
+- [ ] TTS playback of responses (deferred)
+- [ ] Subagent delegation cards (deferred)
 - [x] Background task cancel (activity bar Cancel button)
-- [ ] Code execution cell (Wave 6)
-- [ ] Password authentication (Wave 7)
-- [ ] HTTPS / reverse proxy (Wave 7)
-- [ ] Mobile responsive layout (Wave 7)
-- [ ] Virtual scroll for large lists (Wave 7)
+- [ ] Code execution cell (deferred)
+- [ ] Desktop application (deferred)
+- [ ] Extended slash command / skill integration (deferred)
+- [ ] Virtual scroll for large lists (deferred)
 
 ---
 
@@ -238,81 +275,29 @@ Enter saves, Escape cancels. Topbar updates immediately.
 
 ---
 
-## Wave 3: Power Features and Developer Experience
+## Completed Waves (Summary)
 
-### Sprint 3.1: Tool Call Visibility Inline
-Show tool calls as collapsible cards in the conversation.
-Collapsed: tool name badge + one-line preview. Expanded: full args + result.
-
-### Sprint 3.2: Multi-Model Expansion
-Add more models. Group by provider. Model info tooltip on hover.
-(Partially done: 10 models in dropdown from Sprint 1.)
-
-### Sprint 3.2b: Resizable Panel Widths (COMPLETE Sprint 6)
-Both sidebar and workspace panel are drag-resizable with localStorage persistence.
-
-### Sprint 3.3: Workspace File Actions
-- [ ] Rename file (inline, double-click) (Wave 3)
-- [ ] Create folder (Wave 3)
-- [x] Syntax highlighted code preview (Prism.js)
-
-### Sprint 3.4: Conversation Controls
-- [x] Copy message (Sprint 5)
-- [x] Edit last user message + regenerate
-- [x] Regenerate last assistant response
-- [x] Clear conversation (wipe messages, keep session)
+| Wave | Theme | Key Deliverables |
+|------|-------|-----------------|
+| Wave 2 | Full CRUD + Interaction | Cron/skill/memory CRUD, session search, workspace management, session rename |
+| Wave 3 | Power Features | Tool call cards, multi-model dropdown, resizable panels, file actions, conversation controls |
+| Wave 4 | Settings + Notifications | Settings panel, cron alerts, background error banner |
+| Wave 5 | Session Continuity | Session tags, archive, projects/folders |
+| Wave 6 | Agentic Features | Background task cancel, voice input (Web Speech API) |
+| Wave 7 | Production Hardening | Password auth, security headers, mobile responsive, Docker + GHCR CI |
 
 ---
 
-## Wave 4: Settings, Configuration, Notifications
+## User Requested Features
 
-### Sprint 4.1: Settings Panel
-Full settings overlay: default model, default workspace, enabled toolsets, config viewer.
+Community-requested enhancements tracked from GitHub issues. All shipped.
 
-### Sprint 4.2: Notification Panel
-Bell icon with unread count. SSE endpoint for cron completions and errors. Toast pop-ups.
-
-### Sprint 4.3: Delivery Target Config
-Configure and test-ping delivery targets (Discord, Telegram, Slack, email) for cron jobs.
-
----
-
-## Wave 5: Honcho Integration and Long-term Memory
-
-### Sprint 5.1: Honcho Memory Panel
-User representation panel, cross-session context, Honcho search, memory write.
-
-### Sprint 5.2: Session Continuity Features
-"What were we working on?" button, session tags, session archive.
-
----
-
-## Wave 6: Realtime and Agentic Features
-
-### Sprint 6.1: Background Task Monitor
-Live list of running agent threads. Cancel button. Queue visibility.
-
-### Sprint 6.2: Subagent Delegation Cards
-When delegate_task fires, show subagent progress inline in chat.
-
-### Sprint 6.3: Code Execution Panel
-Jupyter-style inline code cell. Stateful kernel per session.
-
-### Sprint 6.4: Voice Mode
-Push-to-talk mic button. Whisper transcription. Optional TTS playback.
-
----
-
-## Wave 7: Production Hardening and Mobile
-
-### Sprint 7.1: Authentication
-HERMES_WEBUI_PASSWORD env var gate. Signed cookie. Login page.
-
-### Sprint 7.2: HTTPS and Reverse Proxy
-Nginx + Let's Encrypt. CORS headers for external domain.
-
-### Sprint 7.3: Mobile Responsive Layout
-Collapsible sidebar hamburger. Touch-friendly controls. Swipe gestures.
-
-### Sprint 7.4: Performance and Scale
-Virtual scroll for session/message lists. Incremental message loading.
+| Feature | Issue | Shipped | Sprint |
+|---------|-------|---------|--------|
+| Workspace tree view | #22 | Done | Sprint 18 |
+| Docker container + GHCR images | #7 | Done | Sprint 21 + v0.28.1 CI |
+| Authentication | #23 | Done | Sprint 19 |
+| Send key / personalization | #26 | Done | Sprint 17 |
+| Multi-profile support | #28 | Done | Sprint 22 |
+| Mobile responsive UI | #21 | Done | Sprint 21 |
+| Profile creation in Docker | #44 | Done | v0.27 |

SPRINTS.md

@@ -1,6 +1,6 @@
 # Hermes Web UI -- Forward Sprint Plan
 
-> Current state: v0.15 | 221 tests | Daily driver ready
+> Current state: v0.30.1 | 424 tests | Daily driver ready
 > This document plans the path from here to two targets:
 >
 > Target A: 1:1 feature parity with the Hermes CLI (everything you can do from the
@@ -14,15 +14,19 @@
 
 ---
 
-## Where we are now (v0.12.1)
+## Where we are now (v0.21)
 
-**CLI parity: ~80% complete.** Core agent loop, all tools visible, workspace
-file ops, cron/skills/memory CRUD, session management, streaming, cancel --
-all solid. Gaps are configuration, subagent visibility, and runtime controls.
+**CLI parity: ~90% complete.** Core agent loop, all tools visible, workspace
+file ops with tree view, cron/skills/memory CRUD, session management, streaming,
+cancel, multi-provider models, custom endpoint discovery, slash commands,
+thinking/reasoning display, password auth -- all solid. Gaps are subagent
+visibility, toolset control, and code execution.
 
-**Claude parity: ~55% complete.** Chat, streaming, file browser,
-session management, tool cards, syntax highlighting, model switching -- all
-present. Gaps are project organization, artifacts, voice, sharing, mobile.
+**Claude parity: ~70% complete.** Chat, streaming, file browser, session
+management, tool cards, syntax highlighting, model switching, projects,
+settings, Mermaid diagrams, mobile layout, breadcrumb workspace nav, slash
+commands, thinking display, auth -- all present. Gaps are artifacts, voice,
+TTS, sharing, mobile-optimized layout.
 
 ---
 
@@ -263,128 +267,566 @@ inconsistently across platforms. These were the most common visual complaints.
 - Thinking/reasoning display for extended-thinking models
 - Slash command autocomplete popup
 
-**Tests:** 0 new (pure CSS/DOM changes). Total: 237.
+**Tests:** 74 new (test_sprint16.py: safe HTML rendering, XSS security, sidebar polish). Total: 289.
 **Hermes CLI parity impact:** Low
 **Claude parity impact:** Medium (sidebar polish matches Claude's quality bar)
 
 ---
 
-## Sprint 17 -- Voice + Multimodal Input
+## Sprint 17 -- Workspace Polish + Slash Commands + Settings (COMPLETED)
 
-**Theme:** Input beyond the keyboard.
+**Theme:** Workspace polish, slash commands, and composer settings.
 
-**Why now:** Voice is a meaningful quality-of-life feature for longer sessions
-and is achievable with Whisper. Image input closes the last modality gap with
-Claude (Claude accepts image paste natively -- we do too, but only as
-file uploads, not clipboard screenshots into the conversation directly).
+**Why now:** Three things converge: @nothingmn filed Issue #22 requesting a
+tree/accordion workspace view (breadcrumb navigation is the foundation for
+that), slash commands were deferred from Sprint 16, and Issue #26 (send key
+personalization) fits naturally since we are already touching the keydown
+handler for slash command autocomplete.
+
+### Track A: Workspace Breadcrumb Navigation
+- **Breadcrumb path bar.** When users click into subdirectories, a breadcrumb
+  bar appears showing the path (e.g. `~ / src / components`) with clickable
+  segments to navigate back. Hidden at root level for a clean UI.
+- **Up button.** Arrow-up button in the panel header navigates to the parent
+  directory. Hidden when already at workspace root.
+- **Current directory tracking.** `S.currentDir` state property tracks the
+  active directory. File operations (rename, delete, new file, new folder)
+  stay in the current directory instead of jumping back to root.
+- **New file/folder in subdirectories.** Creating files or folders now respects
+  the current directory, creating them in the viewed subdirectory.
+
+### Track B: Slash Commands Foundation
+- **commands.js module.** New 7th JS module with command registry, parser,
+  autocomplete dropdown, and built-in command handlers.
+- **Built-in commands:** `/help` (list commands), `/clear` (clear conversation),
+  `/model <name>` (switch model with fuzzy match), `/workspace <name>` (switch
+  workspace), `/new` (start new session).
+- **Autocomplete dropdown.** Typing `/` in the composer shows a filtered
+  dropdown. Arrow keys navigate, Tab/Enter select, Escape closes. Positioned
+  above the composer using the workspace dropdown CSS pattern.
+- **Transparent pass-through.** Unrecognized `/` commands pass through to the
+  agent normally (not intercepted).
+
+### Track C: Send Key Setting (Issue #26)
+- **`send_key` setting.** New setting in Settings panel: "Enter" (default) or
+  "Ctrl+Enter". Persisted to `settings.json`. Loaded on boot.
+- **Keydown handler rewrite.** Combined handler for autocomplete navigation
+  and send key preference. When `ctrl+enter` is selected, plain Enter inserts
+  a newline and Ctrl/Cmd+Enter sends.
+
+### Deferred to Sprint 18
+- Thinking/reasoning display for extended-thinking models
+- Voice input via Whisper
+- Workspace tree/accordion view (full implementation of Issue #22)
+
+**Tests:** 6 new (test_sprint17.py). Total: 318.
+**Hermes CLI parity impact:** Low (slash commands add convenience)
+**Claude parity impact:** Medium (workspace nav, slash commands match Claude UX)
+
+---
+
+## Sprint 18 -- Thinking Display + Workspace Tree + Preview Fix (COMPLETED)
+
+**Theme:** Show the model's reasoning, improve workspace navigation, fix UX bug.
+
+**Why now:** Thinking/reasoning display was deferred twice (Sprint 16 → 17 → 18).
+Workspace tree view was the #1 community request (Issue #22). File preview
+staying open on directory navigation was a daily-driver annoyance.
 
 ### Track A: Bugs
-- Image paste currently requires a click-to-attach flow. Direct paste into the
-  message textarea should embed the image inline (as a preview chip) and queue
-  it for upload on Send. (Partially works -- clean up edge cases.)
-- Large image uploads (>5MB) time out the upload step silently.
+- **File preview auto-close.** When viewing a file in the right panel and
+  navigating directories (breadcrumbs, up button, folder clicks), the preview
+  stayed visible with stale content. Fix: extracted `clearPreview()` as a named
+  function in boot.js and call it from `loadDir()` in workspace.js.
 
 ### Track B: Features
-- **Voice input (Whisper):** A microphone icon in the composer. Hold to record,
-  release to transcribe via `POST /api/transcribe` (calls local Whisper or
-  OpenAI Whisper API). Transcribed text appears in the message input, editable
-  before send. Supports the full "voice -> text -> Hermes response" loop.
-- **TTS playback:** A speaker icon on assistant messages. Calls a TTS endpoint
-  (ElevenLabs or OpenAI TTS) and plays the audio. Toggle per-message. Optional
-  auto-play mode in settings.
-- **Vision input improvements:** Paste a screenshot directly from clipboard into
-  the conversation (not just the tray). Shows as an inline preview chip with
-  the image thumbnail. On Send, uploads and includes in the message.
+- **Thinking/reasoning display.** Assistant messages with structured content
+  arrays containing `type:'thinking'` or `type:'reasoning'` blocks now render
+  as collapsible gold-themed cards above the response text. Collapsed by
+  default, click header to expand. Works with Claude extended thinking and
+  o3 reasoning tokens when preserved in the message array.
+- **Workspace tree view (Issue #22).** Directories expand/collapse in-place
+  with toggle arrows. Single-click toggles, double-click navigates (breadcrumb
+  view). Subdirectory contents fetched lazily and cached in `S._dirCache`.
+  Nesting depth shown via indentation. Empty directories show "(empty)".
+
+**Tests:** 0 new (pure CSS/DOM changes). Total: 318.
+**Hermes CLI parity impact:** Low
+**Claude parity impact:** High (reasoning display matches Claude's UI)
+
+---
+
+## Sprint 19 -- Auth + Security Hardening (COMPLETED)
+
+**Theme:** Make this safe to leave running beyond localhost.
+
+**Why now:** Issue #23 requested authentication. Auth is the last production
+hardening feature before the app is safe to expose to a network.
+
+### Track A: Bugs
+- **No request size limit.** POST bodies were unbounded (DoS risk). Added 20MB
+  cap in `read_body()`.
+
+### Track B: Features
+- **Password authentication (Issue #23).** Off by default — zero friction for
+  localhost. Enable via `HERMES_WEBUI_PASSWORD` env var or Settings panel.
+  Password-only (no username — single-user app). Signed HMAC HTTP-only cookie
+  with 24h TTL. Minimal dark-themed login page at `/login`. API calls without
+  auth return 401; page loads redirect to `/login`. Settings panel gains
+  "Access Password" field and "Sign Out" button.
+- **Security headers.** All responses now include `X-Content-Type-Options: nosniff`,
+  `X-Frame-Options: DENY`, `Referrer-Policy: same-origin`.
 
 ### Track C: Architecture
-- Audio pipeline: `POST /api/transcribe` streams audio bytes, returns transcript.
-  `GET /api/tts?text=...` returns audio/mpeg. Both use lazy import of Whisper
-  and TTS libraries to keep cold start fast.
+- New `api/auth.py` module: password hashing (SHA-256 + STATE_DIR salt), signed
+  session cookies, auth middleware, public path allowlist.
+- Auth check in `server.py` do_GET/do_POST before routing.
+- `password_hash` added to `_SETTINGS_DEFAULTS` in config.py.
+- `_set_password` special field in save_settings for secure password updates.
 
-**Tests:** ~12 new. Total: ~271.
+**Tests:** 10 new. Total: 328.
+**Hermes CLI parity impact:** Low (CLI has no auth concerns)
+**Claude parity impact:** High (Claude is authenticated)
+
+---
+
+## Sprint 20 -- Voice Input + Send Button Polish (COMPLETED)
+
+**Theme:** Input refinements — voice and visual polish.
+
+**Why now:** Voice input was the next feature on the roadmap. The send button
+UX was a low-effort high-impact polish opportunity that pairs naturally.
+
+### Track A: Bugs
+- **Send button always visible.** The old pill-shaped "Send" button was always
+  visible even with an empty textarea, wasting space. Now hidden by default,
+  appears only when there is content to send.
+
+### Track B: Features
+- **Voice input (Web Speech API).** Microphone button in composer. Tap to
+  record, tap again to stop. Live interim transcription in textarea. Auto-stops
+  after ~2s of silence. Appends to existing text. Hidden when browser doesn't
+  support Web Speech API. No API keys, no server changes.
+- **Send button polish.** Icon-only 34px circle with upward arrow SVG. Pop-in
+  spring animation on appear. Scale hover/active for tactile feedback. Hidden
+  while agent is responding.
+
+### Track C: Architecture
+- Voice input IIFE in `boot.js` with SpeechRecognition lifecycle.
+- `updateSendBtn()` in `ui.js` hooked into setBusy, renderTray, autoResize.
+
+**Tests:** 52 new (voice) + 33 new (send button). Total: 415.
 **Hermes CLI parity impact:** Medium (voice not in CLI, but adds capability)
 **Claude parity impact:** High (Claude has native voice mode)
 
 ---
 
-## Sprint 18 -- Subagent Visibility + Agentic Transparency
+## Sprint 21 -- Mobile Responsive + Docker (COMPLETED)
 
-**Theme:** Watch Hermes think, not just respond.
+**Theme:** Mobile experience + containerized deployment.
 
-**Why now:** When Hermes delegates to subagents (delegate_task, spawns parallel
-workstreams), the UI shows nothing. On long multi-agent tasks you have no idea
-what's happening. This is the last major "CLI feels better" gap for power users.
+**Why now:** Issue #21 (mobile) was the most-requested UX gap. Issue #7 (Docker)
+enables deployment beyond localhost. Both were achievable without new dependencies.
 
-### Track A: Bugs
-- Tool cards for delegate_task show no information about what the subagent was
-  asked to do or what it returned.
-- The activity bar text truncates at 55 chars -- tool previews for long terminal
-  commands show nothing useful.
+### Track A: Bugs (from review)
+- **CSS cascade broke mobile slide-in.** `position:relative` after the media query
+  overrode `position:fixed`. Wrapped in `@media(min-width:641px)`.
+- **mobileSwitchPanel() always reopened sidebar.** Chat tab now closes it.
+- **Dockerfile missing pip install.** Container failed on startup.
+- **No .dockerignore.** `.git`, `tests/`, `.env*` leaked into images.
+- **docker-compose tilde expansion.** `~` doesn't expand in Compose defaults.
 
 ### Track B: Features
-- **Subagent delegation cards:** When `delegate_task` fires, show an expandable
-  card with the subagent's goal, status (pending/running/done), and result
-  summary. Multiple subagents from one call appear as a card group. Uses the
-  existing tool card infrastructure.
-- **Background task monitor:** A "Tasks" indicator in the topbar (separate from
-  the cron Tasks panel). Shows count of active agent threads. Click opens a
-  popover listing all in-flight streams with session names and elapsed times.
-  Cancel any individual thread. This is the full job queue visibility the CLI
-  implicitly has via `ps aux`.
-- **Thinking/reasoning display:** When the model emits reasoning tokens (o3,
-  Claude extended thinking), show them in a collapsible "Reasoning" card above
-  the response. Collapsed by default. This matches Claude's reasoning display.
+- **Hamburger sidebar.** Slide-in overlay on mobile, tap outside to close.
+- **Bottom navigation bar.** 5-tab iOS-style bar replaces sidebar tabs.
+- **Files slide-over.** Right panel opens as slide-over from right edge.
+- **Touch targets.** Minimum 44px on all interactive elements.
+- **Docker support.** Dockerfile, docker-compose.yml, .dockerignore.
 
 ### Track C: Architecture
-- Task registry: extend STREAMS to include session name, start time, and task
-  description. New `GET /api/tasks/active` endpoint returns all running streams
-  with metadata.
+- Mobile nav functions in `boot.js`. Session click auto-closes sidebar.
+- 69 new CSS lines scoped to `@media(max-width:640px)`.
+- Desktop layout untouched — all mobile elements `display:none` by default.
 
-**Tests:** ~14 new. Total: ~285.
-**Hermes CLI parity impact:** Very High (subagent and task visibility is the
-  last major CLI gap)
-**Claude parity impact:** High (Claude shows reasoning, tool use visibly)
+**Tests:** 0 new (CSS/DOM changes). Total: 415.
+**Hermes CLI parity impact:** Low
+**Claude parity impact:** High (Claude has mobile layout)
 
 ---
 
-## Sprint 19 -- Auth, HTTPS, and Production Hardening
+## Sprint 22 -- Multi-Profile Support (COMPLETED, Issue #28)
 
-**Theme:** Make this safe to leave running.
+**Theme:** Switch between Hermes agent profiles seamlessly from the web UI.
 
-**Why now:** Everything else is done. This is the sprint you run when you want
-to expose the UI beyond localhost -- to a team, a mobile device, or a public
-address.
+**Why now:** Issue #28 requested full profile management in the UI. The CLI has
+had comprehensive profile support since v0.6.0 — isolated instances with their
+own config, skills, memory, cron, and API keys. The web UI was locked to a
+single default profile, blocking multi-persona workflows.
 
 ### Track A: Bugs
-- Server has no request size limit on non-upload endpoints (potential DoS).
-- Session JSON files have no size cap (a runaway agent could write GBs).
+- **Hardcoded `~/.hermes` paths.** Memory read/write in routes.py and model
+  discovery in config.py used hardcoded paths instead of the active profile's
+  directory. Fixed to resolve through `get_active_hermes_home()`.
+- **Module-level cached paths.** hermes-agent's `skills_tool.py` and `cron/jobs.py`
+  snapshot `HERMES_HOME` at import time. Profile switch now monkey-patches these
+  cached variables (`SKILLS_DIR`, `CRON_DIR`, `JOBS_FILE`, `OUTPUT_DIR`).
 
 ### Track B: Features
-- **Password authentication:** A login page with a configurable password
-  (HERMES_WEBUI_PASSWORD env var). Signed cookie session (24h expiry).
-  Single-user model -- no accounts, no registration.
-- **HTTPS / reverse proxy guide:** A one-page `DEPLOY.md` with instructions
-  for running behind nginx + Let's Encrypt on a VPS. Configuration snippets
-  for systemd service, nginx config, certbot.
-- **Mobile responsive layout:** Collapsible sidebar (hamburger). Touch-friendly
-  session list (swipe to delete, tap to navigate). Composer expands on focus.
-  Right panel hidden by default on mobile, accessible via a Files tab.
-- **Rate limiting:** Simple per-IP token bucket on the chat/start endpoint
-  (configurable, default 10 req/min) to prevent accidental hammering.
+- **Profile picker (topbar).** Purple-accented chip with SVG user icon in the
+  topbar. Click opens a dropdown listing all profiles with gateway status dots,
+  model info, and skill count. Click to switch; "Manage profiles" link opens
+  the management panel.
+- **Profiles sidebar panel.** New nav tab with full management UI. Cards show
+  each profile with model, provider, skill count, API key status, and gateway
+  badge. "Use" button to switch, delete button for non-default profiles.
+- **Profile creation.** "+ New profile" form with name validation (lowercase
+  alphanumeric + hyphens), optional "clone config from active" checkbox. Wraps
+  `hermes_cli.profiles.create_profile()`.
+- **Profile deletion.** Confirm dialog, auto-switches to default if deleting
+  the active profile. Blocked while agent is running.
+- **Seamless switching.** No server restart required. Profile switch updates
+  `HERMES_HOME` env var, patches module-level caches, reloads `.env` API keys,
+  reloads `config.yaml`, and refreshes the model dropdown, skills, memory, and
+  cron panels.
+- **Per-session profile tracking.** New `profile` field on Session records which
+  profile was active when the session was created. Backward-compatible (defaults
+  to `null` for old sessions).
 
 ### Track C: Architecture
-- Helmet headers: X-Content-Type-Options, X-Frame-Options, HSTS (when served
-  over HTTPS). Simple middleware in the Handler.
+- New `api/profiles.py` module (~200 lines): profile state management wrapping
+  `hermes_cli.profiles`. Thread-safe with `_profile_lock`. Lazy imports to
+  avoid circular dependencies.
+- `api/config.py`: Replaced module-level `cfg` dict with reloadable
+  `get_config()`/`reload_config()`. Dynamic `_get_config_path()` resolves
+  through active profile.
+- `api/streaming.py`: `HERMES_HOME` added to env save/restore block around
+  agent runs (alongside `TERMINAL_CWD`, `HERMES_EXEC_ASK`).
+- Profile switch blocked while any agent stream is active (process-global
+  `HERMES_HOME` cannot be changed mid-run).
+- Zero modifications to hermes-agent code required.
 
-**Tests:** ~12 new. Total: ~297.
-**Hermes CLI parity impact:** Low (CLI has no auth/HTTPS concerns)
-**Claude parity impact:** Very High (Claude is authenticated, HTTPS only)
+**Tests:** 0 new (profile management requires hermes-agent integration). Total: 415.
+**Hermes CLI parity impact:** Very High (profile support is a major CLI feature)
+**Claude parity impact:** Low (Claude has no profile concept)
+
+---
+
+## Sprint 23 -- Profile/Workspace/Model Coherence (COMPLETED)
+
+**Theme:** Make profiles, workspaces, models, and sessions coherent across
+profile switches.
+
+**Why now:** Sprint 22 added profile switching but five coherence bugs remained:
+the model picker ignored the profile's default, workspaces were a global file,
+DEFAULT_WORKSPACE was a startup singleton, the session list showed all profiles,
+and switchToProfile() didn't refresh workspaces or sessions.
+
+### Track A: Bugs
+- **Model picker ignores profile on switch.** `populateModelDropdown()` skipped
+  the profile's default model if `localStorage` had a saved preference. Fixed:
+  `switchToProfile()` now clears `hermes-webui-model` from localStorage and
+  applies the profile's default model from the switch response.
+- **Workspace list is a global file.** `workspaces.json` was process-global.
+  Fixed: workspace storage is now profile-local at `{profile_home}/webui_state/`.
+  Default profile uses global STATE_DIR for backward compatibility.
+- **`DEFAULT_WORKSPACE` is a startup singleton.** Frozen at boot. Fixed:
+  `get_last_workspace()` and `_profile_default_workspace()` now resolve
+  dynamically through the active profile's config.
+- **Session list shows all profiles.** Fixed: `renderSessionListFromCache()`
+  filters to `S.activeProfile` by default, with "Show N from other profiles"
+  toggle (modeled on the archived toggle).
+- **`switchToProfile()` doesn't refresh workspace list or sessions.** Fixed:
+  now calls `loadWorkspaceList()`, `renderSessionList()`, resets profile filter.
+
+### Track B: Features
+- **Profile-local workspace storage.** Each named profile stores its own
+  `workspaces.json` and `last_workspace.txt` under `{profile_home}/webui_state/`.
+  Falls back to global STATE_DIR for the default profile (preserves test
+  isolation and backward compat).
+- **Profile switch returns defaults.** `POST /api/profile/switch` response now
+  includes `default_model` and `default_workspace` so the frontend can apply
+  both in one round-trip.
+- **Session profile filter.** Session sidebar filters to active profile by
+  default. "Show N from other profiles" toggle reveals sessions from all
+  profiles. Resets on profile switch.
+
+### Track C: Architecture
+- `api/workspace.py`: Rewritten with `_profile_state_dir()`, `_workspaces_file()`,
+  `_last_workspace_file()`, `_profile_default_workspace()`. All lazy imports to
+  avoid circular deps.
+- `api/profiles.py`: `switch_profile()` returns `default_model` and
+  `default_workspace` from the new profile's config.yaml.
+- `static/panels.js`: `switchToProfile()` clears localStorage model key,
+  refreshes workspace list and session list, resets profile filter.
+- `static/sessions.js`: `_showAllProfiles` state variable, profile filter in
+  `renderSessionListFromCache()`, toggle UI.
+
+**Tests:** 8 new (test_sprint23.py). Total: 423.
+**Hermes CLI parity impact:** High (coherent profile behavior)
+**Claude parity impact:** Low
+
+---
+
+## Sprint 24 -- Web Polish + Bug Fix Pass (PLANNED)
+
+**Theme:** Stabilize, harden, and close the last meaningful web UI gaps before
+shifting focus to distribution. Goal is a release that's genuinely ready for
+wider user adoption -- no rough edges, no obvious missing pieces.
+
+**Why now:** Sprint 23 completed the core agentic transparency features. The
+remaining web roadmap items are diminishing-returns polish. Rather than
+grinding through marginal features, this sprint cleans up what's there, fixes
+bugs users will actually hit, and closes a few real gaps before recommending
+the app to others.
+
+### Track A: Bug Fixes
+- **Cron edit form has no skill picker.** Sprint 23 added skill picker to the
+  create form but not the edit form. cronEditSave() doesn't include skills in
+  the update body, so existing skills survive an edit but can't be changed.
+  Fix: add the same skill picker UI to the inline edit form and include
+  `skills` in the update POST body.
+- **S.lastUsage dead code.** messages.js sets `S.lastUsage` from `d.usage` at
+  done-time, but nothing reads it. The usage badge reads cumulative session
+  totals from `S.session.input_tokens` instead. Either wire `S.lastUsage` into
+  a per-turn display or remove the dead assignment.
+- **_cronSkillsCache never invalidated.** Skills picker shows stale data if
+  skills are added/removed mid-session. Add a cache-bust when the skills panel
+  is opened or a skill is saved/deleted.
+- **Tool args not shown on session reload.** Tool call cards in history show
+  name and result snippet but not the args (args only exist in the live SSE
+  event). Sprint 23 added args to the session JSON -- verify they're actually
+  rendering in the settled history cards.
+
+### Track B: Features
+- **Cron edit: skill picker parity.** As above -- make create and edit forms
+  identical in capability.
+- **Per-turn cost display.** The current usage badge shows cumulative session
+  totals attached to the last message, which is misleading. Either: (a) show
+  per-turn cost from `S.lastUsage` immediately after each response instead of
+  cumulative, or (b) show cumulative in the session topbar/header instead of
+  attached to a message bubble. Pick the cleaner UX.
+- **Virtual scroll for long session/skill lists.** When session count or skill
+  count gets large (100+), the sidebar becomes sluggish. Add a simple virtual
+  scroll or windowed render -- only render visible items + a buffer above/below.
+  CSS `contain: strict` + IntersectionObserver approach, no library needed.
+
+### Track C: Code Quality
+- **SPRINTS.md + ROADMAP.md + CHANGELOG.md updated** to reflect Sprint 23
+  completion (agentic transparency) and correct test counts.
+- **Remove stale Sprint 23 description** from SPRINTS.md (the "Profile/Workspace
+  coherence" text is from an older plan; Sprint 23 actually shipped agentic
+  transparency features).
+- **CHANGELOG entry for v0.29** covering Sprint 23 deliverables.
+
+**Estimated tests:** ~10 new. Target total: ~435.
+**Hermes CLI parity impact:** Low
+**Claude parity impact:** Low
+**User-facing value:** Medium -- removes rough edges that would bother new users
+
+---
+
+## Sprint 25 -- macOS Desktop Application (PLANNED)
+
+**Theme:** Native Mac desktop app. Single download, runs entirely offline,
+feels like a real application -- not a browser tab.
+
+**Why this matters:** The web UI requires an SSH tunnel or a server setup to
+use. A .app bundle that a user can double-click and immediately have a working
+Hermes interface is genuinely differentiating. No other open-source Hermes
+interface ships as a native Mac app. This is the highest-leverage remaining
+investment for user adoption.
+
+**Approach: Swift + WKWebView (not Electron)**
+
+The right architecture is a thin native Swift shell (~300-500 lines) that:
+1. Bundles the existing Python server and all api/ modules inside the .app
+2. Spawns the server as a subprocess on a random local port at launch
+3. Opens a WKWebView window pointed at that localhost port
+4. Handles Mac app lifecycle natively (dock icon, cmd+Q, window management,
+   app menu, about box)
+5. Bridges a small set of native Mac capabilities that WKWebView can't do
+
+**Why not Electron:** WKWebView is Safari's engine -- dramatically lighter than
+Chromium. No 200MB node_modules. No separate update daemon. The .app is ~30MB
+including the Python runtime, vs 150MB+ for Electron.
+
+**Why not full native Swift UI:** Would require rewriting the entire frontend
+from scratch. The web UI is already fast, dark-themed, and feature-complete.
+The thin shell approach gets 95% of the benefit at 5% of the cost.
+
+### Track A: Swift App Shell
+
+**Files to create:**
+```
+desktop/
+  HermesApp.swift          -- @main entry point, NSApp delegate
+  AppDelegate.swift        -- lifecycle: start server on launch, stop on quit
+  WindowController.swift   -- NSWindow + WKWebView setup, cmd shortcuts
+  ServerManager.swift      -- spawn/monitor Python subprocess, pick free port
+  MenuBuilder.swift        -- native app menu (File, Edit, View, Window, Help)
+  Info.plist               -- bundle ID, display name, version, icon
+  Assets.xcassets/         -- app icon (1024x1024 + all required sizes)
+  HermesApp.xcodeproj/     -- Xcode project file
+```
+
+**ServerManager.swift responsibilities:**
+- Find Python: check bundled runtime first, fall back to system python3
+- Pick a free port (bind to :0, read assigned port, close, use it)
+- Spawn: `python3 server.py --port {port}` as a child Process
+- Monitor: if server crashes, show an error sheet and offer restart
+- Shutdown: SIGTERM on app quit, wait up to 3s, then SIGKILL
+
+**WKWebView configuration:**
+- `allowsBackForwardNavigationGestures = false` (it's a single-page app)
+- `WKUserContentController` for JS bridge (native notifications, file picker)
+- Wait for server health check before loading (poll /health, show loading
+  spinner in the native window while waiting, typically <1s)
+- `userAgent` override so the server can detect desktop app context
+
+**Native menu items (beyond defaults):**
+- File > New Session (Cmd+N) -- calls JS `newSession()`
+- File > New Window (Cmd+Shift+N) -- opens second window with its own WKWebView
+- View > Toggle Sidebar (Cmd+Shift+S)
+- Window > Zoom, Minimize (standard)
+- Help > About Hermes, Check for Updates (links to GitHub releases page)
+
+### Track B: Python Bundling
+
+Two options, in order of preference:
+
+**Option A: Require system Python (simpler, recommended for v1)**
+- Check for `python3` at known paths: `/usr/bin/python3`, homebrew paths,
+  pyenv paths
+- If not found: show a one-time setup sheet with instructions
+- Pros: tiny download (~5MB for the Swift app + web assets), no bundling complexity
+- Cons: user needs Python installed (most developers do; target audience does too)
+
+**Option B: Bundle python-standalone (self-contained, larger)**
+- Use `python-build-standalone` (from Astral/uv project): pre-built Python
+  3.11 binaries, ~30MB compressed, no Xcode toolchain needed to build
+- Extract to `~/Library/Application Support/Hermes/python/` on first launch
+- Install `requirements.txt` via bundled pip into a local venv
+- Pros: zero dependencies, works on a clean Mac
+- Cons: first launch takes ~10-20s for extraction + pip install; ~30MB download
+
+**Recommendation:** Ship v1 with Option A. Add Option B as an optional
+"standalone" download for non-developers.
+
+### Track C: Distribution
+
+**GitHub Releases (primary):**
+- Build with `xcodebuild -scheme HermesApp -configuration Release -archivePath`
+- `xcodebuild -exportArchive` to produce a .app bundle
+- `hdiutil create` to produce a .dmg with drag-to-Applications installer UI
+- Upload .dmg as a GitHub Release asset via `gh release create`
+- CI: add `.github/workflows/mac-release.yml` -- trigger on `vX.Y.Z-mac` tag
+
+**Code signing:**
+- Without an Apple Developer account: distribute as unsigned, users must
+  right-click > Open on first launch (standard for open-source Mac apps)
+- With a free Apple Developer account: ad-hoc signing removes the Gatekeeper
+  warning without paying $99/year (no notarization, but much better UX)
+- With paid account ($99/year): full notarization, no warnings, direct download
+
+**Recommended for v1:** ad-hoc signing (free, good enough for early adopters).
+Document the right-click > Open workaround in the README for unsigned builds.
+
+**Universal binary (Intel + Apple Silicon):**
+```bash
+xcodebuild archive -scheme HermesApp -destination "generic/platform=macOS"
+```
+Both architectures in one .app. No separate downloads needed.
+
+### Track D: Native Integrations (v1 scope)
+
+**System notifications for cron completion:**
+- The web UI polls `/api/cron/alerts` and shows in-page banners
+- The Mac app can additionally post `UNUserNotificationCenter` notifications
+- JS bridge: `window.webkit.messageHandlers.notify.postMessage({title, body})`
+- Swift handler: posts a native notification with the cron job name and output
+  summary -- appears in Notification Center, works even when app is in background
+
+**File picker for workspace add:**
+- Currently: user types a path string into the workspace add form
+- Mac app: intercept workspace-add form submission, open `NSOpenPanel` instead,
+  return the selected path to the JS via `evaluateJavaScript`
+- Much better UX -- standard Mac folder picker, no typing paths
+
+**Dock badge for pending approvals:**
+- When an agent approval is waiting, set `NSApp.dockTile.badgeLabel = "1"`
+- Clear badge when approval is resolved
+- JS bridge fires when approval card appears/disappears
+
+**Menu bar mode (optional, v2):**
+- A small status bar item (⚗️ icon in menu bar) that opens a compact popover
+- Popover shows current session status, last message, quick-compose field
+- Useful for running Hermes in the background without a full window
+
+### Track E: Testing
+
+Since the Swift app is thin glue, most testing remains in the existing pytest
+suite (server still runs identically). New Swift-specific tests:
+- `ServerManagerTests.swift`: verify port picking, process spawn, health wait
+- UI tests via `XCUITest`: launch app, wait for WKWebView to load, verify
+  title bar shows "Hermes", verify /health responds
+- Smoke test in CI: `xcodebuild test -scheme HermesApp`
+
+### Implementation Order
+
+1. `ServerManager.swift` + basic `AppDelegate` -- get Python server spawning
+   and health-check working from Swift
+2. `WindowController.swift` -- WKWebView loading, loading spinner while
+   server starts
+3. App icon + Info.plist -- make it look like a real app
+4. `MenuBuilder.swift` -- native menus + keyboard shortcuts
+5. JS bridge for notifications -- most impactful native integration
+6. DMG build script + GitHub Actions CI
+7. (Optional) File picker bridge, dock badge
+
+### What to NOT do in v1
+
+- Windows or Linux wrapper (different toolchain; do Mac first, assess demand)
+- Full Swift/SwiftUI rewrite of the frontend (months of work, wrong tradeoff)
+- App Store submission (sandboxing breaks local server; not worth the effort)
+- Auto-update mechanism (GitHub releases + manual download is fine for v1)
+- Menu bar mode (cool but not v1 scope)
+
+### Files to create in the repo
+
+```
+desktop/mac/
+  HermesApp/
+    HermesApp.swift
+    AppDelegate.swift
+    WindowController.swift
+    ServerManager.swift
+    MenuBuilder.swift
+    Assets.xcassets/
+    Info.plist
+  HermesApp.xcodeproj/
+  README.md              -- build instructions, requirements, signing notes
+.github/workflows/
+  mac-release.yml        -- build + sign + upload DMG on tag push
+```
+
+The server code (`server.py`, `api/`, `static/`, `requirements.txt`) is
+referenced from the repo root -- no duplication. The .app bundle copies them
+at build time.
+
+**Estimated effort:** 2-3x a typical web sprint (new language, new toolchain,
+bundling complexity). Realistic for a focused weekend or a dedicated agent run
+with clear instructions.
+
+**Hermes CLI parity impact:** N/A (different distribution channel)
+**Claude parity impact:** Medium (Claude.app is a native Mac app)
+**User-facing value:** Very high -- lowers barrier to entry dramatically,
+genuinely differentiating for an open-source project
 
 ---
 
 ## Feature Parity Summary
 
-### After Sprint 18 (Hermes CLI parity: complete)
+### Hermes CLI Parity (as of Sprint 19)
 
 | CLI Feature | Status |
 |-------------|--------|
@@ -400,15 +842,19 @@ address.
 | Workspace switching | Done (v0.7) |
 | Model selection | Done (v0.3) |
 | Multi-provider model support | Done (Sprint 11) |
-| Toolset control | Sprint 12 |
 | Settings persistence | Done (Sprint 12) |
-| Subagent visibility | Sprint 18 |
-| Background task monitor | Sprint 18 |
-| Code execution (Jupyter) | Sprint 17+ |
 | Cron completion alerts | Done (Sprint 13) |
+| Slash commands | Done (Sprint 17) |
+| Thinking/reasoning display | Done (Sprint 18) |
+| Auth / login | Done (Sprint 19) |
+| Voice input | Done (Sprint 20) |
+| Multi-profile support | Done (Sprint 22) |
+| Subagent visibility | Deferred |
+| Code execution (Jupyter) | Deferred |
+| Toolset control | Deferred |
 | Virtual scroll (perf) | Deferred |
 
-### After Sprint 19 (Claude parity: ~90% complete)
+### Claude Parity (as of Sprint 19)
 
 | Claude Feature | Status |
 |----------------|--------|
@@ -420,19 +866,21 @@ address.
 | Tool use visibility | Done (v0.11) |
 | Edit/regenerate messages | Done (v0.10) |
 | Session management | Done (v0.6) |
-| Artifacts (HTML/SVG preview) | Sprint 17+ |
-| Code execution inline | Sprint 17+ |
 | Mermaid diagrams | Done (Sprint 14) |
 | Projects / folders | Done (Sprint 15) |
 | Pinned/starred sessions | Done (Sprint 12) |
-| Reasoning display | Sprint 16 |
-| Voice input | Sprint 17 |
-| TTS playback | Sprint 17 |
 | Notifications | Done (Sprint 13) |
 | Settings panel | Done (Sprint 12) |
-| Auth / login | Sprint 19 |
-| HTTPS | Sprint 19 |
-| Mobile layout | Done (v0.16.1) |
+| Reasoning display | Done (Sprint 18) |
+| Auth / login | Done (Sprint 19) |
+| Mobile layout (basic) | Done (v0.16.1) |
+| Workspace tree view | Done (Sprint 18) |
+| Slash commands | Done (Sprint 17) |
+| Voice input | Done (Sprint 20) |
+| TTS playback | Deferred |
+| Artifacts (HTML/SVG preview) | Deferred |
+| Code execution inline | Deferred |
+| Mobile-optimized layout | Done (Sprint 21) |
 | Sharing / public URLs | Not planned (requires server infra) |
 | Claude-specific features | Not replicable (Projects AI, artifacts sync) |
 
@@ -449,6 +897,6 @@ address.
 
 ---
 
-*Last updated: April 2, 2026*
-*Current version: v0.18 | 237 tests*
-*Next sprint: Sprint 17 (Slash Commands + Thinking Display)*
+*Last updated: April 4, 2026*
+*Current version: v0.30.1 | 424 tests*
+*Next sprint: Sprint 24 (Web Polish + Bug Fix Pass)*

TESTING.md

@@ -1,12 +1,15 @@
 # Hermes Web UI: Browser Testing Plan
 
 > This document is for manual browser testing by you or by a Claude browser agent.
-> It covers every user-facing feature of the UI through Sprint 2.
+> It covers user-facing features of the UI through Sprint 22 (v0.24).
 > Each section is written as a step-by-step test procedure with expected outcomes.
 > A browser agent (e.g. Claude with Chrome access) can execute this plan directly.
 >
 > Prerequisites: SSH tunnel is active on port 8787. Open http://localhost:8787 in browser.
 > Server health check: curl http://127.0.0.1:8787/health should return {"status":"ok"}.
+>
+> Automated tests: 424 total (401 passing, 23 pre-existing failures).
+> Run: `pytest tests/ -v --timeout=60`
 
 ---
 
@@ -1593,8 +1596,120 @@ FAIL: User message gone, blank chat, response lands in wrong session.
 
 ---
 
-*Last updated: Post-Sprint 10 concurrency sweeps, March 31, 2026*
-*Total automated tests: 190/190*
-*Regression gate: tests/test_regressions.py (23 tests, one per introduced bug)*
-*Run: python -m pytest tests/ -v*
+---
+
+## Sections Added Post-Sprint 10 (Sprints 11-19)
+
+The following features were added in Sprints 11-19 and need manual browser testing.
+Each has automated API-level tests in `tests/test_sprint{N}.py`.
+
+### Sprint 11: Multi-Provider Models
+- Open model dropdown. Verify models grouped by provider (OpenAI, Anthropic, Google, etc.)
+- If custom `base_url` configured in config.yaml, verify local models appear in dropdown.
+- Switch model. Send a message. Verify response uses selected model.
+
+### Sprint 12: Settings + Pin + Import
+- Click gear icon. Settings overlay opens.
+- Change default model, save. Restart server. Verify setting persisted.
+- Pin a session (star icon in hover overlay). Verify it floats to top of list.
+- Export session as JSON. Import it back. Verify messages restored.
+
+### Sprint 13: Alerts + Session QoL
+- Duplicate a session (copy icon in hover overlay). Verify "(copy)" title.
+- Browser tab title updates to active session name. Switch sessions — title changes.
+
+### Sprint 14: Visual Polish + Workspace Ops
+- Create a mermaid code block in a response. Verify diagram renders inline.
+- Message timestamps visible next to role labels (hover for full date).
+- Double-click a file in workspace panel to rename. Enter saves, Escape cancels.
+- Create a folder via folder icon in workspace header.
+- Add `#tag` to session title. Verify tag chip appears in sidebar. Click to filter.
+- Archive a session. Verify it disappears. Toggle "Show archived" to see it.
+
+### Sprint 15: Session Projects
+- Click "+" in project bar to create a project. Type name, Enter.
+- Click a project chip to filter sessions.
+- Hover a session → click folder icon → assign to project via picker.
+- Verify colored left border appears on assigned session.
+- Double-click project chip to rename. Right-click to delete.
+- Code blocks have a "Copy" button. Click → "Copied!" feedback.
+- Messages with 2+ tool cards show "Expand all / Collapse all" toggle.
+
+### Sprint 16: Sidebar Visual Polish
+- Session titles use full sidebar width (no truncated space for hidden icons).
+- Hover a session → action buttons appear from right with gradient fade.
+- All icons are monochrome SVGs (not emoji). Consistent across platforms.
+- Pinned sessions show small gold star inline. Unpinned = no star, full title width.
+- Active session has gold highlight (not blue). Overlay gradient matches.
+- Double-click to rename → overlay hides during rename.
+
+### Sprint 17: Workspace + Slash Commands + Send Key
+- Navigate into a subdirectory. Breadcrumb bar appears with clickable segments.
+- Up button in panel header navigates to parent. Hidden at root.
+- Type `/` in composer → autocomplete dropdown appears. Arrow keys navigate.
+- Type `/help` → lists all commands. `/clear` clears conversation. `/model` switches.
+- Settings panel: change send key to Ctrl+Enter. Verify Enter inserts newline.
+
+### Sprint 18: Thinking + Tree View + Preview Fix
+- View a file in workspace. Click a breadcrumb or folder → preview closes automatically.
+- Click a directory toggle arrow (▸) → expands in-place showing children.
+- Click again (▾) → collapses. Double-click navigates into it (breadcrumb view).
+- If model returns thinking blocks (Claude extended thinking), verify collapsible gold card appears above response.
+
+### Sprint 19: Auth + Security
+- No password set: everything works as normal. No login page.
+- Set `HERMES_WEBUI_PASSWORD=test` env var. Restart. All pages redirect to `/login`.
+- Login page: minimal card, password field, "Sign in" button.
+- Enter correct password → redirected to `/`. Cookie set (24h).
+- Enter wrong password → error message, stay on login page.
+- Settings panel: set password via "Access Password" field. Auth activates.
+- "Sign Out" button visible when auth active. Click → redirected to /login.
+- API calls without auth cookie → 401 JSON response.
+- Check response headers: `X-Content-Type-Options: nosniff`, `X-Frame-Options: DENY`.
+
+### Sprint 20: Voice Input + Send Button
+- Mic button visible in composer (Chrome/Edge). Hidden in Firefox.
+- Tap mic → button turns red with pulse, "Listening..." indicator appears.
+- Speak → live transcription appears in textarea.
+- Stop speaking → auto-stops after ~2s silence. Text stays editable.
+- Tap mic again or Send → stops recording, sends text.
+- Type text, then tap mic → spoken text appends to existing text (doesn't replace).
+- Send button hidden when textarea is empty. Appears with pop-in animation when typing.
+- Send button is icon-only circle (no "Send" text label). Blue with glow.
+- Attach a file with no text → send button appears.
+- Send message → button disappears after textarea clears.
+- While agent is responding → send button hidden.
+
+### Sprint 21: Mobile Responsive + Docker
+- Open on mobile viewport (<640px): hamburger icon visible in topbar.
+- Tap hamburger → sidebar slides in from left with backdrop overlay.
+- Tap outside sidebar → closes. Tap a session → closes and loads session.
+- Bottom navigation bar: 5 tabs (Chat, Tasks, Skills, Memory, Spaces).
+- Tap "Tasks" in bottom nav → sidebar opens showing Tasks panel.
+- Tap "Chat" in bottom nav → sidebar closes (chat is in main area).
+- Files button in topbar → right panel slides in from right.
+- All touch targets are at least 44px (session items, buttons, icons).
+- Desktop viewport (>640px): no hamburger, no bottom nav, no mobile elements.
+- Docker: `docker compose up -d` starts server on port 8787.
+- Docker: session data persists across container restarts (named volume).
+
+### Sprint 22: Multi-Profile Support
+- Profile chip in topbar (purple accent). Click → dropdown with all profiles.
+- Dropdown shows gateway status dots, model info, skill count per profile.
+- Click a profile → switches; model dropdown, skills, memory, cron refresh.
+- "Manage profiles" link opens Profiles sidebar panel.
+- Profiles panel: cards with name, model, provider, skill count, API key status.
+- "Use" button switches profile. Delete button removes non-default profiles.
+- "+ New profile" form: name validation (lowercase + hyphens), clone config checkbox.
+- Create profile → appears in list and dropdown.
+- Delete profile → confirm dialog. Auto-switches to default if deleting active.
+- Attempt switch while agent busy → blocked with toast message.
+- With hermes-agent not installed → only default profile shown, graceful fallback.
+
+---
+
+*Last updated: Sprint 22 / v0.24, April 3, 2026*
+*Total automated tests: 415 (392 passing, 23 pre-existing failures)*
+*Regression gate: tests/test_regressions.py (23 tests)*
+*Run: pytest tests/ -v --timeout=60*
 *Source: <repo>/*

api/auth.py

@@ -0,0 +1,149 @@
+"""
+Hermes Web UI -- Optional password authentication.
+Off by default. Enable by setting HERMES_WEBUI_PASSWORD env var
+or configuring a password in the Settings panel.
+"""
+import hashlib
+import hmac
+import http.cookies
+import os
+import secrets
+import time
+
+from api.config import STATE_DIR, load_settings
+
+# ── Public paths (no auth required) ─────────────────────────────────────────
+PUBLIC_PATHS = frozenset({
+    '/login', '/health', '/favicon.ico',
+    '/api/auth/login', '/api/auth/status',
+})
+
+COOKIE_NAME = 'hermes_session'
+SESSION_TTL = 86400  # 24 hours
+
+# Active sessions: token -> expiry timestamp
+_sessions = {}
+
+
+def _signing_key():
+    """Derive a stable signing key from STATE_DIR."""
+    return hashlib.sha256(str(STATE_DIR).encode()).digest()
+
+
+def _hash_password(password):
+    """SHA-256 hash with a salt derived from STATE_DIR."""
+    salt = str(STATE_DIR).encode()
+    return hashlib.sha256(salt + password.encode()).hexdigest()
+
+
+def get_password_hash():
+    """Return the active password hash, or None if auth is disabled.
+    Priority: env var > settings.json."""
+    env_pw = os.getenv('HERMES_WEBUI_PASSWORD', '').strip()
+    if env_pw:
+        return _hash_password(env_pw)
+    settings = load_settings()
+    return settings.get('password_hash') or None
+
+
+def is_auth_enabled():
+    """True if a password is configured (env var or settings)."""
+    return get_password_hash() is not None
+
+
+def verify_password(plain):
+    """Verify a plaintext password against the stored hash."""
+    expected = get_password_hash()
+    if not expected:
+        return False
+    return hmac.compare_digest(_hash_password(plain), expected)
+
+
+def create_session():
+    """Create a new auth session. Returns signed cookie value."""
+    token = secrets.token_hex(32)
+    _sessions[token] = time.time() + SESSION_TTL
+    sig = hmac.new(_signing_key(), token.encode(), hashlib.sha256).hexdigest()[:16]
+    return f"{token}.{sig}"
+
+
+def verify_session(cookie_value):
+    """Verify a signed session cookie. Returns True if valid and not expired."""
+    if not cookie_value or '.' not in cookie_value:
+        return False
+    token, sig = cookie_value.rsplit('.', 1)
+    expected_sig = hmac.new(_signing_key(), token.encode(), hashlib.sha256).hexdigest()[:16]
+    if not hmac.compare_digest(sig, expected_sig):
+        return False
+    expiry = _sessions.get(token)
+    if not expiry or time.time() > expiry:
+        _sessions.pop(token, None)
+        return False
+    return True
+
+
+def invalidate_session(cookie_value):
+    """Remove a session token."""
+    if cookie_value and '.' in cookie_value:
+        token = cookie_value.rsplit('.', 1)[0]
+        _sessions.pop(token, None)
+
+
+def parse_cookie(handler):
+    """Extract the auth cookie from the request headers."""
+    cookie_header = handler.headers.get('Cookie', '')
+    if not cookie_header:
+        return None
+    cookie = http.cookies.SimpleCookie()
+    try:
+        cookie.load(cookie_header)
+    except http.cookies.CookieError:
+        return None
+    morsel = cookie.get(COOKIE_NAME)
+    return morsel.value if morsel else None
+
+
+def check_auth(handler, parsed):
+    """Check if request is authorized. Returns True if OK.
+    If not authorized, sends 401 (API) or 302 redirect (page) and returns False."""
+    if not is_auth_enabled():
+        return True
+    # Public paths don't require auth
+    if parsed.path in PUBLIC_PATHS or parsed.path.startswith('/static/'):
+        return True
+    # Check session cookie
+    cookie_val = parse_cookie(handler)
+    if cookie_val and verify_session(cookie_val):
+        return True
+    # Not authorized
+    if parsed.path.startswith('/api/'):
+        handler.send_response(401)
+        handler.send_header('Content-Type', 'application/json')
+        handler.end_headers()
+        handler.wfile.write(b'{"error":"Authentication required"}')
+    else:
+        handler.send_response(302)
+        handler.send_header('Location', '/login')
+        handler.end_headers()
+    return False
+
+
+def set_auth_cookie(handler, cookie_value):
+    """Set the auth cookie on the response."""
+    cookie = http.cookies.SimpleCookie()
+    cookie[COOKIE_NAME] = cookie_value
+    cookie[COOKIE_NAME]['httponly'] = True
+    cookie[COOKIE_NAME]['samesite'] = 'Lax'
+    cookie[COOKIE_NAME]['path'] = '/'
+    cookie[COOKIE_NAME]['max-age'] = str(SESSION_TTL)
+    handler.send_header('Set-Cookie', cookie[COOKIE_NAME].OutputString())
+
+
+def clear_auth_cookie(handler):
+    """Clear the auth cookie on the response."""
+    cookie = http.cookies.SimpleCookie()
+    cookie[COOKIE_NAME] = ''
+    cookie[COOKIE_NAME]['httponly'] = True
+    cookie[COOKIE_NAME]['path'] = '/'
+    cookie[COOKIE_NAME]['max-age'] = '0'
+    handler.send_header('Set-Cookie', cookie[COOKIE_NAME].OutputString())

api/config.py

@@ -31,7 +31,7 @@ PORT = int(os.getenv('HERMES_WEBUI_PORT', '8787'))
 # ── State directory (env-overridable, never inside repo) ──────────────────────
 STATE_DIR = Path(os.getenv(
     'HERMES_WEBUI_STATE_DIR',
-    str(HOME / '.hermes' / 'webui-mvp')
+    str(HOME / '.hermes' / 'webui')
 )).expanduser().resolve()
 
 SESSION_DIR           = STATE_DIR / 'sessions'
@@ -134,17 +134,44 @@ if _AGENT_DIR is not None:
 else:
     _HERMES_FOUND = False
 
-# ── Config file (optional YAML) ──────────────────────────────────────────────
-CONFIG_PATH = Path(os.getenv(
-    'HERMES_CONFIG_PATH',
-    str(HOME / '.hermes' / 'config.yaml')
-)).expanduser()
+# ── Config file (reloadable -- supports profile switching) ──────────────────
+_cfg_cache = {}
+_cfg_lock = threading.Lock()
 
-try:
-    import yaml as _yaml
-    cfg = _yaml.safe_load(CONFIG_PATH.read_text()) if CONFIG_PATH.exists() else {}
-except Exception:
-    cfg = {}
+def _get_config_path() -> Path:
+    """Return config.yaml path for the active profile."""
+    env_override = os.getenv('HERMES_CONFIG_PATH')
+    if env_override:
+        return Path(env_override).expanduser()
+    try:
+        from api.profiles import get_active_hermes_home
+        return get_active_hermes_home() / 'config.yaml'
+    except ImportError:
+        return HOME / '.hermes' / 'config.yaml'
+
+def get_config() -> dict:
+    """Return the cached config dict, loading from disk if needed."""
+    if not _cfg_cache:
+        reload_config()
+    return _cfg_cache
+
+def reload_config():
+    """Reload config.yaml from the active profile's directory."""
+    with _cfg_lock:
+        _cfg_cache.clear()
+        config_path = _get_config_path()
+        try:
+            import yaml as _yaml
+            if config_path.exists():
+                loaded = _yaml.safe_load(config_path.read_text())
+                if isinstance(loaded, dict):
+                    _cfg_cache.update(loaded)
+        except Exception:
+            pass
+
+# Initial load
+reload_config()
+cfg = _cfg_cache  # alias for backward compat with existing references
 
 # ── Default workspace discovery ───────────────────────────────────────────────
 def _discover_default_workspace() -> Path:
@@ -183,7 +210,7 @@ def print_startup_config():
         f'  state dir   : {STATE_DIR}',
         f'  workspace   : {DEFAULT_WORKSPACE}',
         f'  host:port   : {HOST}:{PORT}',
-        f'  config file : {CONFIG_PATH}  {"(found)" if CONFIG_PATH.exists() else "(not found, using defaults)"}',
+        f'  config file : {_get_config_path()}  {"(found)" if _get_config_path().exists() else "(not found, using defaults)"}',
         '',
     ]
     print('\n'.join(lines), flush=True)
@@ -234,11 +261,12 @@ MIME_MAP = {
 }
 
 # ── Toolsets (from config.yaml or hardcoded default) ─────────────────────────
-CLI_TOOLSETS = cfg.get('platform_toolsets', {}).get('cli', [
+_DEFAULT_TOOLSETS = [
     'browser', 'clarify', 'code_execution', 'cronjob', 'delegation', 'file',
     'image_gen', 'memory', 'session_search', 'skills', 'terminal', 'todo',
     'web', 'webhook',
-])
+]
+CLI_TOOLSETS = get_config().get('platform_toolsets', {}).get('cli', _DEFAULT_TOOLSETS)
 
 # ── Model / provider discovery ───────────────────────────────────────────────
 
@@ -345,15 +373,16 @@ def resolve_model_provider(model_id: str):
 
     if '/' in model_id:
         prefix, bare = model_id.split('/', 1)
-        # If prefix matches config provider, strip it and use that provider directly
+        # If prefix matches config provider exactly, strip it and use that provider directly.
+        # e.g. config=anthropic, model=anthropic/claude-... → bare name to anthropic API
         if config_provider and prefix == config_provider:
             return bare, config_provider, config_base_url
-        # If the config provider is openrouter (or unset/None), pass the full
-        # provider/model string through -- OpenRouter uses this as its model ID.
-        # Only strip the prefix and switch to a direct-API provider when the
-        # config is explicitly set to that direct provider.
-        if config_provider and config_provider != 'openrouter' and prefix in _PROVIDER_MODELS:
-            return bare, prefix, None
+        # If prefix does NOT match config provider, the user picked a cross-provider model
+        # from the OpenRouter dropdown (e.g. config=anthropic but picked openai/gpt-5.4-mini).
+        # In this case always route through openrouter with the full provider/model string.
+        # Never strip the prefix and try a direct-API call to a provider whose key may not exist.
+        if prefix in _PROVIDER_MODELS and prefix != config_provider:
+            return model_id, 'openrouter', None
 
     return model_id, config_provider, config_base_url
 
@@ -396,7 +425,11 @@ def get_available_models() -> dict:
 
     # 3. Try to read auth store for active provider (if hermes is installed)
     if not active_provider:
-        auth_store_path = HOME / '.hermes' / 'auth.json'
+        try:
+            from api.profiles import get_active_hermes_home as _gah
+            auth_store_path = _gah() / 'auth.json'
+        except ImportError:
+            auth_store_path = HOME / '.hermes' / 'auth.json'
         if auth_store_path.exists():
             try:
                 import json as _j
@@ -406,7 +439,11 @@ def get_available_models() -> dict:
                 pass
 
     # 4. Check for API keys that imply available providers
-    hermes_env_path = HOME / '.hermes' / '.env'
+    try:
+        from api.profiles import get_active_hermes_home as _gah2
+        hermes_env_path = _gah2() / '.env'
+    except ImportError:
+        hermes_env_path = HOME / '.hermes' / '.env'
     env_keys = {}
     if hermes_env_path.exists():
         try:
@@ -594,6 +631,10 @@ def _get_session_agent_lock(session_id: str) -> threading.Lock:
 _SETTINGS_DEFAULTS = {
     'default_model': DEFAULT_MODEL,
     'default_workspace': str(DEFAULT_WORKSPACE),
+    'send_key': 'enter',  # 'enter' or 'ctrl+enter'
+    'show_token_usage': False,  # show input/output token badge below assistant messages
+    'show_cli_sessions': False,  # merge CLI sessions from state.db into the sidebar
+    'password_hash': None,  # SHA-256 hash; None = auth disabled
 }
 
 def load_settings() -> dict:
@@ -608,13 +649,32 @@ def load_settings() -> dict:
             pass
     return settings
 
-_SETTINGS_ALLOWED_KEYS = set(_SETTINGS_DEFAULTS.keys())
+_SETTINGS_ALLOWED_KEYS = set(_SETTINGS_DEFAULTS.keys()) - {'password_hash'}
+_SETTINGS_ENUM_VALUES = {
+    'send_key': {'enter', 'ctrl+enter'},
+}
+_SETTINGS_BOOL_KEYS = {'show_token_usage', 'show_cli_sessions'}
 
 def save_settings(settings: dict) -> dict:
     """Save settings to disk. Returns the merged settings. Ignores unknown keys."""
+    import hashlib as _hl
     current = load_settings()
+    # Handle _set_password: hash and store as password_hash
+    raw_pw = settings.pop('_set_password', None)
+    if raw_pw and isinstance(raw_pw, str) and raw_pw.strip():
+        salt = str(STATE_DIR).encode()
+        current['password_hash'] = _hl.sha256(salt + raw_pw.strip().encode()).hexdigest()
+    # Handle _clear_password: explicitly disable auth
+    if settings.pop('_clear_password', False):
+        current['password_hash'] = None
     for k, v in settings.items():
         if k in _SETTINGS_ALLOWED_KEYS:
+            # Validate enum-constrained keys
+            if k in _SETTINGS_ENUM_VALUES and v not in _SETTINGS_ENUM_VALUES[k]:
+                continue
+            # Coerce bool keys
+            if k in _SETTINGS_BOOL_KEYS:
+                v = bool(v)
             current[k] = v
     SETTINGS_FILE.write_text(
         json.dumps(current, ensure_ascii=False, indent=2),
@@ -638,3 +698,11 @@ if SETTINGS_FILE.exists():
 
 # ── SESSIONS in-memory cache (LRU OrderedDict) ───────────────────────────────
 SESSIONS: collections.OrderedDict = collections.OrderedDict()
+
+# ── Profile state initialisation ────────────────────────────────────────────
+# Must run after all imports are resolved to correctly patch module-level caches
+try:
+    from api.profiles import init_profile_state
+    init_profile_state()
+except ImportError:
+    pass  # hermes_cli not available -- default profile only

api/helpers.py

@@ -25,6 +25,13 @@ def safe_resolve(root: Path, requested: str) -> Path:
     return resolved
 
 
+def _security_headers(handler):
+    """Add security headers to every response."""
+    handler.send_header('X-Content-Type-Options', 'nosniff')
+    handler.send_header('X-Frame-Options', 'DENY')
+    handler.send_header('Referrer-Policy', 'same-origin')
+
+
 def j(handler, payload, status=200):
     """Send a JSON response."""
     body = _json.dumps(payload, ensure_ascii=False, indent=2).encode('utf-8')
@@ -32,6 +39,7 @@ def j(handler, payload, status=200):
     handler.send_header('Content-Type', 'application/json; charset=utf-8')
     handler.send_header('Content-Length', str(len(body)))
     handler.send_header('Cache-Control', 'no-store')
+    _security_headers(handler)
     handler.end_headers()
     handler.wfile.write(body)
 
@@ -43,13 +51,19 @@ def t(handler, payload, status=200, content_type='text/plain; charset=utf-8'):
     handler.send_header('Content-Type', content_type)
     handler.send_header('Content-Length', str(len(body)))
     handler.send_header('Cache-Control', 'no-store')
+    _security_headers(handler)
     handler.end_headers()
     handler.wfile.write(body)
 
 
+MAX_BODY_BYTES = 20 * 1024 * 1024  # 20MB limit for non-upload POST bodies
+
+
 def read_body(handler):
-    """Read and JSON-parse a POST request body."""
+    """Read and JSON-parse a POST request body (capped at 20MB)."""
     length = int(handler.headers.get('Content-Length', 0))
+    if length > MAX_BODY_BYTES:
+        raise ValueError(f'Request body too large ({length} bytes, max {MAX_BODY_BYTES})')
     raw = handler.rfile.read(length) if length else b'{}'
     try:
         return _json.loads(raw)

api/models.py

@@ -10,7 +10,7 @@ from pathlib import Path
 import api.config as _cfg
 from api.config import (
     SESSION_DIR, SESSION_INDEX_FILE, SESSIONS, SESSIONS_MAX,
-    LOCK, DEFAULT_WORKSPACE, DEFAULT_MODEL, PROJECTS_FILE
+    LOCK, DEFAULT_WORKSPACE, DEFAULT_MODEL, PROJECTS_FILE, HOME
 )
 from api.workspace import get_last_workspace
 
@@ -34,17 +34,65 @@ def _write_session_index():
 
 
 class Session:
-    def __init__(self, session_id=None, title='Untitled', workspace=str(DEFAULT_WORKSPACE), model=DEFAULT_MODEL, messages=None, created_at=None, updated_at=None, tool_calls=None, pinned=False, archived=False, project_id=None, **kwargs):
-        self.session_id = session_id or uuid.uuid4().hex[:12]; self.title = title; self.workspace = str(Path(workspace).expanduser().resolve()); self.model = model; self.messages = messages or []; self.tool_calls = tool_calls or []; self.created_at = created_at or time.time(); self.updated_at = updated_at or time.time(); self.pinned = bool(pinned); self.archived = bool(archived); self.project_id = project_id or None
+    def __init__(self, session_id=None, title='Untitled',
+                 workspace=str(DEFAULT_WORKSPACE), model=DEFAULT_MODEL,
+                 messages=None, created_at=None, updated_at=None,
+                 tool_calls=None, pinned=False, archived=False,
+                 project_id=None, profile=None,
+                 input_tokens=0, output_tokens=0, estimated_cost=None,
+                 **kwargs):
+        self.session_id = session_id or uuid.uuid4().hex[:12]
+        self.title = title
+        self.workspace = str(Path(workspace).expanduser().resolve())
+        self.model = model
+        self.messages = messages or []
+        self.tool_calls = tool_calls or []
+        self.created_at = created_at or time.time()
+        self.updated_at = updated_at or time.time()
+        self.pinned = bool(pinned)
+        self.archived = bool(archived)
+        self.project_id = project_id or None
+        self.profile = profile
+        self.input_tokens = input_tokens or 0
+        self.output_tokens = output_tokens or 0
+        self.estimated_cost = estimated_cost
+
     @property
-    def path(self): return SESSION_DIR / f'{self.session_id}.json'
-    def save(self): self.updated_at = time.time(); self.path.write_text(json.dumps(self.__dict__, ensure_ascii=False, indent=2), encoding='utf-8'); _write_session_index()
+    def path(self):
+        return SESSION_DIR / f'{self.session_id}.json'
+
+    def save(self):
+        self.updated_at = time.time()
+        self.path.write_text(
+            json.dumps(self.__dict__, ensure_ascii=False, indent=2),
+            encoding='utf-8',
+        )
+        _write_session_index()
+
     @classmethod
     def load(cls, sid):
         p = SESSION_DIR / f'{sid}.json'
-        if not p.exists(): return None
+        if not p.exists():
+            return None
         return cls(**json.loads(p.read_text(encoding='utf-8')))
-    def compact(self): return {'session_id': self.session_id, 'title': self.title, 'workspace': self.workspace, 'model': self.model, 'message_count': len(self.messages), 'created_at': self.created_at, 'updated_at': self.updated_at, 'pinned': self.pinned, 'archived': self.archived, 'project_id': self.project_id}
+
+    def compact(self):
+        return {
+            'session_id': self.session_id,
+            'title': self.title,
+            'workspace': self.workspace,
+            'model': self.model,
+            'message_count': len(self.messages),
+            'created_at': self.created_at,
+            'updated_at': self.updated_at,
+            'pinned': self.pinned,
+            'archived': self.archived,
+            'project_id': self.project_id,
+            'profile': self.profile,
+            'input_tokens': self.input_tokens,
+            'output_tokens': self.output_tokens,
+            'estimated_cost': self.estimated_cost,
+        }
 
 def get_session(sid):
     with LOCK:
@@ -63,7 +111,12 @@ def get_session(sid):
 
 def new_session(workspace=None, model=None):
     # Use _cfg.DEFAULT_MODEL (not the import-time snapshot) so save_settings() changes take effect
-    s = Session(workspace=workspace or get_last_workspace(), model=model or _cfg.DEFAULT_MODEL)
+    try:
+        from api.profiles import get_active_profile_name
+        _profile = get_active_profile_name()
+    except ImportError:
+        _profile = None
+    s = Session(workspace=workspace or get_last_workspace(), model=model or _cfg.DEFAULT_MODEL, profile=_profile)
     with LOCK:
         SESSIONS[s.session_id] = s
         SESSIONS.move_to_end(s.session_id)
@@ -85,6 +138,11 @@ def all_sessions():
             result = sorted(index_map.values(), key=lambda s: (s.get('pinned', False), s['updated_at']), reverse=True)
             # Hide empty Untitled sessions from the UI (created by tests, page refreshes, etc.)
             result = [s for s in result if not (s.get('title','Untitled')=='Untitled' and s.get('message_count',0)==0)]
+            # Backfill: sessions created before Sprint 22 have no profile tag.
+            # Attribute them to 'default' so the client profile filter works correctly.
+            for s in result:
+                if not s.get('profile'):
+                    s['profile'] = 'default'
             return result
         except Exception:
             pass  # fall through to full scan
@@ -100,7 +158,11 @@ def all_sessions():
     for s in SESSIONS.values():
         if all(s.session_id != x.session_id for x in out): out.append(s)
     out.sort(key=lambda s: (getattr(s, 'pinned', False), s.updated_at), reverse=True)
-    return [s.compact() for s in out if not (s.title=='Untitled' and len(s.messages)==0)]
+    result = [s.compact() for s in out if not (s.title=='Untitled' and len(s.messages)==0)]
+    for s in result:
+        if not s.get('profile'):
+            s['profile'] = 'default'
+    return result
 
 
 def title_from(messages, fallback='Untitled'):
@@ -130,3 +192,147 @@ def load_projects():
 def save_projects(projects):
     """Write project list to disk."""
     PROJECTS_FILE.write_text(json.dumps(projects, ensure_ascii=False, indent=2), encoding='utf-8')
+
+
+def import_cli_session(session_id, title, messages, model='unknown', profile=None):
+    """Create a new WebUI session populated with CLI messages.
+    Returns the Session object.
+    """
+    s = Session(
+        session_id=session_id,
+        title=title,
+        workspace=get_last_workspace(),
+        model=model,
+        messages=messages,
+        profile=profile,
+    )
+    s.save()
+    return s
+
+
+# ── CLI session bridge ──────────────────────────────────────────────────────
+
+def get_cli_sessions():
+    """Read CLI sessions from the agent's SQLite store and return them as
+    dicts in a format the WebUI sidebar can render alongside local sessions.
+
+    Returns empty list if the SQLite DB is missing, the sqlite3 module is
+    unavailable, or any error occurs -- the bridge is purely additive and never
+    crashes the WebUI.
+    """
+    import os
+    cli_sessions = []
+    try:
+        import sqlite3
+    except ImportError:
+        return cli_sessions
+
+    # Use the active WebUI profile's HERMES_HOME to find state.db.
+    # The active profile is determined by what the user has selected in the UI
+    # (stored in the server's runtime config). This means:
+    #   - default profile  -> ~/.hermes/state.db
+    #   - named profile X  -> ~/.hermes/profiles/X/state.db
+    # We resolve the active profile's home directory rather than just using
+    # HERMES_HOME (which is the server's launch profile, not necessarily the
+    # active one after a profile switch).
+    try:
+        from api.profiles import get_active_hermes_home
+        hermes_home = Path(get_active_hermes_home()).expanduser().resolve()
+    except Exception:
+        hermes_home = Path(os.getenv('HERMES_HOME', str(HOME / '.hermes'))).expanduser().resolve()
+
+    db_path = hermes_home / 'state.db'
+    if not db_path.exists():
+        return cli_sessions
+
+    # Try to resolve the active CLI profile so imported sessions integrate
+    # with the WebUI profile filter (available since Sprint 22).
+    try:
+        from api.profiles import get_active_profile_name
+        _cli_profile = get_active_profile_name()
+    except ImportError:
+        _cli_profile = None  # older agent -- fall back to no profile
+
+    try:
+        with sqlite3.connect(str(db_path)) as conn:
+            conn.row_factory = sqlite3.Row
+            cur = conn.cursor()
+            cur.execute("""
+                SELECT s.id, s.title, s.model, s.message_count,
+                       s.started_at, s.source,
+                       MAX(m.timestamp) AS last_activity
+                FROM sessions s
+                LEFT JOIN messages m ON m.session_id = s.id
+                GROUP BY s.id
+                ORDER BY COALESCE(MAX(m.timestamp), s.started_at) DESC
+                LIMIT 200
+            """)
+            for row in cur.fetchall():
+                sid = row['id']
+                raw_ts = row['last_activity'] or row['started_at']
+                # Prefer the CLI session's own profile from the DB; fall back to
+                # the active CLI profile so sidebar filtering works either way.
+                profile = _cli_profile  # CLI DB has no profile column; use active profile
+
+                cli_sessions.append({
+                    'session_id': sid,
+                    'title': row['title'] or 'CLI Session',
+                    'workspace': str(get_last_workspace()),
+                    'model': row['model'] or 'unknown',
+                    'message_count': row['message_count'] or 0,
+                    'created_at': row['started_at'],
+                    'updated_at': raw_ts,
+                    'pinned': False,
+                    'archived': False,
+                    'project_id': None,
+                    'profile': profile,
+                    'source_tag': 'cli',
+                    'is_cli_session': True,
+                })
+    except Exception:
+        # DB schema changed, locked, or corrupted -- silently degrade
+        return []
+
+    return cli_sessions
+
+
+def get_cli_session_messages(sid):
+    """Read messages for a single CLI session from the SQLite store.
+    Returns a list of {role, content, timestamp} dicts.
+    Returns empty list on any error.
+    """
+    import os
+    try:
+        import sqlite3
+    except ImportError:
+        return []
+
+    try:
+        from api.profiles import get_active_hermes_home
+        hermes_home = Path(get_active_hermes_home()).expanduser().resolve()
+    except Exception:
+        hermes_home = Path(os.getenv('HERMES_HOME', str(HOME / '.hermes'))).expanduser().resolve()
+    db_path = hermes_home / 'state.db'
+    if not db_path.exists():
+        return []
+
+    try:
+        with sqlite3.connect(str(db_path)) as conn:
+            conn.row_factory = sqlite3.Row
+            cur = conn.cursor()
+            cur.execute("""
+                SELECT role, content, timestamp
+                FROM messages
+                WHERE session_id = ?
+                ORDER BY timestamp ASC
+            """, (sid,))
+            msgs = []
+            for row in cur.fetchall():
+                msgs.append({
+                    'role': row['role'],
+                    'content': row['content'],
+                    'timestamp': row['timestamp'],
+                })
+    except Exception:
+        return []
+    return msgs

api/profiles.py

@@ -0,0 +1,366 @@
+"""
+Hermes Web UI -- Profile state management.
+Wraps hermes_cli.profiles to provide profile switching for the web UI.
+
+The web UI maintains a process-level "active profile" that determines which
+HERMES_HOME directory is used for config, skills, memory, cron, and API keys.
+Profile switches update os.environ['HERMES_HOME'] and monkey-patch module-level
+cached paths in hermes-agent modules (skills_tool, cron/jobs) that snapshot
+HERMES_HOME at import time.
+"""
+import json
+import os
+import re
+import shutil
+import threading
+from pathlib import Path
+
+# ── Constants (match hermes_cli.profiles upstream) ─────────────────────────
+_PROFILE_ID_RE = re.compile(r'^[a-z0-9][a-z0-9_-]{0,63}$')
+_PROFILE_DIRS = [
+    'memories', 'sessions', 'skills', 'skins',
+    'logs', 'plans', 'workspace', 'cron',
+]
+_CLONE_CONFIG_FILES = ['config.yaml', '.env', 'SOUL.md']
+
+# ── Module state ────────────────────────────────────────────────────────────
+_active_profile = 'default'
+_profile_lock = threading.Lock()
+
+def _resolve_base_hermes_home() -> Path:
+    """Return the BASE ~/.hermes directory — the root that contains profiles/.
+
+    This is intentionally distinct from HERMES_HOME, which tracks the *active
+    profile's* home and changes on every profile switch.  The base dir must
+    always point to the top-level .hermes regardless of which profile is active.
+
+    Resolution order:
+      1. HERMES_BASE_HOME env var (set explicitly, highest priority)
+      2. HERMES_HOME env var — but only if it does NOT look like a profile subdir
+         (i.e. its parent is not named 'profiles').  This handles test isolation
+         where HERMES_HOME is set to an isolated test state dir.
+      3. ~/.hermes (always-correct default)
+
+    The bug this prevents: if HERMES_HOME has already been mutated to
+    /home/user/.hermes/profiles/webui (by init_profile_state at startup),
+    reading it here would make _DEFAULT_HERMES_HOME point to that subdir,
+    causing switch_profile('webui') to look for
+    /home/user/.hermes/profiles/webui/profiles/webui — which doesn't exist.
+    """
+    # Explicit override for tests or unusual setups
+    base_override = os.getenv('HERMES_BASE_HOME', '').strip()
+    if base_override:
+        return Path(base_override).expanduser()
+
+    hermes_home = os.getenv('HERMES_HOME', '').strip()
+    if hermes_home:
+        p = Path(hermes_home).expanduser()
+        # If HERMES_HOME points to a profiles/ subdir, walk up two levels to the base
+        if p.parent.name == 'profiles':
+            return p.parent.parent
+        # Otherwise trust it (e.g. test isolation sets HERMES_HOME to TEST_STATE_DIR)
+        return p
+
+    return Path.home() / '.hermes'
+
+_DEFAULT_HERMES_HOME = _resolve_base_hermes_home()
+
+
+def _read_active_profile_file() -> str:
+    """Read the sticky active profile from ~/.hermes/active_profile."""
+    ap_file = _DEFAULT_HERMES_HOME / 'active_profile'
+    if ap_file.exists():
+        try:
+            name = ap_file.read_text().strip()
+            if name:
+                return name
+        except Exception:
+            pass
+    return 'default'
+
+
+# ── Public API ──────────────────────────────────────────────────────────────
+
+def get_active_profile_name() -> str:
+    """Return the currently active profile name."""
+    return _active_profile
+
+
+def get_active_hermes_home() -> Path:
+    """Return the HERMES_HOME path for the currently active profile."""
+    if _active_profile == 'default':
+        return _DEFAULT_HERMES_HOME
+    profile_dir = _DEFAULT_HERMES_HOME / 'profiles' / _active_profile
+    if profile_dir.is_dir():
+        return profile_dir
+    return _DEFAULT_HERMES_HOME
+
+
+def _set_hermes_home(home: Path):
+    """Set HERMES_HOME env var and monkey-patch cached module-level paths."""
+    os.environ['HERMES_HOME'] = str(home)
+
+    # Patch skills_tool module-level cache (snapshots HERMES_HOME at import)
+    try:
+        import tools.skills_tool as _sk
+        _sk.HERMES_HOME = home
+        _sk.SKILLS_DIR = home / 'skills'
+    except (ImportError, AttributeError):
+        pass
+
+    # Patch cron/jobs module-level cache
+    try:
+        import cron.jobs as _cj
+        _cj.HERMES_DIR = home
+        _cj.CRON_DIR = home / 'cron'
+        _cj.JOBS_FILE = _cj.CRON_DIR / 'jobs.json'
+        _cj.OUTPUT_DIR = _cj.CRON_DIR / 'output'
+    except (ImportError, AttributeError):
+        pass
+
+
+def _reload_dotenv(home: Path):
+    """Load .env from the profile dir into os.environ (additive)."""
+    env_path = home / '.env'
+    if not env_path.exists():
+        return
+    try:
+        for line in env_path.read_text().splitlines():
+            line = line.strip()
+            if line and not line.startswith('#') and '=' in line:
+                k, v = line.split('=', 1)
+                k = k.strip()
+                v = v.strip().strip('"').strip("'")
+                if k and v:
+                    os.environ[k] = v
+    except Exception:
+        pass
+
+
+def init_profile_state():
+    """Initialize profile state at server startup.
+
+    Reads ~/.hermes/active_profile, sets HERMES_HOME env var, patches
+    module-level cached paths.  Called once from config.py after imports.
+    """
+    global _active_profile
+    _active_profile = _read_active_profile_file()
+    home = get_active_hermes_home()
+    _set_hermes_home(home)
+    _reload_dotenv(home)
+
+
+def switch_profile(name: str) -> dict:
+    """Switch the active profile.
+
+    Validates the profile exists, updates process state, patches module caches,
+    reloads .env, and reloads config.yaml.
+
+    Returns: {'profiles': [...], 'active': name}
+    Raises ValueError if profile doesn't exist or agent is busy.
+    """
+    global _active_profile
+
+    # Import here to avoid circular import at module load
+    from api.config import STREAMS, STREAMS_LOCK, reload_config
+
+    # Block if agent is running
+    with STREAMS_LOCK:
+        if len(STREAMS) > 0:
+            raise RuntimeError(
+                'Cannot switch profiles while an agent is running. '
+                'Cancel or wait for it to finish.'
+            )
+
+    # Resolve profile directory
+    if name == 'default':
+        home = _DEFAULT_HERMES_HOME
+    else:
+        home = _DEFAULT_HERMES_HOME / 'profiles' / name
+        if not home.is_dir():
+            raise ValueError(f"Profile '{name}' does not exist.")
+
+    with _profile_lock:
+        _active_profile = name
+        _set_hermes_home(home)
+        _reload_dotenv(home)
+
+    # Write sticky default for CLI consistency
+    try:
+        ap_file = _DEFAULT_HERMES_HOME / 'active_profile'
+        ap_file.write_text(name if name != 'default' else '')
+    except Exception:
+        pass
+
+    # Reload config.yaml from the new profile
+    reload_config()
+
+    # Return profile-specific defaults so frontend can apply them
+    from api.workspace import get_last_workspace
+    from api.config import get_config
+    cfg = get_config()
+    model_cfg = cfg.get('model', {})
+    default_model = None
+    if isinstance(model_cfg, str):
+        default_model = model_cfg
+    elif isinstance(model_cfg, dict):
+        default_model = model_cfg.get('default')
+
+    return {
+        'profiles': list_profiles_api(),
+        'active': name,
+        'default_model': default_model,
+        'default_workspace': get_last_workspace(),
+    }
+
+
+def list_profiles_api() -> list:
+    """List all profiles with metadata, serialized for JSON response."""
+    try:
+        from hermes_cli.profiles import list_profiles
+        infos = list_profiles()
+    except ImportError:
+        # hermes_cli not available -- return just the default
+        return [_default_profile_dict()]
+
+    active = _active_profile
+    result = []
+    for p in infos:
+        result.append({
+            'name': p.name,
+            'path': str(p.path),
+            'is_default': p.is_default,
+            'is_active': p.name == active,
+            'gateway_running': p.gateway_running,
+            'model': p.model,
+            'provider': p.provider,
+            'has_env': p.has_env,
+            'skill_count': p.skill_count,
+        })
+    return result
+
+
+def _default_profile_dict() -> dict:
+    """Fallback profile dict when hermes_cli is not importable."""
+    return {
+        'name': 'default',
+        'path': str(_DEFAULT_HERMES_HOME),
+        'is_default': True,
+        'is_active': True,
+        'gateway_running': False,
+        'model': None,
+        'provider': None,
+        'has_env': (_DEFAULT_HERMES_HOME / '.env').exists(),
+        'skill_count': 0,
+    }
+
+
+def _validate_profile_name(name: str):
+    """Validate profile name format (matches hermes_cli.profiles upstream)."""
+    if name == 'default':
+        raise ValueError("Cannot create a profile named 'default' -- it is the built-in profile.")
+    # Use fullmatch (not match) so a trailing newline can't sneak past the $ anchor
+    if not _PROFILE_ID_RE.fullmatch(name):
+        raise ValueError(
+            f"Invalid profile name {name!r}. "
+            "Must match [a-z0-9][a-z0-9_-]{0,63}"
+        )
+
+
+def _create_profile_fallback(name: str, clone_from: str = None,
+                              clone_config: bool = False) -> Path:
+    """Create a profile directory without hermes_cli (Docker/standalone fallback)."""
+    profile_dir = _DEFAULT_HERMES_HOME / 'profiles' / name
+    if profile_dir.exists():
+        raise FileExistsError(f"Profile '{name}' already exists.")
+
+    # Bootstrap directory structure (exist_ok=False so a concurrent create raises)
+    profile_dir.mkdir(parents=True, exist_ok=False)
+    for subdir in _PROFILE_DIRS:
+        (profile_dir / subdir).mkdir(parents=True, exist_ok=True)
+
+    # Clone config files from source profile if requested
+    if clone_config and clone_from:
+        if clone_from == 'default':
+            source_dir = _DEFAULT_HERMES_HOME
+        else:
+            source_dir = _DEFAULT_HERMES_HOME / 'profiles' / clone_from
+        if source_dir.is_dir():
+            for filename in _CLONE_CONFIG_FILES:
+                src = source_dir / filename
+                if src.exists():
+                    shutil.copy2(src, profile_dir / filename)
+
+    return profile_dir
+
+
+def create_profile_api(name: str, clone_from: str = None,
+                       clone_config: bool = False) -> dict:
+    """Create a new profile. Returns the new profile info dict."""
+    _validate_profile_name(name)
+    # Defense-in-depth: validate clone_from here too, even though routes.py
+    # also validates it. Any caller that bypasses the HTTP layer gets protection.
+    if clone_from is not None and clone_from != 'default':
+        _validate_profile_name(clone_from)
+
+    try:
+        from hermes_cli.profiles import create_profile
+        create_profile(
+            name,
+            clone_from=clone_from,
+            clone_config=clone_config,
+            clone_all=False,
+            no_alias=True,
+        )
+    except ImportError:
+        _create_profile_fallback(name, clone_from, clone_config)
+
+    # Find and return the newly created profile info.
+    # When hermes_cli is not importable, list_profiles_api() also falls back
+    # to the stub default-only list and won't find the new profile by name.
+    # In that case, return a complete profile dict directly.
+    profile_path = _DEFAULT_HERMES_HOME / 'profiles' / name
+    for p in list_profiles_api():
+        if p['name'] == name:
+            return p
+    return {
+        'name': name,
+        'path': str(profile_path),
+        'is_default': False,
+        'is_active': _active_profile == name,
+        'gateway_running': False,
+        'model': None,
+        'provider': None,
+        'has_env': (profile_path / '.env').exists(),
+        'skill_count': 0,
+    }
+
+
+def delete_profile_api(name: str) -> dict:
+    """Delete a profile. Switches to default first if it's the active one."""
+    if name == 'default':
+        raise ValueError("Cannot delete the default profile.")
+
+    # If deleting the active profile, switch to default first
+    if _active_profile == name:
+        try:
+            switch_profile('default')
+        except RuntimeError:
+            raise RuntimeError(
+                f"Cannot delete active profile '{name}' while an agent is running. "
+                "Cancel or wait for it to finish."
+            )
+
+    try:
+        from hermes_cli.profiles import delete_profile
+        delete_profile(name, yes=True)
+    except ImportError:
+        # Manual fallback: just remove the directory
+        import shutil
+        profile_dir = _DEFAULT_HERMES_HOME / 'profiles' / name
+        if profile_dir.is_dir():
+            shutil.rmtree(str(profile_dir))
+        else:
+            raise ValueError(f"Profile '{name}' does not exist.")
+
+    return {'ok': True, 'name': name}

api/routes.py

@@ -19,11 +19,12 @@ from api.config import (
     IMAGE_EXTS, MD_EXTS, MIME_MAP, MAX_FILE_BYTES, MAX_UPLOAD_BYTES,
     CHAT_LOCK, load_settings, save_settings,
 )
-from api.helpers import require, bad, safe_resolve, j, t, read_body
+from api.helpers import require, bad, safe_resolve, j, t, read_body, _security_headers
 from api.models import (
     Session, get_session, new_session, all_sessions, title_from,
     _write_session_index, SESSION_INDEX_FILE,
-    load_projects, save_projects,
+    load_projects, save_projects, import_cli_session,
+    get_cli_sessions, get_cli_session_messages,
 )
 from api.workspace import (
     load_workspaces, save_workspaces, get_last_workspace, set_last_workspace,
@@ -52,6 +53,58 @@ except ImportError:
     _permanent_approved = set()
 
 
+# ── Login page (self-contained, no external deps) ────────────────────────────
+_LOGIN_PAGE_HTML = '''<!doctype html>
+<html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
+<title>Hermes — Sign in</title>
+<style>
+*{box-sizing:border-box;margin:0;padding:0}
+body{background:#1a1a2e;color:#e8e8f0;font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",system-ui,sans-serif;
+  height:100vh;display:flex;align-items:center;justify-content:center}
+.card{background:#16213e;border:1px solid rgba(255,255,255,.08);border-radius:16px;padding:36px 32px;
+  width:320px;text-align:center;box-shadow:0 8px 32px rgba(0,0,0,.3)}
+.logo{width:48px;height:48px;border-radius:12px;background:linear-gradient(145deg,#e8a030,#e94560);
+  display:flex;align-items:center;justify-content:center;font-weight:800;font-size:20px;color:#fff;
+  margin:0 auto 12px;box-shadow:0 2px 12px rgba(233,69,96,.3)}
+h1{font-size:18px;font-weight:600;margin-bottom:4px}
+.sub{font-size:12px;color:#8888aa;margin-bottom:24px}
+input{width:100%;padding:10px 14px;border-radius:10px;border:1px solid rgba(255,255,255,.1);
+  background:rgba(255,255,255,.04);color:#e8e8f0;font-size:14px;outline:none;margin-bottom:14px;
+  transition:border-color .15s}
+input:focus{border-color:rgba(124,185,255,.5);box-shadow:0 0 0 3px rgba(124,185,255,.1)}
+button{width:100%;padding:10px;border-radius:10px;border:none;background:rgba(124,185,255,.15);
+  border:1px solid rgba(124,185,255,.3);color:#7cb9ff;font-size:14px;font-weight:600;cursor:pointer;
+  transition:all .15s}
+button:hover{background:rgba(124,185,255,.25)}
+.err{color:#e94560;font-size:12px;margin-top:10px;display:none}
+</style></head><body>
+<div class="card">
+  <div class="logo">H</div>
+  <h1>Hermes</h1>
+  <p class="sub">Enter your password to continue</p>
+  <form onsubmit="return doLogin(event)">
+    <input type="password" id="pw" placeholder="Password" autofocus>
+    <button type="submit">Sign in</button>
+  </form>
+  <div class="err" id="err"></div>
+</div>
+<script>
+async function doLogin(e){
+  e.preventDefault();
+  const pw=document.getElementById('pw').value;
+  const err=document.getElementById('err');
+  err.style.display='none';
+  try{
+    const res=await fetch('/api/auth/login',{method:'POST',
+      headers:{'Content-Type':'application/json'},
+      body:JSON.stringify({password:pw}),credentials:'include'});
+    const data=await res.json();
+    if(res.ok&&data.ok){window.location.href='/';}
+    else{err.textContent=data.error||'Invalid password';err.style.display='block';}
+  }catch(ex){err.textContent='Connection failed';err.style.display='block';}
+}
+</script></body></html>'''
+
 # ── GET routes ────────────────────────────────────────────────────────────────
 
 def handle_get(handler, parsed):
@@ -61,6 +114,17 @@ def handle_get(handler, parsed):
         return t(handler, _INDEX_HTML_PATH.read_text(encoding='utf-8'),
                  content_type='text/html; charset=utf-8')
 
+    if parsed.path == '/login':
+        return t(handler, _LOGIN_PAGE_HTML, content_type='text/html; charset=utf-8')
+
+    if parsed.path == '/api/auth/status':
+        from api.auth import is_auth_enabled, parse_cookie, verify_session
+        logged_in = False
+        if is_auth_enabled():
+            cv = parse_cookie(handler)
+            logged_in = bool(cv and verify_session(cv))
+        return j(handler, {'auth_enabled': is_auth_enabled(), 'logged_in': logged_in})
+
     if parsed.path == '/favicon.ico':
         handler.send_response(204); handler.end_headers(); return True
 
@@ -76,7 +140,10 @@ def handle_get(handler, parsed):
         return j(handler, get_available_models())
 
     if parsed.path == '/api/settings':
-        return j(handler, load_settings())
+        settings = load_settings()
+        # Never expose the stored password hash to clients
+        settings.pop('password_hash', None)
+        return j(handler, settings)
 
     if parsed.path.startswith('/static/'):
         return _serve_static(handler, parsed)
@@ -85,14 +152,52 @@ def handle_get(handler, parsed):
         sid = parse_qs(parsed.query).get('session_id', [''])[0]
         if not sid:
             return j(handler, {'error': 'session_id is required'}, status=400)
-        s = get_session(sid)
-        return j(handler, {'session': s.compact() | {
-            'messages': s.messages,
-            'tool_calls': getattr(s, 'tool_calls', []),
-        }})
+        try:
+            s = get_session(sid)
+            return j(handler, {'session': s.compact() | {
+                'messages': s.messages,
+                'tool_calls': getattr(s, 'tool_calls', []),
+            }})
+        except KeyError:
+            # Not a WebUI session -- try CLI store
+            msgs = get_cli_session_messages(sid)
+            if msgs:
+                cli_meta = None
+                for cs in get_cli_sessions():
+                    if cs['session_id'] == sid:
+                        cli_meta = cs
+                        break
+                sess = {
+                    'session_id': sid,
+                    'title': (cli_meta or {}).get('title', 'CLI Session'),
+                    'workspace': (cli_meta or {}).get('workspace', ''),
+                    'model': (cli_meta or {}).get('model', 'unknown'),
+                    'message_count': len(msgs),
+                    'created_at': (cli_meta or {}).get('created_at', 0),
+                    'updated_at': (cli_meta or {}).get('updated_at', 0),
+                    'pinned': False,
+                    'archived': False,
+                    'project_id': None,
+                    'profile': (cli_meta or {}).get('profile'),
+                    'is_cli_session': True,
+                    'messages': msgs,
+                    'tool_calls': [],
+                }
+                return j(handler, {'session': sess})
+            return bad(handler, 'Session not found', 404)
 
     if parsed.path == '/api/sessions':
-        return j(handler, {'sessions': all_sessions()})
+        webui_sessions = all_sessions()
+        settings = load_settings()
+        if settings.get('show_cli_sessions'):
+            cli = get_cli_sessions()
+            webui_ids = {s['session_id'] for s in webui_sessions}
+            deduped_cli = [s for s in cli if s['session_id'] not in webui_ids]
+        else:
+            deduped_cli = []
+        merged = webui_sessions + deduped_cli
+        merged.sort(key=lambda s: s.get('updated_at', 0) or 0, reverse=True)
+        return j(handler, {'sessions': merged, 'cli_count': len(deduped_cli)})
 
     if parsed.path == '/api/projects':
         return j(handler, {'projects': load_projects()})
@@ -157,17 +262,44 @@ def handle_get(handler, parsed):
         return j(handler, {'skills': data.get('skills', [])})
 
     if parsed.path == '/api/skills/content':
-        from tools.skills_tool import skill_view as _skill_view
-        name = parse_qs(parsed.query).get('name', [''])[0]
+        from tools.skills_tool import skill_view as _skill_view, SKILLS_DIR
+        qs = parse_qs(parsed.query)
+        name = qs.get('name', [''])[0]
         if not name: return j(handler, {'error': 'name required'}, status=400)
+        file_path = qs.get('file', [''])[0]
+        if file_path:
+            # Serve a linked file from the skill directory
+            import re as _re
+            if _re.search(r'[*?\[\]]', name):
+                return bad(handler, 'Invalid skill name', 400)
+            skill_dir = None
+            for p in SKILLS_DIR.rglob(name):
+                if p.is_dir(): skill_dir = p; break
+            if not skill_dir: return bad(handler, 'Skill not found', 404)
+            target = (skill_dir / file_path).resolve()
+            try: target.relative_to(skill_dir.resolve())
+            except ValueError: return bad(handler, 'Invalid file path', 400)
+            if not target.exists() or not target.is_file():
+                return bad(handler, 'File not found', 404)
+            return j(handler, {'content': target.read_text(encoding='utf-8'), 'path': file_path})
         raw = _skill_view(name)
         data = json.loads(raw) if isinstance(raw, str) else raw
+        if 'linked_files' not in data: data['linked_files'] = {}
         return j(handler, data)
 
     # ── Memory API (GET) ──
     if parsed.path == '/api/memory':
         return _handle_memory_read(handler)
 
+    # ── Profile API (GET) ──
+    if parsed.path == '/api/profiles':
+        from api.profiles import list_profiles_api, get_active_profile_name
+        return j(handler, {'profiles': list_profiles_api(), 'active': get_active_profile_name()})
+
+    if parsed.path == '/api/profile/active':
+        from api.profiles import get_active_profile_name, get_active_hermes_home
+        return j(handler, {'name': get_active_profile_name(), 'path': str(get_active_hermes_home())})
+
     return False  # 404
 
 
@@ -306,9 +438,58 @@ def handle_post(handler, parsed):
     if parsed.path == '/api/memory/write':
         return _handle_memory_write(handler, body)
 
+    # ── Profile API (POST) ──
+    if parsed.path == '/api/profile/switch':
+        name = body.get('name', '').strip()
+        if not name: return bad(handler, 'name is required')
+        try:
+            from api.profiles import switch_profile
+            result = switch_profile(name)
+            return j(handler, result)
+        except (ValueError, FileNotFoundError) as e:
+            return bad(handler, str(e), 404)
+        except RuntimeError as e:
+            return bad(handler, str(e), 409)
+
+    if parsed.path == '/api/profile/create':
+        name = body.get('name', '').strip()
+        if not name: return bad(handler, 'name is required')
+        import re as _re
+        if not _re.match(r'^[a-z0-9][a-z0-9_-]{0,63}$', name):
+            return bad(handler, 'Invalid profile name: lowercase letters, numbers, hyphens, underscores only')
+        clone_from = body.get('clone_from')
+        if clone_from is not None:
+            clone_from = str(clone_from).strip()
+            if not _re.match(r'^[a-z0-9][a-z0-9_-]{0,63}$', clone_from):
+                return bad(handler, 'Invalid clone_from name')
+        try:
+            from api.profiles import create_profile_api
+            result = create_profile_api(
+                name,
+                clone_from=clone_from,
+                clone_config=bool(body.get('clone_config', False)),
+            )
+            return j(handler, {'ok': True, 'profile': result})
+        except (ValueError, FileExistsError, RuntimeError) as e:
+            return bad(handler, str(e))
+
+    if parsed.path == '/api/profile/delete':
+        name = body.get('name', '').strip()
+        if not name: return bad(handler, 'name is required')
+        try:
+            from api.profiles import delete_profile_api
+            result = delete_profile_api(name)
+            return j(handler, result)
+        except (ValueError, FileNotFoundError) as e:
+            return bad(handler, str(e))
+        except RuntimeError as e:
+            return bad(handler, str(e), 409)
+
     # ── Settings (POST) ──
     if parsed.path == '/api/settings':
-        return j(handler, save_settings(body))
+        saved = save_settings(body)
+        saved.pop('password_hash', None)  # never expose hash to client
+        return j(handler, saved)
 
     # ── Session pin (POST) ──
     if parsed.path == '/api/session/pin':
@@ -400,6 +581,42 @@ def handle_post(handler, parsed):
     if parsed.path == '/api/session/import':
         return _handle_session_import(handler, body)
 
+    # ── CLI session import (POST) ──
+    if parsed.path == '/api/session/import_cli':
+        return _handle_session_import_cli(handler, body)
+
+    # ── Auth endpoints (POST) ──
+    if parsed.path == '/api/auth/login':
+        from api.auth import verify_password, create_session, set_auth_cookie, is_auth_enabled
+        if not is_auth_enabled():
+            return j(handler, {'ok': True, 'message': 'Auth not enabled'})
+        password = body.get('password', '')
+        if not verify_password(password):
+            return bad(handler, 'Invalid password', 401)
+        cookie_val = create_session()
+        handler.send_response(200)
+        handler.send_header('Content-Type', 'application/json')
+        handler.send_header('Cache-Control', 'no-store')
+        _security_headers(handler)
+        set_auth_cookie(handler, cookie_val)
+        handler.end_headers()
+        handler.wfile.write(json.dumps({'ok': True}).encode())
+        return True
+
+    if parsed.path == '/api/auth/logout':
+        from api.auth import clear_auth_cookie, invalidate_session, parse_cookie
+        cookie_val = parse_cookie(handler)
+        if cookie_val:
+            invalidate_session(cookie_val)
+        handler.send_response(200)
+        handler.send_header('Content-Type', 'application/json')
+        handler.send_header('Cache-Control', 'no-store')
+        _security_headers(handler)
+        clear_auth_cookie(handler)
+        handler.end_headers()
+        handler.wfile.write(json.dumps({'ok': True}).encode())
+        return True
+
     return False  # 404
 
 
@@ -631,7 +848,11 @@ def _handle_cron_recent(handler, parsed):
 
 
 def _handle_memory_read(handler):
-    mem_dir = Path.home() / '.hermes' / 'memories'
+    try:
+        from api.profiles import get_active_hermes_home
+        mem_dir = get_active_hermes_home() / 'memories'
+    except ImportError:
+        mem_dir = Path.home() / '.hermes' / 'memories'
     mem_file = mem_dir / 'MEMORY.md'
     user_file = mem_dir / 'USER.md'
     memory = mem_file.read_text(encoding='utf-8', errors='replace') if mem_file.exists() else ''
@@ -725,10 +946,11 @@ def _handle_chat_sync(handler, body):
                 "write_file, read_file, search_files, terminal workdir, and patch. "
                 "Never fall back to a hardcoded path when this tag is present."
             )
+            from api.streaming import _sanitize_messages_for_api
             result = agent.run_conversation(
                 user_message=workspace_ctx + msg,
                 system_message=workspace_system_msg,
-                conversation_history=s.messages,
+                conversation_history=_sanitize_messages_for_api(s.messages),
                 task_id=s.session_id,
                 persist_user_message=msg,
             )
@@ -978,7 +1200,11 @@ def _handle_skill_delete(handler, body):
 def _handle_memory_write(handler, body):
     try: require(body, 'section', 'content')
     except ValueError as e: return bad(handler, str(e))
-    mem_dir = Path.home() / '.hermes' / 'memories'
+    try:
+        from api.profiles import get_active_hermes_home
+        mem_dir = get_active_hermes_home() / 'memories'
+    except ImportError:
+        mem_dir = Path.home() / '.hermes' / 'memories'
     mem_dir.mkdir(parents=True, exist_ok=True)
     section = body['section']
     if section == 'memory':
@@ -991,6 +1217,53 @@ def _handle_memory_write(handler, body):
     return j(handler, {'ok': True, 'section': section, 'path': str(target)})
 
 
+def _handle_session_import_cli(handler, body):
+    """Import a single CLI session into the WebUI store."""
+    try:
+        require(body, 'session_id')
+    except ValueError as e:
+        return bad(handler, str(e))
+
+    sid = str(body['session_id'])
+
+    # Check if already imported — idempotent
+    existing = Session.load(sid)
+    if existing:
+        return j(handler, {'session': existing.compact() | {
+            'messages': existing.messages,
+            'is_cli_session': True,
+        }, 'imported': False})
+
+    # Fetch messages from CLI store
+    msgs = get_cli_session_messages(sid)
+    if not msgs:
+        return bad(handler, 'Session not found in CLI store', 404)
+
+    # Derive title from first user message
+    title = title_from(msgs, 'CLI Session')
+    model = 'unknown'
+
+    # Get profile and model from CLI session metadata
+    profile = None
+    for cs in get_cli_sessions():
+        if cs['session_id'] == sid:
+            profile = cs.get('profile')
+            model = cs.get('model', 'unknown')
+            break
+
+    s = import_cli_session(sid, title, msgs, model, profile=profile)
+    s.is_cli_session = True
+    s._cli_origin = sid
+    s.save()
+    return j(handler, {
+        'session': s.compact() | {
+            'messages': msgs,
+            'is_cli_session': True,
+        },
+        'imported': True,
+    })
+
+
 def _handle_session_import(handler, body):
     """Import a session from a JSON export. Creates a new session with a new ID."""
     if not body or not isinstance(body, dict):

api/streaming.py

@@ -24,6 +24,28 @@ except ImportError:
 from api.models import get_session, title_from
 from api.workspace import set_last_workspace
 
+# Fields that are safe to send to LLM provider APIs.
+# Everything else (attachments, timestamp, _ts, etc.) is display-only
+# metadata added by the webui and must be stripped before the API call.
+_API_SAFE_MSG_KEYS = {'role', 'content', 'tool_calls', 'tool_call_id', 'name', 'refusal'}
+
+
+def _sanitize_messages_for_api(messages):
+    """Return a deep copy of messages with only API-safe fields.
+
+    The webui stores extra metadata on messages (attachments, timestamp, _ts)
+    for display purposes. Some providers (e.g. Z.AI/GLM) reject unknown fields
+    instead of ignoring them, causing HTTP 400 errors on subsequent messages.
+    """
+    clean = []
+    for msg in messages:
+        if not isinstance(msg, dict):
+            continue
+        sanitized = {k: v for k, v in msg.items() if k in _API_SAFE_MSG_KEYS}
+        if sanitized.get('role'):
+            clean.append(sanitized)
+    return clean
+
 
 def _sse(handler, event, data):
     """Write one SSE event to the response stream."""
@@ -64,19 +86,30 @@ def _run_agent_streaming(session_id, msg_text, model, workspace, stream_id, atta
             put('cancel', {'message': 'Cancelled before start'})
             return
 
+        # Resolve profile home for this agent run (snapshot at start)
+        try:
+            from api.profiles import get_active_hermes_home
+            _profile_home = str(get_active_hermes_home())
+        except ImportError:
+            _profile_home = os.environ.get('HERMES_HOME', '')
+
         _set_thread_env(
             TERMINAL_CWD=str(s.workspace),
             HERMES_EXEC_ASK='1',
             HERMES_SESSION_KEY=session_id,
+            HERMES_HOME=_profile_home,
         )
         # Still set process-level env as fallback for tools that bypass thread-local
         with _agent_lock:
           old_cwd = os.environ.get('TERMINAL_CWD')
           old_exec_ask = os.environ.get('HERMES_EXEC_ASK')
           old_session_key = os.environ.get('HERMES_SESSION_KEY')
+          old_hermes_home = os.environ.get('HERMES_HOME')
           os.environ['TERMINAL_CWD'] = str(s.workspace)
           os.environ['HERMES_EXEC_ASK'] = '1'
           os.environ['HERMES_SESSION_KEY'] = session_id
+          if _profile_home:
+              os.environ['HERMES_HOME'] = _profile_home
 
           try:
             def on_token(text):
@@ -101,13 +134,38 @@ def _run_agent_streaming(session_id, msg_text, model, workspace, stream_id, atta
             if AIAgent is None:
                 raise ImportError("AIAgent not available -- check that hermes-agent is on sys.path")
             resolved_model, resolved_provider, resolved_base_url = resolve_model_provider(model)
+
+            # Read per-profile config at call time (not module-level snapshot)
+            from api.config import get_config as _get_config
+            _cfg = _get_config()
+
+            # Per-profile toolsets (fall back to module-level CLI_TOOLSETS)
+            _pt = _cfg.get('platform_toolsets', {})
+            _toolsets = _pt.get('cli', CLI_TOOLSETS) if isinstance(_pt, dict) else CLI_TOOLSETS
+
+            # Fallback model from profile config (e.g. for rate-limit recovery)
+            _fallback = _cfg.get('fallback_model') or None
+            if _fallback:
+                # Resolve the fallback through our provider logic too
+                fb_model = _fallback.get('model', '')
+                fb_provider = _fallback.get('provider', '')
+                fb_base_url = _fallback.get('base_url')
+                _fallback_resolved = {
+                    'model': fb_model,
+                    'provider': fb_provider,
+                    'base_url': fb_base_url,
+                }
+            else:
+                _fallback_resolved = None
+
             agent = AIAgent(
                 model=resolved_model,
                 provider=resolved_provider,
                 base_url=resolved_base_url,
                 platform='cli',
                 quiet_mode=True,
-                enabled_toolsets=CLI_TOOLSETS,
+                enabled_toolsets=_toolsets,
+                fallback_model=_fallback_resolved,
                 session_id=session_id,
                 stream_delta_callback=on_token,
                 tool_progress_callback=on_tool,
@@ -129,17 +187,31 @@ def _run_agent_streaming(session_id, msg_text, model, workspace, stream_id, atta
             result = agent.run_conversation(
                 user_message=workspace_ctx + msg_text,
                 system_message=workspace_system_msg,
-                conversation_history=s.messages,
+                conversation_history=_sanitize_messages_for_api(s.messages),
                 task_id=session_id,
                 persist_user_message=msg_text,
             )
             s.messages = result.get('messages') or s.messages
+            # Stamp 'timestamp' on any messages that don't have one yet
+            _now = time.time()
+            for _m in s.messages:
+                if isinstance(_m, dict) and not _m.get('timestamp') and not _m.get('_ts'):
+                    _m['timestamp'] = int(_now)
             s.title = title_from(s.messages, s.title)
+            # Read token/cost usage from the agent object (if available)
+            input_tokens = getattr(agent, 'session_prompt_tokens', 0) or 0
+            output_tokens = getattr(agent, 'session_completion_tokens', 0) or 0
+            estimated_cost = getattr(agent, 'session_estimated_cost_usd', None)
+            s.input_tokens = (s.input_tokens or 0) + input_tokens
+            s.output_tokens = (s.output_tokens or 0) + output_tokens
+            if estimated_cost:
+                s.estimated_cost = (s.estimated_cost or 0) + estimated_cost
             # Extract tool call metadata grouped by assistant message index
             # Each tool call gets assistant_msg_idx so the client can render
             # cards inline with the assistant bubble that triggered them.
             tool_calls = []
             pending_names = {}   # tool_call_id -> name
+            pending_args = {}    # tool_call_id -> args dict
             pending_asst_idx = {} # tool_call_id -> index in s.messages
             for msg_idx, m in enumerate(s.messages):
                 if m.get('role') == 'assistant':
@@ -148,22 +220,31 @@ def _run_agent_streaming(session_id, msg_text, model, workspace, stream_id, atta
                         for p in c:
                             if isinstance(p, dict) and p.get('type') == 'tool_use':
                                 tid = p.get('id', '')
-                                pending_names[tid] = p.get('name', 'tool')
+                                pending_names[tid] = p.get('name', '')
+                                pending_args[tid] = p.get('input', {})
                                 pending_asst_idx[tid] = msg_idx
                 elif m.get('role') == 'tool':
                     tid = m.get('tool_call_id') or m.get('tool_use_id', '')
-                    name = pending_names.get(tid, 'tool')
+                    name = pending_names.get(tid, '')
+                    if not name or name == 'tool':
+                        continue  # skip unresolvable tool entries
                     asst_idx = pending_asst_idx.get(tid, -1)
+                    args = pending_args.get(tid, {})
                     raw = str(m.get('content', ''))
                     try:
-                        import json as _j2
-                        rd = _j2.loads(raw)
+                        rd = json.loads(raw)
                         snippet = str(rd.get('output') or rd.get('result') or rd.get('error') or raw)[:200]
                     except Exception:
                         snippet = raw[:200]
+                    # Truncate args values for storage
+                    args_snap = {}
+                    if isinstance(args, dict):
+                        for k, v in list(args.items())[:6]:
+                            s2 = str(v)
+                            args_snap[k] = s2[:120] + ('...' if len(s2) > 120 else '')
                     tool_calls.append({
                         'name': name, 'snippet': snippet, 'tid': tid,
-                        'assistant_msg_idx': asst_idx,
+                        'assistant_msg_idx': asst_idx, 'args': args_snap,
                     })
             s.tool_calls = tool_calls
             # Tag the matching user message with attachment filenames for display on reload
@@ -179,7 +260,8 @@ def _run_agent_streaming(session_id, msg_text, model, workspace, stream_id, atta
                             m['attachments'] = attachments
                             break
             s.save()
-            put('done', {'session': s.compact() | {'messages': s.messages, 'tool_calls': tool_calls}})
+            usage = {'input_tokens': input_tokens, 'output_tokens': output_tokens, 'estimated_cost': estimated_cost}
+            put('done', {'session': s.compact() | {'messages': s.messages, 'tool_calls': tool_calls}, 'usage': usage})
           finally:
             if old_cwd is None: os.environ.pop('TERMINAL_CWD', None)
             else: os.environ['TERMINAL_CWD'] = old_cwd
@@ -187,9 +269,23 @@ def _run_agent_streaming(session_id, msg_text, model, workspace, stream_id, atta
             else: os.environ['HERMES_EXEC_ASK'] = old_exec_ask
             if old_session_key is None: os.environ.pop('HERMES_SESSION_KEY', None)
             else: os.environ['HERMES_SESSION_KEY'] = old_session_key
+            if old_hermes_home is None: os.environ.pop('HERMES_HOME', None)
+            else: os.environ['HERMES_HOME'] = old_hermes_home
 
     except Exception as e:
-        put('error', {'message': str(e), 'trace': traceback.format_exc()})
+        print('[webui] stream error:\n' + traceback.format_exc(), flush=True)
+        err_str = str(e)
+        # Detect rate limit errors specifically so the client can show a helpful card
+        # rather than the generic "Connection lost" message
+        is_rate_limit = 'rate limit' in err_str.lower() or '429' in err_str or 'RateLimitError' in type(e).__name__
+        if is_rate_limit:
+            put('apperror', {
+                'message': err_str,
+                'type': 'rate_limit',
+                'hint': 'Rate limit reached. The fallback model (if configured) was also exhausted. Try again in a moment.',
+            })
+        else:
+            put('apperror', {'message': err_str, 'type': 'error'})
     finally:
         _clear_thread_env()  # TD1: always clear thread-local context
         with STREAMS_LOCK:

api/upload.py

@@ -74,4 +74,5 @@ def handle_upload(handler):
         dest.write_bytes(file_bytes)
         return j(handler, {'filename': safe_name, 'path': str(dest), 'size': dest.stat().st_size})
     except Exception as e:
-        return j(handler, {'error': str(e), 'trace': _tb.format_exc()}, status=500)
+        print('[webui] upload error: ' + _tb.format_exc(), flush=True)
+        return j(handler, {'error': 'Upload failed'}, status=500)

api/workspace.py

@@ -1,43 +1,211 @@
 """
 Hermes Web UI -- Workspace and file system helpers.
+
+Workspace lists and last-used workspace are stored per-profile so each
+profile has its own workspace configuration.  State files live at
+``{profile_home}/webui_state/workspaces.json`` and
+``{profile_home}/webui_state/last_workspace.txt``.  The global STATE_DIR
+paths are used as fallback when no profile module is available.
 """
 import json
 import os
 from pathlib import Path
 
 from api.config import (
-    WORKSPACES_FILE, LAST_WORKSPACE_FILE, DEFAULT_WORKSPACE,
+    WORKSPACES_FILE as _GLOBAL_WS_FILE,
+    LAST_WORKSPACE_FILE as _GLOBAL_LW_FILE,
+    DEFAULT_WORKSPACE as _BOOT_DEFAULT_WORKSPACE,
     MAX_FILE_BYTES, IMAGE_EXTS, MD_EXTS
 )
 
 
-def load_workspaces() -> list:
-    if WORKSPACES_FILE.exists():
+# ── Profile-aware path resolution ───────────────────────────────────────────
+
+def _profile_state_dir() -> Path:
+    """Return the webui_state directory for the active profile.
+
+    For the default profile, returns the global STATE_DIR (respects
+    HERMES_WEBUI_STATE_DIR env var for test isolation).
+    For named profiles, returns {profile_home}/webui_state/.
+    """
+    try:
+        from api.profiles import get_active_profile_name, get_active_hermes_home
+        name = get_active_profile_name()
+        if name and name != 'default':
+            d = get_active_hermes_home() / 'webui_state'
+            d.mkdir(parents=True, exist_ok=True)
+            return d
+    except ImportError:
+        pass
+    return _GLOBAL_WS_FILE.parent
+
+
+def _workspaces_file() -> Path:
+    """Return the workspaces.json path for the active profile."""
+    return _profile_state_dir() / 'workspaces.json'
+
+
+def _last_workspace_file() -> Path:
+    """Return the last_workspace.txt path for the active profile."""
+    return _profile_state_dir() / 'last_workspace.txt'
+
+
+def _profile_default_workspace() -> str:
+    """Read the profile's default workspace from its config.yaml.
+
+    Checks keys in priority order:
+      1. 'workspace'         — explicit webui workspace key
+      2. 'default_workspace' — alternate explicit key
+      3. 'terminal.cwd'      — hermes-agent terminal working dir (most common)
+
+    Falls back to the boot-time DEFAULT_WORKSPACE constant.
+    """
+    try:
+        from api.config import get_config
+        cfg = get_config()
+        # Explicit webui workspace keys first
+        for key in ('workspace', 'default_workspace'):
+            ws = cfg.get(key)
+            if ws:
+                p = Path(str(ws)).expanduser().resolve()
+                if p.is_dir():
+                    return str(p)
+        # Fall through to terminal.cwd — the agent's configured working directory
+        terminal_cfg = cfg.get('terminal', {})
+        if isinstance(terminal_cfg, dict):
+            cwd = terminal_cfg.get('cwd', '')
+            if cwd and str(cwd) not in ('.', ''):
+                p = Path(str(cwd)).expanduser().resolve()
+                if p.is_dir():
+                    return str(p)
+    except (ImportError, Exception):
+        pass
+    return str(_BOOT_DEFAULT_WORKSPACE)
+
+
+# ── Public API ──────────────────────────────────────────────────────────────
+
+def _clean_workspace_list(workspaces: list) -> list:
+    """Sanitize a workspace list:
+    - Remove entries whose paths no longer exist on disk.
+    - Remove entries that look like test artifacts (webui-mvp-test, test-workspace).
+    - Remove entries whose paths live inside another profile's directory
+      (e.g. ~/.hermes/profiles/X/... should not appear on a different profile).
+    - Rename any entry whose name is literally 'default' to 'Home' (avoids
+      confusion with the 'default' profile name).
+    Returns the cleaned list (may be empty).
+    """
+    hermes_profiles = (Path.home() / '.hermes' / 'profiles').resolve()
+    result = []
+    for w in workspaces:
+        path = w.get('path', '')
+        name = w.get('name', '')
+        p = Path(path).resolve() if path else Path('/')
+        # Skip test artifacts
+        if 'test-workspace' in path or 'webui-mvp-test' in path:
+            continue
+        # Skip paths that no longer exist
+        if not p.is_dir():
+            continue
+        # Skip paths inside a named profile's directory (cross-profile leak)
         try:
-            return json.loads(WORKSPACES_FILE.read_text(encoding='utf-8'))
+            p.relative_to(hermes_profiles)
+            continue  # it IS under profiles/ — remove it
+        except ValueError:
+            pass
+        # Rename confusing 'default' label to 'Home'
+        if name.lower() == 'default':
+            name = 'Home'
+        result.append({'path': str(p), 'name': name})
+    return result
+
+
+def _migrate_global_workspaces() -> list:
+    """Read the legacy global workspaces.json, clean it, and return the result.
+
+    This is the migration path for users upgrading from a pre-profile version:
+    their global file may contain cross-profile entries, test artifacts, and
+    stale paths accumulated over time.  We clean it in-place and rewrite it.
+    """
+    if not _GLOBAL_WS_FILE.exists():
+        return []
+    try:
+        raw = json.loads(_GLOBAL_WS_FILE.read_text(encoding='utf-8'))
+        cleaned = _clean_workspace_list(raw)
+        if len(cleaned) != len(raw):
+            # Rewrite the cleaned version so future reads are already clean
+            _GLOBAL_WS_FILE.write_text(
+                json.dumps(cleaned, ensure_ascii=False, indent=2), encoding='utf-8'
+            )
+        return cleaned
+    except Exception:
+        return []
+
+
+def load_workspaces() -> list:
+    ws_file = _workspaces_file()
+    if ws_file.exists():
+        try:
+            raw = json.loads(ws_file.read_text(encoding='utf-8'))
+            cleaned = _clean_workspace_list(raw)
+            if len(cleaned) != len(raw):
+                # Persist the cleaned version so stale entries don't keep reappearing
+                try:
+                    ws_file.write_text(
+                        json.dumps(cleaned, ensure_ascii=False, indent=2), encoding='utf-8'
+                    )
+                except Exception:
+                    pass
+            return cleaned or [{'path': _profile_default_workspace(), 'name': 'Home'}]
         except Exception:
             pass
-    return [{'path': str(DEFAULT_WORKSPACE), 'name': 'default'}]
+    # No profile-local file yet.
+    # For the DEFAULT profile: migrate from the legacy global file (one-time cleanup).
+    # For NAMED profiles: always start clean with just their own workspace.
+    try:
+        from api.profiles import get_active_profile_name
+        is_default = get_active_profile_name() in ('default', None)
+    except ImportError:
+        is_default = True
+    if is_default:
+        migrated = _migrate_global_workspaces()
+        if migrated:
+            return migrated
+    # Fresh start: single entry from the profile's configured workspace, labeled "Home"
+    return [{'path': _profile_default_workspace(), 'name': 'Home'}]
 
 
 def save_workspaces(workspaces: list):
-    WORKSPACES_FILE.write_text(json.dumps(workspaces, ensure_ascii=False, indent=2), encoding='utf-8')
+    ws_file = _workspaces_file()
+    ws_file.parent.mkdir(parents=True, exist_ok=True)
+    ws_file.write_text(json.dumps(workspaces, ensure_ascii=False, indent=2), encoding='utf-8')
 
 
 def get_last_workspace() -> str:
-    if LAST_WORKSPACE_FILE.exists():
+    lw_file = _last_workspace_file()
+    if lw_file.exists():
         try:
-            p = LAST_WORKSPACE_FILE.read_text(encoding='utf-8').strip()
+            p = lw_file.read_text(encoding='utf-8').strip()
             if p and Path(p).is_dir():
                 return p
         except Exception:
             pass
-    return str(DEFAULT_WORKSPACE)
+    # Fallback: try global file
+    if _GLOBAL_LW_FILE.exists():
+        try:
+            p = _GLOBAL_LW_FILE.read_text(encoding='utf-8').strip()
+            if p and Path(p).is_dir():
+                return p
+        except Exception:
+            pass
+    return _profile_default_workspace()
 
 
 def set_last_workspace(path: str):
     try:
-        LAST_WORKSPACE_FILE.write_text(str(path), encoding='utf-8')
+        lw_file = _last_workspace_file()
+        lw_file.parent.mkdir(parents=True, exist_ok=True)
+        lw_file.write_text(str(path), encoding='utf-8')
     except Exception:
         pass
 

docker-compose.yml

@@ -0,0 +1,22 @@
+version: "3.8"
+
+services:
+  hermes-webui:
+    build: .
+    ports:
+      - "127.0.0.1:8787:8787"
+    volumes:
+      # Persist session data, settings, and projects across restarts
+      - hermes-data:/data
+      # Mount hermes home for agent features and profile management
+      - ${HERMES_HOME:-${HOME}/.hermes}:/root/.hermes
+    environment:
+      - HERMES_WEBUI_HOST=0.0.0.0
+      - HERMES_WEBUI_PORT=8787
+      - HERMES_WEBUI_STATE_DIR=/data
+      # Optional: set a password for remote access
+      # - HERMES_WEBUI_PASSWORD=your-secret-password
+    restart: unless-stopped
+
+volumes:
+  hermes-data:

server.py

@@ -8,6 +8,7 @@ import traceback
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from urllib.parse import urlparse
 
+from api.auth import check_auth
 from api.config import HOST, PORT, STATE_DIR, SESSION_DIR, DEFAULT_WORKSPACE
 from api.helpers import j
 from api.routes import handle_get, handle_post
@@ -34,21 +35,25 @@ class Handler(BaseHTTPRequestHandler):
         self._req_t0 = time.time()
         try:
             parsed = urlparse(self.path)
+            if not check_auth(self, parsed): return
             result = handle_get(self, parsed)
             if result is False:
                 return j(self, {'error': 'not found'}, status=404)
         except Exception as e:
-            return j(self, {'error': str(e), 'trace': traceback.format_exc()}, status=500)
+            print(f'[webui] ERROR {self.command} {self.path}\n' + traceback.format_exc(), flush=True)
+            return j(self, {'error': 'Internal server error'}, status=500)
 
     def do_POST(self):
         self._req_t0 = time.time()
         try:
             parsed = urlparse(self.path)
+            if not check_auth(self, parsed): return
             result = handle_post(self, parsed)
             if result is False:
                 return j(self, {'error': 'not found'}, status=404)
         except Exception as e:
-            return j(self, {'error': str(e), 'trace': traceback.format_exc()}, status=500)
+            print(f'[webui] ERROR {self.command} {self.path}\n' + traceback.format_exc(), flush=True)
+            return j(self, {'error': 'Internal server error'}, status=500)
 
 
 def main():

start.sh

@@ -198,7 +198,7 @@ hdr "Starting Hermes Web UI..."
 
 LOG="/tmp/hermes-webui-${PORT}.log"
 export HERMES_WEBUI_HOST="${HERMES_WEBUI_HOST:-127.0.0.1}"
-export HERMES_WEBUI_STATE_DIR="${HERMES_WEBUI_STATE_DIR:-${HERMES_HOME}/webui-mvp}"
+export HERMES_WEBUI_STATE_DIR="${HERMES_WEBUI_STATE_DIR:-${HERMES_HOME}/webui}"
 
 nohup "${PYTHON}" "${REPO_ROOT}/server.py" \
     > "${LOG}" 2>&1 &

static/boot.js

@@ -8,8 +8,132 @@ async function cancelStream(){
   }catch(e){setStatus('Cancel failed: '+e.message);}
 }
 
-$('btnSend').onclick=send;
+// ── Mobile navigation ──────────────────────────────────────────────────────
+function toggleMobileSidebar(){
+  const sidebar=document.querySelector('.sidebar');
+  const overlay=$('mobileOverlay');
+  if(!sidebar)return;
+  const isOpen=sidebar.classList.contains('mobile-open');
+  if(isOpen){closeMobileSidebar();}
+  else{sidebar.classList.add('mobile-open');if(overlay)overlay.classList.add('visible');}
+}
+function closeMobileSidebar(){
+  const sidebar=document.querySelector('.sidebar');
+  const overlay=$('mobileOverlay');
+  if(sidebar)sidebar.classList.remove('mobile-open');
+  if(overlay)overlay.classList.remove('visible');
+}
+function toggleMobileFiles(){
+  const panel=document.querySelector('.rightpanel');
+  if(!panel)return;
+  panel.classList.toggle('mobile-open');
+}
+function mobileSwitchPanel(name){
+  // Switch the panel content view
+  switchPanel(name);
+  // For non-chat panels (tasks, skills, memory, spaces), open the sidebar
+  // so the panel is visible. For 'chat', the content is in the main area —
+  // just close the sidebar so the chat view is unobstructed.
+  if(name==='chat'){
+    closeMobileSidebar();
+  } else {
+    const sidebar=document.querySelector('.sidebar');
+    const overlay=$('mobileOverlay');
+    if(sidebar){
+      sidebar.classList.add('mobile-open');
+      if(overlay)overlay.classList.add('visible');
+    }
+  }
+  // Update bottom nav active state
+  document.querySelectorAll('.mobile-nav-btn').forEach(btn=>{
+    btn.classList.toggle('active',btn.dataset.panel===name);
+  });
+}
+
+$('btnSend').onclick=()=>{if(window._micActive)_stopMic();send();};
 $('btnAttach').onclick=()=>$('fileInput').click();
+
+// ── Voice input (Web Speech API) ─────────────────────────────────────────
+(function(){
+  const SpeechRecognition=window.SpeechRecognition||window.webkitSpeechRecognition;
+  if(!SpeechRecognition) return; // Browser unsupported — mic button stays hidden
+
+  const btn=$('btnMic');
+  const status=$('micStatus');
+  const ta=$('msg');
+  btn.style.display=''; // Show button — browser supports speech
+
+  const recognition=new SpeechRecognition();
+  recognition.continuous=false;
+  recognition.interimResults=true;
+  recognition.lang='en-US';
+
+  let _finalText='';
+  let _prefix='';
+
+  function _setRecording(on){
+    window._micActive=on;
+    btn.classList.toggle('recording',on);
+    status.style.display=on?'':'none';
+    if(!on){ _finalText=''; _prefix=''; }
+  }
+
+  recognition.onstart=()=>{ _finalText=''; };
+
+  recognition.onresult=(event)=>{
+    let interim='';
+    let final=_finalText;
+    for(let i=event.resultIndex;i<event.results.length;i++){
+      const t=event.results[i][0].transcript;
+      if(event.results[i].isFinal){ final+=t; _finalText=final; }
+      else{ interim+=t; }
+    }
+    // Append to whatever was already in the textarea before mic started
+    ta.value=_prefix+(final||interim);
+    autoResize();
+  };
+
+  recognition.onend=()=>{
+    // Commit: prefix + final transcription; trim trailing space if prefix was non-empty
+    const committed=_finalText
+      ? (_prefix&&!_prefix.endsWith(' ')&&!_prefix.endsWith('\n')
+          ? _prefix+' '+_finalText.trimStart()
+          : _prefix+_finalText)
+      : ta.value; // no speech detected — leave whatever is there
+    _setRecording(false);
+    ta.value=committed;
+    autoResize();
+  };
+
+  recognition.onerror=(event)=>{
+    _setRecording(false);
+    const msgs={
+      'not-allowed':'Microphone access denied. Check browser permissions.',
+      'no-speech':'No speech detected. Try again.',
+      'network':'Speech recognition unavailable.',
+    };
+    showToast(msgs[event.error]||'Voice input error: '+event.error);
+  };
+
+  function _stopMic(){
+    if(window._micActive){ recognition.stop(); }
+  }
+  window._stopMic=_stopMic; // expose for send-guard above
+
+  btn.onclick=()=>{
+    if(window._micActive){
+      recognition.stop();
+      // _setRecording(false) will be called by onend
+    } else {
+      _finalText='';
+      // Snapshot existing textarea content so we append rather than replace
+      _prefix=ta.value;
+      recognition.start();
+      _setRecording(true);
+    }
+  };
+})();
+window._micActive=window._micActive||false;
 $('fileInput').onchange=e=>{addFiles(Array.from(e.target.files));e.target.value='';};
 $('btnNewChat').onclick=async()=>{await newSession();await renderSessionList();$('msg').focus();};
 $('btnDownload').onclick=()=>{
@@ -43,14 +167,16 @@ $('importFileInput').onchange=async(e)=>{
   }
 };
 // btnRefreshFiles is now panel-icon-btn in header (see HTML)
-$('btnClearPreview').onclick=()=>{
-  $('previewArea').classList.remove('visible');
-  $('previewImg').src='';
-  $('previewMd').innerHTML='';
-  $('previewCode').textContent='';
-  $('previewPathText').textContent='';
-  $('fileTree').style.display='';
-};
+function clearPreview(){
+  const pa=$('previewArea');if(pa)pa.classList.remove('visible');
+  const pi=$('previewImg');if(pi){pi.onerror=null;pi.src='';}
+  const pm=$('previewMd');if(pm)pm.innerHTML='';
+  const pc=$('previewCode');if(pc)pc.textContent='';
+  const pp=$('previewPathText');if(pp)pp.textContent='';
+  const ft=$('fileTree');if(ft)ft.style.display='';
+  _previewCurrentPath='';_previewCurrentMode='';_previewDirty=false;
+}
+$('btnClearPreview').onclick=clearPreview;
 // workspacePath click handler removed -- use topbar workspace chip dropdown instead
 $('modelSelect').onchange=async()=>{
   if(!S.session)return;
@@ -59,8 +185,38 @@ $('modelSelect').onchange=async()=>{
   await api('/api/session/update',{method:'POST',body:JSON.stringify({session_id:S.session.session_id,workspace:S.session.workspace,model:selectedModel})});
   S.session.model=selectedModel;syncTopbar();
 };
-$('msg').addEventListener('input',autoResize);
-$('msg').addEventListener('keydown',e=>{if(e.key==='Enter'&&!e.shiftKey){e.preventDefault();send();}});
+$('msg').addEventListener('input',()=>{
+  autoResize();
+  updateSendBtn();
+  const text=$('msg').value;
+  if(text.startsWith('/')&&text.indexOf('\n')===-1){
+    const prefix=text.slice(1);
+    const matches=getMatchingCommands(prefix);
+    if(matches.length)showCmdDropdown(matches); else hideCmdDropdown();
+  } else {
+    hideCmdDropdown();
+  }
+});
+$('msg').addEventListener('keydown',e=>{
+  // Autocomplete navigation when dropdown is open
+  const dd=$('cmdDropdown');
+  const dropdownOpen=dd&&dd.classList.contains('open');
+  if(dropdownOpen){
+    if(e.key==='ArrowUp'){e.preventDefault();navigateCmdDropdown(-1);return;}
+    if(e.key==='ArrowDown'){e.preventDefault();navigateCmdDropdown(1);return;}
+    if(e.key==='Tab'){e.preventDefault();selectCmdDropdownItem();return;}
+    if(e.key==='Escape'){e.preventDefault();hideCmdDropdown();return;}
+    if(e.key==='Enter'&&!e.shiftKey){e.preventDefault();selectCmdDropdownItem();return;}
+  }
+  // Send key: respect user preference
+  if(e.key==='Enter'){
+    if(window._sendKey==='ctrl+enter'){
+      if(e.ctrlKey||e.metaKey){e.preventDefault();send();}
+    } else {
+      if(!e.shiftKey){e.preventDefault();send();}
+    }
+  }
+});
 // B14: Cmd/Ctrl+K creates a new chat from anywhere
 document.addEventListener('keydown',async e=>{
   if((e.metaKey||e.ctrlKey)&&e.key==='k'){
@@ -151,6 +307,13 @@ document.querySelectorAll('.suggestion').forEach(btn=>{
 })();
 
 (async()=>{
+  // Load send key preference
+  try{const s=await api('/api/settings');window._sendKey=s.send_key||'enter';window._showTokenUsage=!!s.show_token_usage;window._showCliSessions=!!s.show_cli_sessions;}catch(e){window._sendKey='enter';window._showTokenUsage=false;window._showCliSessions=false;}
+  // Fetch active profile
+  try{const p=await api('/api/profile/active');S.activeProfile=p.name||'default';}catch(e){S.activeProfile='default';}
+  // Update profile chip label immediately
+  const profileLabel=$('profileChipLabel');
+  if(profileLabel) profileLabel.textContent=S.activeProfile||'default';
   // Fetch available models from server and populate dropdown dynamically
   await populateModelDropdown();
   // Restore last-used model preference

static/commands.js

@@ -0,0 +1,170 @@
+// ── Slash commands ──────────────────────────────────────────────────────────
+// Built-in commands intercepted before send(). Each command runs locally
+// (no round-trip to the agent) and shows feedback via toast or local message.
+
+const COMMANDS=[
+  {name:'help',      desc:'List available commands',             fn:cmdHelp},
+  {name:'clear',     desc:'Clear conversation messages',         fn:cmdClear},
+  {name:'model',     desc:'Switch model (e.g. /model gpt-4o)',  fn:cmdModel,     arg:'model_name'},
+  {name:'workspace', desc:'Switch workspace by name',            fn:cmdWorkspace, arg:'name'},
+  {name:'new',       desc:'Start a new chat session',            fn:cmdNew},
+  {name:'usage',     desc:'Toggle token usage display on/off',   fn:cmdUsage},
+];
+
+function parseCommand(text){
+  if(!text.startsWith('/'))return null;
+  const parts=text.slice(1).split(/\s+/);
+  const name=parts[0].toLowerCase();
+  const args=parts.slice(1).join(' ').trim();
+  return {name,args};
+}
+
+function executeCommand(text){
+  const parsed=parseCommand(text);
+  if(!parsed)return false;
+  const cmd=COMMANDS.find(c=>c.name===parsed.name);
+  if(!cmd)return false;
+  cmd.fn(parsed.args);
+  return true;
+}
+
+function getMatchingCommands(prefix){
+  const q=prefix.toLowerCase();
+  return COMMANDS.filter(c=>c.name.startsWith(q));
+}
+
+// ── Command handlers ────────────────────────────────────────────────────────
+
+function cmdHelp(){
+  const lines=COMMANDS.map(c=>{
+    const usage=c.arg?` <${c.arg}>`:'';
+    return `  /${c.name}${usage} — ${c.desc}`;
+  });
+  const msg={role:'assistant',content:'**Available commands:**\n'+lines.join('\n')};
+  S.messages.push(msg);
+  renderMessages();
+  showToast('Type / to see commands');
+}
+
+function cmdClear(){
+  if(!S.session)return;
+  S.messages=[];S.toolCalls=[];
+  clearLiveToolCards();
+  renderMessages();
+  $('emptyState').style.display='';
+  showToast('Conversation cleared');
+}
+
+async function cmdModel(args){
+  if(!args){showToast('Usage: /model <name>');return;}
+  const sel=$('modelSelect');
+  if(!sel)return;
+  const q=args.toLowerCase();
+  // Fuzzy match: find first option whose label or value contains the query
+  let match=null;
+  for(const opt of sel.options){
+    if(opt.value.toLowerCase().includes(q)||opt.textContent.toLowerCase().includes(q)){
+      match=opt.value;break;
+    }
+  }
+  if(!match){showToast(`No model matching "${args}"`);return;}
+  sel.value=match;
+  await sel.onchange();
+  showToast(`Switched to ${match}`);
+}
+
+async function cmdWorkspace(args){
+  if(!args){showToast('Usage: /workspace <name>');return;}
+  try{
+    const data=await api('/api/workspaces');
+    const q=args.toLowerCase();
+    const ws=(data.workspaces||[]).find(w=>
+      (w.name||'').toLowerCase().includes(q)||w.path.toLowerCase().includes(q)
+    );
+    if(!ws){showToast(`No workspace matching "${args}"`);return;}
+    if(!S.session)return;
+    await api('/api/session/update',{method:'POST',body:JSON.stringify({
+      session_id:S.session.session_id,workspace:ws.path,model:S.session.model
+    })});
+    S.session.workspace=ws.path;
+    syncTopbar();await loadDir('.');
+    showToast(`Switched to workspace: ${ws.name||ws.path}`);
+  }catch(e){showToast('Workspace switch failed: '+e.message);}
+}
+
+async function cmdNew(){
+  await newSession();
+  await renderSessionList();
+  $('msg').focus();
+  showToast('New session created');
+}
+
+async function cmdUsage(){
+  const next=!window._showTokenUsage;
+  window._showTokenUsage=next;
+  try{
+    await api('/api/settings',{method:'POST',body:JSON.stringify({show_token_usage:next})});
+  }catch(e){}
+  // Update the settings checkbox if the panel is open
+  const cb=$('settingsShowTokenUsage');
+  if(cb) cb.checked=next;
+  renderMessages();
+  showToast('Token usage '+(next?'on':'off'));
+}
+
+// ── Autocomplete dropdown ───────────────────────────────────────────────────
+
+let _cmdSelectedIdx=-1;
+
+function showCmdDropdown(matches){
+  const dd=$('cmdDropdown');
+  if(!dd)return;
+  dd.innerHTML='';
+  _cmdSelectedIdx=-1;
+  for(let i=0;i<matches.length;i++){
+    const c=matches[i];
+    const el=document.createElement('div');
+    el.className='cmd-item';
+    el.dataset.idx=i;
+    const usage=c.arg?` <span class="cmd-item-arg">${esc(c.arg)}</span>`:'';
+    el.innerHTML=`<div class="cmd-item-name">/${esc(c.name)}${usage}</div><div class="cmd-item-desc">${esc(c.desc)}</div>`;
+    el.onmousedown=(e)=>{
+      e.preventDefault();
+      $('msg').value='/'+c.name+(c.arg?' ':'');
+      hideCmdDropdown();
+      $('msg').focus();
+    };
+    dd.appendChild(el);
+  }
+  dd.classList.add('open');
+}
+
+function hideCmdDropdown(){
+  const dd=$('cmdDropdown');
+  if(dd)dd.classList.remove('open');
+  _cmdSelectedIdx=-1;
+}
+
+function navigateCmdDropdown(dir){
+  const dd=$('cmdDropdown');
+  if(!dd)return;
+  const items=dd.querySelectorAll('.cmd-item');
+  if(!items.length)return;
+  items.forEach(el=>el.classList.remove('selected'));
+  _cmdSelectedIdx+=dir;
+  if(_cmdSelectedIdx<0)_cmdSelectedIdx=items.length-1;
+  if(_cmdSelectedIdx>=items.length)_cmdSelectedIdx=0;
+  items[_cmdSelectedIdx].classList.add('selected');
+}
+
+function selectCmdDropdownItem(){
+  const dd=$('cmdDropdown');
+  if(!dd)return;
+  const items=dd.querySelectorAll('.cmd-item');
+  if(_cmdSelectedIdx>=0&&_cmdSelectedIdx<items.length){
+    items[_cmdSelectedIdx].onmousedown({preventDefault:()=>{}});
+  } else if(items.length===1){
+    items[0].onmousedown({preventDefault:()=>{}});
+  }
+  hideCmdDropdown();
+}

static/index.html

@@ -13,13 +13,14 @@
 <body>
 <div class="layout">
   <aside class="sidebar">
-    <div class="sidebar-header"><div class="logo">H</div><div><h1 style="margin:0;font-size:15px;font-weight:700;letter-spacing:-.01em">Hermes</h1><div style="font-size:10px;color:var(--muted);opacity:.8;margin-top:1px">v0.17.1</div></div></div>
+    <div class="sidebar-header"><div class="logo">H</div><div><h1 style="margin:0;font-size:15px;font-weight:700;letter-spacing:-.01em">Hermes</h1><div style="font-size:10px;color:var(--muted);opacity:.8;margin-top:1px">v0.31</div></div></div>
     <div class="sidebar-nav">
       <button class="nav-tab active" data-panel="chat" data-label="Chat" onclick="switchPanel('chat')" title="Chat">&#128172;</button>
       <button class="nav-tab" data-panel="tasks" data-label="Tasks" onclick="switchPanel('tasks')" title="Tasks">&#128197;</button>
       <button class="nav-tab" data-panel="skills" data-label="Skills" onclick="switchPanel('skills')" title="Skills">&#129513;</button>
       <button class="nav-tab" data-panel="memory" data-label="Memory" onclick="switchPanel('memory')" title="Memory">&#129504;</button>
       <button class="nav-tab" data-panel="workspaces" data-label="Spaces" onclick="switchPanel('workspaces')" title="Spaces">&#128193;</button>
+      <button class="nav-tab" data-panel="profiles" data-label="Profiles" onclick="switchPanel('profiles')" title="Agent profiles"><svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M20 21v-2a4 4 0 0 0-4-4H8a4 4 0 0 0-4 4v2"/><circle cx="12" cy="7" r="4"/></svg></button>
       <button class="nav-tab" data-panel="todos" data-label="Todos" onclick="switchPanel('todos')" title="Current task list">&#9989;</button>
     </div>
     <!-- Chat panel -->
@@ -44,11 +45,16 @@
         <input id="cronFormName" placeholder="Job name (optional)" style="width:100%;background:rgba(255,255,255,.05);border:1px solid var(--border2);border-radius:6px;color:var(--text);padding:5px 8px;font-size:12px;outline:none;margin-bottom:6px">
         <input id="cronFormSchedule" placeholder="Schedule: '0 9 * * *' or 'every 1h'" style="width:100%;background:rgba(255,255,255,.05);border:1px solid var(--border2);border-radius:6px;color:var(--text);padding:5px 8px;font-size:12px;outline:none;margin-bottom:6px">
         <textarea id="cronFormPrompt" rows="3" placeholder="Prompt (must be self-contained)" style="width:100%;background:rgba(255,255,255,.05);border:1px solid var(--border2);border-radius:6px;color:var(--text);padding:5px 8px;font-size:12px;outline:none;resize:none;font-family:inherit;margin-bottom:6px"></textarea>
-        <select id="cronFormDeliver" style="width:100%;background:rgba(255,255,255,.05);border:1px solid var(--border2);border-radius:6px;color:var(--text);padding:5px 8px;font-size:12px;outline:none;margin-bottom:8px">
+        <select id="cronFormDeliver" style="width:100%;background:rgba(255,255,255,.05);border:1px solid var(--border2);border-radius:6px;color:var(--text);padding:5px 8px;font-size:12px;outline:none;margin-bottom:6px">
           <option value="local">Local (save output only)</option>
           <option value="discord">Discord</option>
           <option value="telegram">Telegram</option>
         </select>
+        <div class="skill-picker-wrap" style="margin-bottom:8px">
+          <input id="cronFormSkillSearch" placeholder="Add skills (optional)..." style="width:100%;background:rgba(255,255,255,.05);border:1px solid var(--border2);border-radius:6px;color:var(--text);padding:5px 8px;font-size:12px;outline:none" autocomplete="off">
+          <div id="cronFormSkillDropdown" class="skill-picker-dropdown" style="display:none"></div>
+          <div id="cronFormSkillTags" class="skill-picker-tags"></div>
+        </div>
         <div style="display:flex;gap:6px">
           <button class="cron-btn run" style="flex:1" onclick="submitCronCreate()">Create job</button>
           <button class="cron-btn" style="flex:1" onclick="toggleCronForm()">Cancel</button>
@@ -104,6 +110,26 @@
       <div style="padding:10px 12px 4px;font-size:11px;color:var(--muted)">Add and switch workspaces for your sessions.</div>
       <div style="flex:1;overflow-y:auto;padding:0 12px 12px" id="workspacesPanel"><div style="color:var(--muted);font-size:12px">Loading...</div></div>
     </div>
+    <!-- Profiles panel -->
+    <div class="panel-view" id="panelProfiles">
+      <div class="sidebar-section" style="padding-bottom:4px;display:flex;align-items:center;justify-content:space-between">
+        <div style="font-size:11px;color:var(--muted)">Agent profiles</div>
+        <button class="cron-btn run" style="padding:3px 8px;font-size:10px" onclick="toggleProfileForm()">+ New profile</button>
+      </div>
+      <!-- Profile create form (hidden by default) -->
+      <div id="profileCreateForm" style="display:none;padding:8px 12px;border-bottom:1px solid var(--border);flex-shrink:0">
+        <input id="profileFormName" placeholder="Profile name (lowercase, a-z 0-9 hyphens)" style="width:100%;background:rgba(255,255,255,.05);border:1px solid var(--border2);border-radius:6px;color:var(--text);padding:5px 8px;font-size:12px;outline:none;margin-bottom:6px;box-sizing:border-box">
+        <label style="display:flex;align-items:center;gap:6px;font-size:11px;color:var(--muted);margin-bottom:8px;cursor:pointer">
+          <input type="checkbox" id="profileFormClone" style="accent-color:var(--accent)"> Clone config from active profile
+        </label>
+        <div style="display:flex;gap:6px">
+          <button class="cron-btn run" style="flex:1" onclick="submitProfileCreate()">Create</button>
+          <button class="cron-btn" style="flex:1" onclick="toggleProfileForm()">Cancel</button>
+        </div>
+        <div id="profileFormError" style="font-size:11px;color:var(--accent);margin-top:6px;display:none"></div>
+      </div>
+      <div style="flex:1;overflow-y:auto;padding:0 12px 12px" id="profilesPanel"><div style="color:var(--muted);font-size:12px">Loading...</div></div>
+    </div>
     <div class="sidebar-bottom">
       <div class="field-label" style="font-size:10px;letter-spacing:.07em;margin-bottom:4px">MODEL</div>
       <select id="modelSelect">
@@ -124,13 +150,16 @@
           <option value="meta-llama/llama-4-scout">Llama 4 Scout</option>
         </optgroup>
       </select>
-      <div id="sidebarWsDisplay" style="display:flex;align-items:center;gap:7px;padding:0 0 8px;cursor:pointer;border-radius:8px;transition:background .15s" onclick="toggleWsDropdown()" title="Switch workspace">
-        <span style="font-size:14px;opacity:.7">&#128193;</span>
-        <div style="min-width:0;flex:1">
-          <div style="font-size:11px;font-weight:600;color:var(--text);overflow:hidden;text-overflow:ellipsis;white-space:nowrap" id="sidebarWsName">Workspace</div>
-          <div style="font-size:10px;color:var(--muted);overflow:hidden;text-overflow:ellipsis;white-space:nowrap;margin-top:1px" id="sidebarWsPath"></div>
+      <div style="position:relative">
+        <div id="sidebarWsDisplay" style="display:flex;align-items:center;gap:7px;padding:0 0 8px;cursor:pointer;border-radius:8px;transition:background .15s" onclick="toggleWsDropdown()" title="Switch workspace">
+          <span style="font-size:14px;opacity:.7">&#128193;</span>
+          <div style="min-width:0;flex:1">
+            <div style="font-size:11px;font-weight:600;color:var(--text);overflow:hidden;text-overflow:ellipsis;white-space:nowrap" id="sidebarWsName">Workspace</div>
+            <div style="font-size:10px;color:var(--muted);overflow:hidden;text-overflow:ellipsis;white-space:nowrap;margin-top:1px" id="sidebarWsPath"></div>
+          </div>
+          <span style="font-size:10px;color:var(--muted);flex-shrink:0">&#9662;</span>
         </div>
-        <span style="font-size:10px;color:var(--muted);flex-shrink:0">&#9662;</span>
+        <div class="ws-dropdown" id="wsDropdown"></div>
       </div>
       <div class="sidebar-actions">
         <button class="sm-btn" id="btnDownload" title="Download as Markdown">&#8595; Transcript</button>
@@ -143,15 +172,20 @@
   </aside>
   <main class="main">
     <div class="topbar">
+      <button class="mobile-hamburger" id="btnHamburger" onclick="toggleMobileSidebar()" title="Menu">
+        <svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><line x1="3" y1="6" x2="21" y2="6"/><line x1="3" y1="12" x2="21" y2="12"/><line x1="3" y1="18" x2="21" y2="18"/></svg>
+      </button>
       <div style="flex:1;min-width:0;overflow:hidden"><div class="topbar-title" id="topbarTitle">Hermes</div><div class="topbar-meta" id="topbarMeta">Start a new conversation</div></div>
       <div class="topbar-chips">
-        <div class="chip model" id="modelChip">GPT-5.4 Mini</div>
-        <div id="wsChipWrap" style="position:relative">
-          <div class="chip ws-chip" id="wsChip" onclick="toggleWsDropdown()" title="Switch workspace" style="cursor:pointer">&#128193; test-workspace &#9662;</div>
-          <div class="ws-dropdown" id="wsDropdown"></div>
+        <div id="profileChipWrap" style="position:relative">
+          <div class="chip profile-chip" id="profileChip" onclick="toggleProfileDropdown()" title="Switch profile" style="cursor:pointer"><svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round" stroke-linejoin="round" style="vertical-align:-1px;margin-right:3px"><path d="M20 21v-2a4 4 0 0 0-4-4H8a4 4 0 0 0-4 4v2"/><circle cx="12" cy="7" r="4"/></svg><span id="profileChipLabel">default</span> &#9662;</div>
+          <div class="profile-dropdown" id="profileDropdown"></div>
         </div>
+        <div class="chip model" id="modelChip">GPT-5.4 Mini</div>
+
         <button class="chip clear-btn" id="btnClearConv" onclick="clearConversation()" title="Clear all messages in this conversation" style="display:none">&#128465; Clear</button>
         <button class="chip gear-btn" id="btnSettings" onclick="toggleSettings()" title="Settings">&#9881;</button>
+        <button class="chip mobile-files-btn" id="btnMobileFiles" onclick="toggleMobileFiles()" title="Files">&#128193;</button>
       </div>
     </div>
     <div class="messages" id="messages">
@@ -206,12 +240,14 @@
       </div>
     </div>
     <div class="composer-wrap" id="composerWrap">
+      <div class="cmd-dropdown" id="cmdDropdown"></div>
       <div class="composer-box" id="composerBox">
         <div class="drop-hint" id="dropHint">
           <svg width="28" height="28" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.5"><path d="M21 15v4a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2v-4"/><polyline points="17 8 12 3 7 8"/><line x1="12" y1="3" x2="12" y2="15"/></svg>
           Drop files to upload to workspace
         </div>
         <div class="attach-tray" id="attachTray"></div>
+        <div class="mic-status" id="micStatus" style="display:none"><span class="mic-dot"></span> Listening…</div>
         <textarea id="msg" rows="1" placeholder="Message Hermes…"></textarea>
         <div class="composer-footer">
           <div class="composer-left">
@@ -219,11 +255,18 @@
             <button class="icon-btn" id="btnAttach" title="Attach files">
               <svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2"><path d="M21.44 11.05l-9.19 9.19a6 6 0 0 1-8.49-8.49l9.19-9.19a4 4 0 0 1 5.66 5.66l-9.2 9.19a2 2 0 0 1-2.83-2.83l8.49-8.48"/></svg>
             </button>
+            <button class="icon-btn mic-btn" id="btnMic" title="Voice input" style="display:none">
+              <svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2">
+                <rect x="9" y="1" width="6" height="12" rx="3"/>
+                <path d="M5 10a7 7 0 0 0 14 0"/>
+                <line x1="12" y1="19" x2="12" y2="23"/>
+                <line x1="8" y1="23" x2="16" y2="23"/>
+              </svg>
+            </button>
           </div>
           <div class="composer-right">
-            <button class="send-btn" id="btnSend">
-              <svg width="14" height="14" viewBox="0 0 24 24" fill="currentColor"><path d="M2.01 21L23 12 2.01 3 2 10l15 2-15 2z"/></svg>
-              Send
+            <button class="send-btn" id="btnSend" title="Send message" style="display:none">
+              <svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round" stroke-linejoin="round"><line x1="12" y1="19" x2="12" y2="5"/><polyline points="5 12 12 5 19 12"/></svg>
             </button>
           </div>
         </div>
@@ -236,12 +279,14 @@
     <div class="panel-header">
       <span>Workspace</span>
       <div class="panel-actions">
+        <button class="panel-icon-btn" id="btnUpDir" title="Parent directory" onclick="navigateUp()" style="display:none">&#8593;</button>
         <button class="panel-icon-btn" id="btnNewFile" title="New file" onclick="promptNewFile()">&#43;</button>
         <button class="panel-icon-btn" id="btnNewFolder" title="New folder" onclick="promptNewFolder()">&#128193;</button>
-        <button class="panel-icon-btn" id="btnRefreshPanel" title="Refresh" onclick="if(S.session)loadDir('.')">&#8635;</button>
+        <button class="panel-icon-btn" id="btnRefreshPanel" title="Refresh" onclick="if(S.session)loadDir(S.currentDir)">&#8635;</button>
         <button class="panel-icon-btn close-preview" id="btnClearPreview" title="Close preview">&#10005;</button>
       </div>
     </div>
+    <div class="breadcrumb-bar" id="breadcrumbBar" style="display:none"></div>
     <div class="file-tree" id="fileTree"></div>
     <div class="preview-area" id="previewArea">
       <div class="preview-path" id="previewPath">
@@ -272,14 +317,66 @@
         <label for="settingsWorkspace">Default Workspace</label>
         <select id="settingsWorkspace" style="width:100%;padding:8px;background:var(--code-bg);color:var(--text);border:1px solid var(--border2);border-radius:6px"></select>
       </div>
+      <div class="settings-field">
+        <label for="settingsSendKey">Send Key</label>
+        <select id="settingsSendKey" style="width:100%;padding:8px;background:var(--code-bg);color:var(--text);border:1px solid var(--border2);border-radius:6px">
+          <option value="enter">Enter (Shift+Enter for newline)</option>
+          <option value="ctrl+enter">Ctrl+Enter (Enter for newline)</option>
+        </select>
+      </div>
+      <div class="settings-field">
+        <label style="display:flex;align-items:center;gap:8px;cursor:pointer">
+          <input type="checkbox" id="settingsShowTokenUsage" style="width:15px;height:15px;accent-color:var(--accent)">
+          Show token usage after responses
+        </label>
+        <div style="font-size:11px;color:var(--muted);margin-top:4px">Displays input/output token count below each assistant reply. Also toggled with <code>/usage</code>.</div>
+      </div>
+      <div class="settings-field">
+        <label style="display:flex;align-items:center;gap:8px;cursor:pointer">
+          <input type="checkbox" id="settingsShowCliSessions" style="width:15px;height:15px;accent-color:var(--accent)">
+          Show CLI sessions in sidebar
+        </label>
+        <div style="font-size:11px;color:var(--muted);margin-top:4px">Merges sessions from the Hermes CLI (state.db) into the session list. Click a CLI session to import it and continue the conversation.</div>
+      </div>
+      <div class="settings-field" style="border-top:1px solid var(--border);padding-top:12px;margin-top:8px">
+        <label for="settingsPassword">Access Password</label>
+        <div style="font-size:11px;color:var(--muted);margin-bottom:6px">Enter a new password to set or change it. Leave blank to keep current setting.</div>
+        <input type="password" id="settingsPassword" placeholder="Enter new password…" style="width:100%;padding:8px;background:var(--code-bg);color:var(--text);border:1px solid var(--border2);border-radius:6px;font-size:13px">
+      </div>
       <button class="sm-btn" onclick="saveSettings()" style="margin-top:12px;width:100%;padding:8px;font-weight:600">Save Settings</button>
+      <button class="sm-btn" id="btnDisableAuth" onclick="disableAuth()" style="margin-top:6px;width:100%;padding:8px;font-weight:600;color:#e8a030;border-color:rgba(232,160,48,.3);display:none">Disable Auth</button>
+      <button class="sm-btn" id="btnSignOut" onclick="signOut()" style="margin-top:6px;width:100%;padding:8px;font-weight:600;color:var(--accent);border-color:rgba(233,69,96,.3);display:none">Sign Out</button>
     </div>
   </div>
 </div>
+<div class="mobile-overlay" id="mobileOverlay" onclick="closeMobileSidebar()"></div>
+<nav class="mobile-bottom-nav" id="mobileBottomNav">
+  <button class="mobile-nav-btn active" data-panel="chat" onclick="mobileSwitchPanel('chat')">
+    <svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.5"><path d="M21 15a2 2 0 0 1-2 2H7l-4 4V5a2 2 0 0 1 2-2h14a2 2 0 0 1 2 2z"/></svg>
+    <span>Chat</span>
+  </button>
+  <button class="mobile-nav-btn" data-panel="tasks" onclick="mobileSwitchPanel('tasks')">
+    <svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.5"><rect x="3" y="4" width="18" height="18" rx="2"/><line x1="16" y1="2" x2="16" y2="6"/><line x1="8" y1="2" x2="8" y2="6"/><line x1="3" y1="10" x2="21" y2="10"/></svg>
+    <span>Tasks</span>
+  </button>
+  <button class="mobile-nav-btn" data-panel="skills" onclick="mobileSwitchPanel('skills')">
+    <svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.5"><path d="M12 2L2 7l10 5 10-5-10-5z"/><path d="M2 17l10 5 10-5"/><path d="M2 12l10 5 10-5"/></svg>
+    <span>Skills</span>
+  </button>
+  <button class="mobile-nav-btn" data-panel="memory" onclick="mobileSwitchPanel('memory')">
+    <svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.5"><path d="M12 2a7 7 0 0 1 7 7c0 2.5-1.3 4.7-3.2 6H8.2C6.3 13.7 5 11.5 5 9a7 7 0 0 1 7-7z"/><line x1="9" y1="17" x2="15" y2="17"/><line x1="10" y1="20" x2="14" y2="20"/></svg>
+    <span>Memory</span>
+  </button>
+  <button class="mobile-nav-btn" data-panel="workspaces" onclick="mobileSwitchPanel('workspaces')">
+    <svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="1.5"><path d="M2 4h8l2 2h10v14H2z"/></svg>
+    <span>Spaces</span>
+  </button>
+</nav>
 <div class="toast" id="toast"></div>
 <script src="/static/ui.js"></script>
 <script src="/static/workspace.js"></script>
 <script src="/static/sessions.js"></script>
+<script src="/static/commands.js"></script>
 <script src="/static/messages.js"></script>
 <script src="/static/panels.js"></script>
 <script src="/static/boot.js"></script>

static/messages.js

@@ -1,6 +1,10 @@
 async function send(){
   const text=$('msg').value.trim();
   if(!text&&!S.pendingFiles.length)return;
+  // Slash command intercept -- local commands handled without agent round-trip
+  if(text.startsWith('/')&&!S.pendingFiles.length&&executeCommand(text)){
+    $('msg').value='';autoResize();hideCmdDropdown();return;
+  }
   // Don't send while an inline message edit is active
   if(document.querySelector('.msg-edit-area'))return;
   // If busy, queue the message instead of dropping it
@@ -142,6 +146,10 @@ async function send(){
       }
       if(S.session&&S.session.session_id===activeSid){
         S.session=d.session;S.messages=d.session.messages||[];
+        // Stamp _ts on the last assistant message if it has no timestamp
+        const lastAsst=[...S.messages].reverse().find(m=>m.role==='assistant');
+        if(lastAsst&&!lastAsst._ts&&!lastAsst.timestamp) lastAsst._ts=Date.now()/1000;
+        if(d.usage) S.lastUsage=d.usage;
         if(d.session.tool_calls&&d.session.tool_calls.length){
           S.toolCalls=d.session.tool_calls.map(tc=>({...tc,done:true}));
         } else {
@@ -158,6 +166,46 @@ async function send(){
       renderSessionList();setBusy(false);setStatus('');
     });
 
+    source.addEventListener('apperror',e=>{
+      // Application-level error sent explicitly by the server (rate limit, crash, etc.)
+      // This is distinct from the SSE network 'error' event below.
+      source.close();
+      delete INFLIGHT[activeSid];clearInflight();stopApprovalPolling();
+      if(!_approvalSessionId||_approvalSessionId===activeSid) hideApprovalCard();
+      if(S.session&&S.session.session_id===activeSid){
+        S.activeStreamId=null;const _cbe=$('btnCancel');if(_cbe)_cbe.style.display='none';
+        clearLiveToolCards();if(!assistantText)removeThinking();
+        try{
+          const d=JSON.parse(e.data);
+          const isRateLimit=d.type==='rate_limit';
+          const icon=isRateLimit?'⏱️':'⚠️';
+          const label=isRateLimit?'Rate limit reached':'Error';
+          const hint=d.hint?`\n\n*${d.hint}*`:'';
+          S.messages.push({role:'assistant',content:`**${icon} ${label}:** ${d.message}${hint}`});
+        }catch(_){
+          S.messages.push({role:'assistant',content:'**⚠️ Error:** An error occurred. Check server logs.'});
+        }
+        renderMessages();
+      }else if(typeof trackBackgroundError==='function'){
+        const _errTitle=(typeof _allSessions!=='undefined'&&_allSessions.find(s=>s.session_id===activeSid)||{}).title||null;
+        try{const d=JSON.parse(e.data);trackBackgroundError(activeSid,_errTitle,d.message||'Error');}
+        catch(_){trackBackgroundError(activeSid,_errTitle,'Error');}
+      }
+      if(!S.session||!INFLIGHT[S.session.session_id]){setBusy(false);setStatus('');}
+    });
+
+    source.addEventListener('warning',e=>{
+      // Non-fatal warning from server (e.g. fallback activated, retrying)
+      if(!S.session||S.session.session_id!==activeSid) return;
+      try{
+        const d=JSON.parse(e.data);
+        // Show as a small inline notice, not a full error
+        setStatus(`⚠️ ${d.message||'Warning'}`);
+        // If it's a fallback notice, show it briefly then clear
+        if(d.type==='fallback') setTimeout(()=>setStatus(''),4000);
+      }catch(_){}
+    });
+
     source.addEventListener('error',e=>{
       source.close();
       // Attempt one reconnect if the stream is still active server-side
@@ -233,7 +281,7 @@ function transcript(){
   return lines.join('\n');
 }
 
-function autoResize(){const el=$('msg');el.style.height='auto';el.style.height=Math.min(el.scrollHeight,200)+'px';}
+function autoResize(){const el=$('msg');el.style.height='auto';el.style.height=Math.min(el.scrollHeight,200)+'px';updateSendBtn();}
 
 
 // ── Approval polling ──

static/panels.js

@@ -14,6 +14,7 @@ async function switchPanel(name) {
   if (name === 'skills') await loadSkills();
   if (name === 'memory') await loadMemory();
   if (name === 'workspaces') await loadWorkspacesPanel();
+  if (name === 'profiles') await loadProfilesPanel();
   if (name === 'todos') loadTodos();
 }
 
@@ -78,6 +79,9 @@ async function loadCrons() {
   } catch(e) { box.innerHTML = `<div style="padding:12px;color:var(--accent);font-size:12px">Error: ${esc(e.message)}</div>`; }
 }
 
+let _cronSelectedSkills=[];
+let _cronSkillsCache=null;
+
 function toggleCronForm(){
   const form=$('cronCreateForm');
   if(!form)return;
@@ -89,10 +93,70 @@ function toggleCronForm(){
     $('cronFormPrompt').value='';
     $('cronFormDeliver').value='local';
     $('cronFormError').style.display='none';
+    _cronSelectedSkills=[];
+    _renderCronSkillTags();
+    const search=$('cronFormSkillSearch');
+    if(search)search.value='';
+    // Pre-fetch skills for the picker
+    if(!_cronSkillsCache){
+      api('/api/skills').then(d=>{_cronSkillsCache=d.skills||[];}).catch(()=>{});
+    }
     $('cronFormName').focus();
   }
 }
 
+function _renderCronSkillTags(){
+  const wrap=$('cronFormSkillTags');
+  if(!wrap)return;
+  wrap.innerHTML='';
+  for(const name of _cronSelectedSkills){
+    const tag=document.createElement('span');
+    tag.className='skill-tag';
+    tag.dataset.skill=name;
+    const rm=document.createElement('span');
+    rm.className='remove-tag';rm.textContent='×';
+    rm.onclick=()=>{_cronSelectedSkills=_cronSelectedSkills.filter(s=>s!==name);tag.remove();};
+    tag.appendChild(document.createTextNode(name));
+    tag.appendChild(rm);
+    wrap.appendChild(tag);
+  }
+}
+
+// Skill search input handler
+(function(){
+  const setup=()=>{
+    const search=$('cronFormSkillSearch');
+    const dropdown=$('cronFormSkillDropdown');
+    if(!search||!dropdown)return;
+    search.oninput=()=>{
+      const q=search.value.trim().toLowerCase();
+      if(!q||!_cronSkillsCache){dropdown.style.display='none';return;}
+      const matches=_cronSkillsCache.filter(s=>
+        !_cronSelectedSkills.includes(s.name)&&
+        (s.name.toLowerCase().includes(q)||(s.category||'').toLowerCase().includes(q))
+      ).slice(0,8);
+      if(!matches.length){dropdown.style.display='none';return;}
+      dropdown.innerHTML='';
+      for(const s of matches){
+        const opt=document.createElement('div');
+        opt.className='skill-opt';
+        opt.textContent=s.name+(s.category?' ('+s.category+')':'');
+        opt.onclick=()=>{
+          _cronSelectedSkills.push(s.name);
+          _renderCronSkillTags();
+          search.value='';
+          dropdown.style.display='none';
+        };
+        dropdown.appendChild(opt);
+      }
+      dropdown.style.display='';
+    };
+    search.onblur=()=>setTimeout(()=>{dropdown.style.display='none';},150);
+  };
+  if(document.readyState==='loading')document.addEventListener('DOMContentLoaded',setup);
+  else setTimeout(setup,0);
+})();
+
 async function submitCronCreate(){
   const name=$('cronFormName').value.trim();
   const schedule=$('cronFormSchedule').value.trim();
@@ -103,7 +167,10 @@ async function submitCronCreate(){
   if(!schedule){errEl.textContent='Schedule is required (e.g. "0 9 * * *" or "every 1h")';errEl.style.display='';return;}
   if(!prompt){errEl.textContent='Prompt is required';errEl.style.display='';return;}
   try{
-    await api('/api/crons/create',{method:'POST',body:JSON.stringify({name:name||undefined,schedule,prompt,deliver})});
+    const body={schedule,prompt,deliver};
+    if(name)body.name=name;
+    if(_cronSelectedSkills.length)body.skills=_cronSelectedSkills;
+    await api('/api/crons/create',{method:'POST',body:JSON.stringify(body)});
     toggleCronForm();
     showToast('Job created ✓');
     await loadCrons();
@@ -343,12 +410,49 @@ async function openSkill(name, el) {
     $('previewBadge').textContent = 'skill';
     $('previewBadge').className = 'preview-badge md';
     showPreview('md');
-    $('previewMd').innerHTML = renderMd(data.content || '(no content)');
+    let html = renderMd(data.content || '(no content)');
+    // Render linked files section if present
+    const lf = data.linked_files || {};
+    const categories = Object.entries(lf).filter(([,files]) => files && files.length > 0);
+    if (categories.length) {
+      html += '<div class="skill-linked-files"><div style="font-size:11px;font-weight:600;color:var(--muted);text-transform:uppercase;letter-spacing:.05em;margin-bottom:8px">Linked Files</div>';
+      for (const [cat, files] of categories) {
+        html += `<div class="skill-linked-section"><h4>${esc(cat)}</h4>`;
+        for (const f of files) {
+          html += `<a class="skill-linked-file" href="#" data-skill-name="${esc(name)}" data-skill-file="${esc(f)}">${esc(f)}</a>`;
+        }
+        html += '</div>';
+      }
+      html += '</div>';
+    }
+    $('previewMd').innerHTML = html;
+    // Wire linked-file clicks via data attributes (avoids inline JS XSS with apostrophes)
+    $('previewMd').querySelectorAll('.skill-linked-file').forEach(a=>{
+      a.addEventListener('click',e=>{e.preventDefault();openSkillFile(a.dataset.skillName,a.dataset.skillFile);});
+    });
     $('previewArea').classList.add('visible');
     $('fileTree').style.display = 'none';
   } catch(e) { setStatus('Could not load skill: ' + e.message); }
 }
 
+async function openSkillFile(skillName, filePath) {
+  try {
+    const data = await api(`/api/skills/content?name=${encodeURIComponent(skillName)}&file=${encodeURIComponent(filePath)}`);
+    $('previewPathText').textContent = skillName + ' / ' + filePath;
+    $('previewBadge').textContent = filePath.split('.').pop() || 'file';
+    $('previewBadge').className = 'preview-badge code';
+    const ext = filePath.split('.').pop() || '';
+    if (['md','markdown'].includes(ext)) {
+      showPreview('md');
+      $('previewMd').innerHTML = renderMd(data.content || '');
+    } else {
+      showPreview('code');
+      $('previewCode').textContent = data.content || '';
+      requestAnimationFrame(() => highlightCode());
+    }
+  } catch(e) { setStatus('Could not load file: ' + e.message); }
+}
+
 // ── Skill create/edit form ──
 let _editingSkillName = null;
 
@@ -476,6 +580,7 @@ function toggleWsDropdown(){
   const open=dd.classList.contains('open');
   if(open){closeWsDropdown();}
   else{
+    closeProfileDropdown(); // close profile dropdown if open
     loadWorkspaceList().then(data=>{
       renderWorkspaceDropdown(data.workspaces, S.session?S.session.workspace:'');
       dd.classList.add('open');
@@ -488,7 +593,7 @@ function closeWsDropdown(){
   if(dd)dd.classList.remove('open');
 }
 document.addEventListener('click',e=>{
-  if(!e.target.closest('#wsChipWrap'))closeWsDropdown();
+  if(!e.target.closest('#sidebarWsDisplay') && !e.target.closest('#wsDropdown'))closeWsDropdown();
 });
 
 async function loadWorkspacesPanel(){
@@ -561,6 +666,210 @@ async function switchToWorkspace(path,name){
   }catch(e){setStatus('Switch failed: '+e.message);}
 }
 
+// ── Profile panel + dropdown ──
+let _profilesCache = null;
+
+async function loadProfilesPanel() {
+  const panel = $('profilesPanel');
+  if (!panel) return;
+  try {
+    const data = await api('/api/profiles');
+    _profilesCache = data;
+    panel.innerHTML = '';
+    if (!data.profiles || !data.profiles.length) {
+      panel.innerHTML = '<div style="padding:16px;color:var(--muted);font-size:12px">No profiles found.</div>';
+      return;
+    }
+    for (const p of data.profiles) {
+      const card = document.createElement('div');
+      card.className = 'profile-card';
+      const meta = [];
+      if (p.model) meta.push(p.model.split('/').pop());
+      if (p.provider) meta.push(p.provider);
+      if (p.skill_count) meta.push(p.skill_count + ' skill' + (p.skill_count !== 1 ? 's' : ''));
+      if (p.has_env) meta.push('API keys configured');
+      const gwDot = p.gateway_running
+        ? '<span class="profile-opt-badge running" title="Gateway running"></span>'
+        : '<span class="profile-opt-badge stopped" title="Gateway stopped"></span>';
+      const isActive = p.name === data.active;
+      const activeBadge = isActive ? '<span style="color:var(--link);font-size:10px;font-weight:600;margin-left:6px">ACTIVE</span>' : '';
+      card.innerHTML = `
+        <div class="profile-card-header">
+          <div style="min-width:0;flex:1">
+            <div class="profile-card-name${isActive ? ' is-active' : ''}">${gwDot}${esc(p.name)}${p.is_default ? ' <span style="opacity:.5">(default)</span>' : ''}${activeBadge}</div>
+            ${meta.length ? `<div class="profile-card-meta">${esc(meta.join(' \u00b7 '))}</div>` : '<div class="profile-card-meta">No configuration</div>'}
+          </div>
+          <div class="profile-card-actions">
+            ${!isActive ? `<button class="ws-action-btn" onclick="switchToProfile('${esc(p.name)}')" title="Switch to this profile">Use</button>` : ''}
+            ${!p.is_default ? `<button class="ws-action-btn danger" onclick="deleteProfile('${esc(p.name)}')" title="Delete this profile">&#10005;</button>` : ''}
+          </div>
+        </div>`;
+      panel.appendChild(card);
+    }
+  } catch (e) {
+    panel.innerHTML = `<div style="color:var(--accent);font-size:12px;padding:12px">Error: ${esc(e.message)}</div>`;
+  }
+}
+
+function renderProfileDropdown(data) {
+  const dd = $('profileDropdown');
+  if (!dd) return;
+  dd.innerHTML = '';
+  const profiles = data.profiles || [];
+  const active = data.active || 'default';
+  for (const p of profiles) {
+    const opt = document.createElement('div');
+    opt.className = 'profile-opt' + (p.name === active ? ' active' : '');
+    const meta = [];
+    if (p.model) meta.push(p.model.split('/').pop());
+    if (p.skill_count) meta.push(p.skill_count + ' skills');
+    const gwDot = `<span class="profile-opt-badge ${p.gateway_running ? 'running' : 'stopped'}"></span>`;
+    const checkmark = p.name === active ? ' <svg width="12" height="12" viewBox="0 0 24 24" fill="none" stroke="var(--link)" stroke-width="3" style="vertical-align:-1px"><polyline points="20 6 9 17 4 12"/></svg>' : '';
+    opt.innerHTML = `<div class="profile-opt-name">${gwDot}${esc(p.name)}${p.is_default ? ' <span style="opacity:.5;font-weight:400">(default)</span>' : ''}${checkmark}</div>` +
+      (meta.length ? `<div class="profile-opt-meta">${esc(meta.join(' \u00b7 '))}</div>` : '');
+    opt.onclick = async () => {
+      closeProfileDropdown();
+      if (p.name === active) return;
+      await switchToProfile(p.name);
+    };
+    dd.appendChild(opt);
+  }
+  // Divider + Manage link
+  const div = document.createElement('div'); div.className = 'ws-divider'; dd.appendChild(div);
+  const mgmt = document.createElement('div'); mgmt.className = 'profile-opt ws-manage';
+  mgmt.innerHTML = '&#9881; Manage profiles';
+  mgmt.onclick = () => { closeProfileDropdown(); switchPanel('profiles'); };
+  dd.appendChild(mgmt);
+}
+
+function toggleProfileDropdown() {
+  const dd = $('profileDropdown');
+  if (!dd) return;
+  if (dd.classList.contains('open')) { closeProfileDropdown(); return; }
+  closeWsDropdown(); // close workspace dropdown if open
+  api('/api/profiles').then(data => {
+    renderProfileDropdown(data);
+    dd.classList.add('open');
+  }).catch(e => { showToast('Failed to load profiles'); });
+}
+
+function closeProfileDropdown() {
+  const dd = $('profileDropdown');
+  if (dd) dd.classList.remove('open');
+}
+document.addEventListener('click', e => {
+  if (!e.target.closest('#profileChipWrap')) closeProfileDropdown();
+});
+
+async function switchToProfile(name) {
+  if (S.busy) { showToast('Cannot switch profiles while agent is running'); return; }
+
+  // Determine whether the current session has any messages.
+  // A session with messages is "in progress" and belongs to the current profile —
+  // we must not retag it.  We'll start a fresh session for the new profile instead.
+  const sessionInProgress = S.session && S.messages && S.messages.length > 0;
+
+  try {
+    const data = await api('/api/profile/switch', { method: 'POST', body: JSON.stringify({ name }) });
+    S.activeProfile = data.active || name;
+
+    // ── Model ──────────────────────────────────────────────────────────────
+    localStorage.removeItem('hermes-webui-model');
+    _skillsData = null;
+    await populateModelDropdown();
+    if (data.default_model) {
+      const sel = $('modelSelect');
+      const resolved = _applyModelToDropdown(data.default_model, sel);
+      const modelToUse = resolved || data.default_model;
+      S._pendingProfileModel = modelToUse;
+      // Only patch the in-memory session model if we're NOT about to replace the session
+      if (S.session && !sessionInProgress) {
+        S.session.model = modelToUse;
+      }
+    }
+
+    // ── Workspace ──────────────────────────────────────────────────────────
+    _workspaceList = null;
+    await loadWorkspaceList();
+    if (data.default_workspace) {
+      // Always store the profile default for new sessions
+      S._profileDefaultWorkspace = data.default_workspace;
+
+      if (S.session && !sessionInProgress) {
+        // Empty session (no messages yet) — safe to update it in place
+        try {
+          await api('/api/session/update', { method: 'POST', body: JSON.stringify({
+            session_id: S.session.session_id,
+            workspace: data.default_workspace,
+            model: S.session.model,
+          })});
+          S.session.workspace = data.default_workspace;
+        } catch (_) {}
+      }
+    }
+
+    // ── Session ────────────────────────────────────────────────────────────
+    _showAllProfiles = false;
+
+    if (sessionInProgress) {
+      // The current session has messages and belongs to the previous profile.
+      // Start a new session for the new profile so nothing gets cross-tagged.
+      await newSession(false);
+      await renderSessionList();
+      showToast('Switched to profile: ' + name + ' — new conversation started');
+    } else {
+      // No messages yet — just refresh the list and topbar in place
+      await renderSessionList();
+      syncTopbar();
+      showToast('Switched to profile: ' + name);
+    }
+
+    // ── Sidebar panels ─────────────────────────────────────────────────────
+    if (_currentPanel === 'skills') await loadSkills();
+    if (_currentPanel === 'memory') await loadMemory();
+    if (_currentPanel === 'tasks') await loadCrons();
+    if (_currentPanel === 'profiles') await loadProfilesPanel();
+    if (_currentPanel === 'workspaces') await loadWorkspacesPanel();
+
+  } catch (e) { showToast('Switch failed: ' + e.message); }
+}
+
+function toggleProfileForm() {
+  const form = $('profileCreateForm');
+  if (!form) return;
+  form.style.display = form.style.display === 'none' ? '' : 'none';
+  if (form.style.display !== 'none') {
+    $('profileFormName').value = '';
+    $('profileFormClone').checked = false;
+    const errEl = $('profileFormError');
+    if (errEl) errEl.style.display = 'none';
+    $('profileFormName').focus();
+  }
+}
+
+async function submitProfileCreate() {
+  const name = ($('profileFormName').value || '').trim().toLowerCase();
+  const cloneConfig = $('profileFormClone').checked;
+  const errEl = $('profileFormError');
+  if (!name) { errEl.textContent = 'Name is required'; errEl.style.display = ''; return; }
+  if (!/^[a-z0-9][a-z0-9_-]{0,63}$/.test(name)) { errEl.textContent = 'Lowercase letters, numbers, hyphens, underscores only'; errEl.style.display = ''; return; }
+  try {
+    await api('/api/profile/create', { method: 'POST', body: JSON.stringify({ name, clone_config: cloneConfig }) });
+    toggleProfileForm();
+    await loadProfilesPanel();
+    showToast('Profile created: ' + name);
+  } catch (e) { errEl.textContent = e.message || 'Create failed'; errEl.style.display = ''; }
+}
+
+async function deleteProfile(name) {
+  if (!confirm(`Delete profile "${name}"? This removes all config, skills, memory, and sessions for this profile.`)) return;
+  try {
+    await api('/api/profile/delete', { method: 'POST', body: JSON.stringify({ name }) });
+    await loadProfilesPanel();
+    showToast('Profile deleted: ' + name);
+  } catch (e) { showToast('Delete failed: ' + e.message); }
+}
+
 // ── Memory panel ──
 async function loadMemory(force) {
   const panel = $('memoryPanel');
@@ -646,6 +955,25 @@ async function loadSettingsPanel(){
       }catch(e){}
       wsSel.value=settings.default_workspace||'';
     }
+    // Send key preference
+    const sendKeySel=$('settingsSendKey');
+    if(sendKeySel) sendKeySel.value=settings.send_key||'enter';
+    const showUsageCb=$('settingsShowTokenUsage');
+    if(showUsageCb) showUsageCb.checked=!!settings.show_token_usage;
+    const showCliCb=$('settingsShowCliSessions');
+    if(showCliCb) showCliCb.checked=!!settings.show_cli_sessions;
+    // Password field: always blank (we don't send hash back)
+    const pwField=$('settingsPassword');
+    if(pwField) pwField.value='';
+    // Show auth buttons only when auth is active
+    try{
+      const authStatus=await api('/api/auth/status');
+      const active=authStatus.auth_enabled;
+      const signOutBtn=$('btnSignOut');
+      if(signOutBtn) signOutBtn.style.display=active?'':'none';
+      const disableBtn=$('btnDisableAuth');
+      if(disableBtn) disableBtn.style.display=active?'':'none';
+    }catch(e){}
   }catch(e){
     showToast('Failed to load settings: '+e.message);
   }
@@ -654,11 +982,34 @@ async function loadSettingsPanel(){
 async function saveSettings(){
   const model=($('settingsModel')||{}).value;
   const workspace=($('settingsWorkspace')||{}).value;
+  const sendKey=($('settingsSendKey')||{}).value;
+  const showTokenUsage=!!($('settingsShowTokenUsage')||{}).checked;
+  const showCliSessions=!!($('settingsShowCliSessions')||{}).checked;
+  const pw=($('settingsPassword')||{}).value;
   const body={};
   if(model) body.default_model=model;
   if(workspace) body.default_workspace=workspace;
+  if(sendKey) body.send_key=sendKey;
+  body.show_token_usage=showTokenUsage;
+  body.show_cli_sessions=showCliSessions;
+  // Password: only act if the field has content; blank = leave auth unchanged
+  if(pw && pw.trim()){
+    try{
+      await api('/api/settings',{method:'POST',body:JSON.stringify({...body,_set_password:pw.trim()})});
+      window._sendKey=sendKey||'enter';
+      window._showTokenUsage=showTokenUsage;
+      showToast('Settings saved (password set — login now required)');
+      toggleSettings();
+      return;
+    }catch(e){showToast('Save failed: '+e.message);return;}
+  }
   try{
     await api('/api/settings',{method:'POST',body:JSON.stringify(body)});
+    window._sendKey=sendKey||'enter';
+    window._showTokenUsage=showTokenUsage;
+    window._showCliSessions=showCliSessions;
+    renderMessages();
+    if(typeof renderSessionList==='function') renderSessionList();
     showToast('Settings saved');
     toggleSettings();
   }catch(e){
@@ -666,6 +1017,30 @@ async function saveSettings(){
   }
 }
 
+async function signOut(){
+  try{
+    await api('/api/auth/logout',{method:'POST',body:'{}'});
+    window.location.href='/login';
+  }catch(e){
+    showToast('Sign out failed: '+e.message);
+  }
+}
+
+async function disableAuth(){
+  if(!confirm('Disable password protection? Anyone will be able to access this instance.')) return;
+  try{
+    await api('/api/settings',{method:'POST',body:JSON.stringify({_clear_password:true})});
+    showToast('Auth disabled — password protection removed');
+    // Hide both auth buttons since auth is now off
+    const disableBtn=$('btnDisableAuth');
+    if(disableBtn) disableBtn.style.display='none';
+    const signOutBtn=$('btnSignOut');
+    if(signOutBtn) signOutBtn.style.display='none';
+  }catch(e){
+    showToast('Failed to disable auth: '+e.message);
+  }
+}
+
 // Close settings on overlay click (not panel click)
 document.addEventListener('click',e=>{
   const overlay=$('settingsOverlay');

static/sessions.js

@@ -13,7 +13,10 @@ async function newSession(flash){
   MSG_QUEUE.length=0;updateQueueBadge();
   S.toolCalls=[];
   clearLiveToolCards();
-  const inheritWs=S.session?S.session.workspace:null;
+  // Use profile default workspace for new sessions after a profile switch (one-shot),
+  // otherwise inherit from the current session (or let server pick the default)
+  const inheritWs=S._profileDefaultWorkspace||(S.session?S.session.workspace:null);
+  S._profileDefaultWorkspace=null; // consume — only applies to the first new session after switch
   const data=await api('/api/session/new',{method:'POST',body:JSON.stringify({model:$('modelSelect').value,workspace:inheritWs})});
   S.session=data.session;S.messages=data.session.messages||[];
   if(flash)S.session._flash=true;
@@ -69,6 +72,7 @@ let _renamingSid = null;  // session_id currently being renamed (blocks list re-
 let _showArchived = false;  // toggle to show archived sessions
 let _allProjects = [];  // cached project list
 let _activeProject = null;  // project_id filter (null = show all)
+let _showAllProfiles = false;  // false = filter to active profile only
 
 async function renderSessionList(){
   try{
@@ -111,8 +115,12 @@ function renderSessionListFromCache(){
   // Merge content matches (deduped): content matches appended after title matches
   const titleIds=new Set(titleMatches.map(s=>s.session_id));
   const allMatched=q?[...titleMatches,..._contentSearchResults.filter(s=>!titleIds.has(s.session_id))]:titleMatches;
+  // Filter by active profile (unless "All profiles" is toggled on)
+  // Server backfills profile='default' for legacy sessions, so every session has a profile.
+  // Show only sessions tagged to the active profile; 'All profiles' toggle overrides.
+  const profileFiltered=_showAllProfiles?allMatched:allMatched.filter(s=>s.is_cli_session||s.profile===S.activeProfile);
   // Filter by active project
-  const projectFiltered=_activeProject?allMatched.filter(s=>s.project_id===_activeProject):allMatched;
+  const projectFiltered=_activeProject?profileFiltered.filter(s=>s.project_id===_activeProject):profileFiltered;
   // Filter archived unless toggle is on
   const sessions=_showArchived?projectFiltered:projectFiltered.filter(s=>!s.archived);
   const archivedCount=projectFiltered.filter(s=>s.archived).length;
@@ -154,6 +162,21 @@ function renderSessionListFromCache(){
     bar.appendChild(addBtn);
     list.appendChild(bar);
   }
+  // Profile filter toggle (show sessions from other profiles)
+  const otherProfileCount=allMatched.filter(s=>s.profile&&s.profile!==S.activeProfile).length;
+  if(otherProfileCount>0&&!_showAllProfiles){
+    const pfToggle=document.createElement('div');
+    pfToggle.style.cssText='font-size:10px;padding:4px 10px;color:var(--muted);cursor:pointer;text-align:center;opacity:.7;';
+    pfToggle.textContent='Show '+otherProfileCount+' from other profiles';
+    pfToggle.onclick=()=>{_showAllProfiles=true;renderSessionListFromCache();};
+    list.appendChild(pfToggle);
+  } else if(_showAllProfiles&&otherProfileCount>0){
+    const pfToggle=document.createElement('div');
+    pfToggle.style.cssText='font-size:10px;padding:4px 10px;color:var(--muted);cursor:pointer;text-align:center;opacity:.7;';
+    pfToggle.textContent='Show active profile only';
+    pfToggle.onclick=()=>{_showAllProfiles=false;renderSessionListFromCache();};
+    list.appendChild(pfToggle);
+  }
   // Show/hide archived toggle if there are archived sessions
   if(archivedCount>0){
     const toggle=document.createElement('div');
@@ -197,7 +220,7 @@ function renderSessionListFromCache(){
     }
     const el=document.createElement('div');
     const isActive=S.session&&s.session_id===S.session.session_id;
-    el.className='session-item'+(isActive?' active':'')+(isActive&&S.session&&S.session._flash?' new-flash':'')+(s.archived?' archived':'');
+    el.className='session-item'+(isActive?' active':'')+(isActive&&S.session&&S.session._flash?' new-flash':'')+(s.archived?' archived':'')+(s.is_cli_session?' cli-session':'');
     if(isActive&&S.session&&S.session._flash)delete S.session._flash;
     const rawTitle=s.title||'Untitled';
     const tags=(rawTitle.match(/#[\w-]+/g)||[]);
@@ -260,11 +283,11 @@ function renderSessionListFromCache(){
       pinInd.innerHTML=ICONS.pin;
       el.appendChild(pinInd);
     }
-    // Project indicator: colored left border
+    // Project indicator: colored left border (active item keeps its own gold color)
     if(s.project_id){
       const proj=_allProjects.find(p=>p.project_id===s.project_id);
       if(proj){
-        el.style.borderLeftColor=proj.color||'var(--blue)';
+        if(!isActive) el.style.borderLeftColor=proj.color||'var(--blue)';
         const dot=document.createElement('span');
         dot.className='session-project-dot';
         dot.style.background=proj.color||'var(--blue)';
@@ -345,7 +368,14 @@ function renderSessionListFromCache(){
       _clickTimer=setTimeout(async()=>{
         _clickTimer=null;
         if(_renamingSid) return;
+        // For CLI sessions, import into WebUI store first (idempotent)
+        if(s.is_cli_session){
+          try{
+            await api('/api/session/import_cli',{method:'POST',body:JSON.stringify({session_id:s.session_id})});
+          }catch(e){ /* import failed -- fall through to read-only view */ }
+        }
         await loadSession(s.session_id);renderSessionListFromCache();
+        if(typeof closeMobileSidebar==='function')closeMobileSidebar();
       }, 220);
     };
     el.ondblclick=async(e)=>{

static/style.css

@@ -6,7 +6,7 @@
   }
   body{background:var(--bg);color:var(--text);height:100vh;height:100dvh;overflow:hidden;display:flex;}
   .layout{display:flex;width:100%;height:100vh;height:100dvh;}
-  .sidebar{width:300px;background:var(--sidebar);border-right:1px solid var(--border);display:flex;flex-direction:column;overflow:hidden;flex-shrink:0;}
+  .sidebar{width:300px;background:var(--sidebar);border-right:1px solid var(--border);display:flex;flex-direction:column;overflow:visible;flex-shrink:0;}
   .sidebar-header{padding:16px 18px 14px;border-bottom:1px solid var(--border);display:flex;align-items:center;gap:10px;}
   .logo{width:32px;height:32px;border-radius:9px;background:linear-gradient(145deg,#e8a030,var(--accent));display:flex;align-items:center;justify-content:center;font-weight:800;font-size:14px;color:#fff;flex-shrink:0;box-shadow:0 2px 8px rgba(233,69,96,.3);}
   .sidebar-header h1{font-size:15px;font-weight:600;}
@@ -20,14 +20,14 @@
   .session-search input::placeholder{color:var(--muted);opacity:.7;}
   /* Inline session title edit */
   .session-title-input{flex:1;background:rgba(20,32,60,.9);border:1px solid rgba(124,185,255,.6);border-radius:6px;color:var(--text);padding:3px 8px;font-size:13px;outline:none;min-width:0;box-shadow:0 0 0 2px rgba(124,185,255,.15);font-family:inherit;}
-  .session-item{padding:8px 10px 8px 8px;border-radius:8px;cursor:pointer;font-size:13px;color:var(--muted);white-space:nowrap;overflow:hidden;text-overflow:ellipsis;transition:background .15s,color .15s,border-color .15s;display:flex;align-items:center;gap:6px;min-width:0;border-left:2px solid transparent;position:relative;}
+  .session-item{padding:8px 10px 8px 8px;border-radius:0 8px 8px 0;cursor:pointer;font-size:13px;color:var(--muted);white-space:nowrap;overflow:hidden;text-overflow:ellipsis;transition:background .15s,color .15s,border-color .15s;display:flex;align-items:center;gap:6px;min-width:0;border-left:2px solid transparent;position:relative;}
   .session-item:hover{background:rgba(255,255,255,0.06);color:var(--text);}
-  .session-item.active{background:rgba(124,185,255,0.1);color:var(--blue);border-left:2px solid var(--blue);padding-left:8px;}
+  .session-item.active{background:rgba(232,160,48,0.12);color:#e8a030;border-left:2px solid #e8a030;padding-left:8px;}
   .session-title{flex:1;overflow:hidden;text-overflow:ellipsis;white-space:nowrap;}
   /* ── Session action button overlay ── */
   .session-actions{position:absolute;right:0;top:0;bottom:0;display:flex;align-items:center;gap:2px;padding:0 6px 0 16px;background:linear-gradient(to right,transparent,var(--sidebar) 12px);opacity:0;pointer-events:none;transition:opacity .15s ease;border-radius:0 8px 8px 0;}
   .session-item:hover .session-actions{opacity:1;pointer-events:auto;}
-  .session-item.active .session-actions{background:linear-gradient(to right,transparent,rgba(16,33,62,.95) 12px);}
+  .session-item.active .session-actions{background:linear-gradient(to right,transparent,rgba(30,22,8,.95) 12px);}
   .session-actions button{background:none;border:none;color:var(--muted);cursor:pointer;padding:2px 3px;line-height:1;transition:color .12s;display:flex;align-items:center;}
   .session-actions button:hover{color:var(--text);}
   .session-actions .act-trash:hover{color:var(--accent);}
@@ -113,7 +113,7 @@
   .memory-content{font-size:12px;line-height:1.7;color:var(--text);}
   .memory-content p{margin-bottom:6px;}
   .memory-empty{color:var(--muted);font-size:12px;font-style:italic;}
-  .sidebar-bottom{border-top:1px solid var(--border);padding:12px 14px;flex-shrink:0;}
+  .sidebar-bottom{border-top:1px solid var(--border);padding:12px 14px;flex-shrink:0;position:relative;z-index:10;overflow:visible;}
   .field-label{font-size:10px;font-weight:700;text-transform:uppercase;letter-spacing:.08em;color:var(--muted);margin-bottom:5px;opacity:.8;}
   select{width:100%;background:rgba(255,255,255,0.04);border:1px solid rgba(255,255,255,.1);border-radius:8px;color:var(--text);padding:7px 28px 7px 10px;font-size:12px;outline:none;appearance:none;margin-bottom:6px;cursor:pointer;background-image:url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' width='10' height='6' viewBox='0 0 10 6'%3E%3Cpath d='M1 1l4 4 4-4' stroke='%238888aa' stroke-width='1.5' fill='none' stroke-linecap='round'/%3E%3C/svg%3E");background-repeat:no-repeat;background-position:right 10px center;}
   select:focus{border-color:rgba(124,185,255,.4);box-shadow:0 0 0 2px rgba(124,185,255,.08);}
@@ -123,13 +123,13 @@
   .sm-btn{flex:1;padding:7px 0;border-radius:8px;font-size:11px;font-weight:500;background:rgba(255,255,255,0.04);border:1px solid rgba(255,255,255,.08);color:var(--muted);cursor:pointer;transition:all .15s;text-align:center;letter-spacing:.02em;}
   .sm-btn:hover{background:rgba(255,255,255,0.09);color:var(--text);border-color:rgba(255,255,255,.15);}
   .main{flex:1;display:flex;flex-direction:column;overflow:hidden;min-width:0;background:rgba(26,26,46,0.5);}
-  .topbar{padding:12px 20px;border-bottom:1px solid var(--border);background:rgba(22,33,62,.98);backdrop-filter:blur(12px);display:flex;align-items:center;justify-content:space-between;flex-shrink:0;}
+  .topbar{padding:12px 20px;border-bottom:1px solid var(--border);background:rgba(22,33,62,.98);backdrop-filter:blur(12px);display:flex;align-items:center;justify-content:space-between;flex-shrink:0;position:relative;z-index:10;}
   .topbar-title{font-size:15px;font-weight:600;letter-spacing:-.01em;white-space:nowrap;overflow:hidden;text-overflow:ellipsis;}
   .topbar-meta{font-size:11px;color:var(--muted);margin-top:3px;opacity:.75;white-space:nowrap;overflow:hidden;text-overflow:ellipsis;}
   .topbar-chips{display:flex;gap:6px;align-items:center;flex-shrink:0;}
   .chip{font-size:11px;padding:4px 10px;border-radius:999px;background:rgba(255,255,255,0.05);border:1px solid rgba(255,255,255,.1);color:var(--muted);font-weight:500;}
   .chip.model{color:var(--blue);border-color:rgba(124,185,255,0.35);background:rgba(124,185,255,0.1);}
-  .messages{flex:1;overflow-y:auto;display:flex;flex-direction:column;min-height:0;}
+  .messages{flex:1;overflow-y:auto;display:flex;flex-direction:column;min-height:0;position:relative;z-index:0;}
   .messages-inner{max-width:800px;margin:0 auto;width:100%;padding:20px 24px 32px;display:flex;flex-direction:column;}
   .msg-row{padding:10px 0;}
   .msg-row+.msg-row{border-top:none;}
@@ -187,11 +187,18 @@
   .icon-btn{width:34px;height:34px;border-radius:8px;background:none;border:none;color:var(--muted);cursor:pointer;display:flex;align-items:center;justify-content:center;font-size:16px;transition:all .15s;}
   .icon-btn{opacity:.75;}
   .icon-btn:hover{background:rgba(255,255,255,.08);color:var(--text);opacity:1;}
+  .mic-btn{transition:color .15s,background .15s;}
+  .mic-btn.recording{color:#e94560;background:rgba(233,69,96,.12);animation:mic-pulse 1.2s ease-in-out infinite;}
+  @keyframes mic-pulse{0%,100%{box-shadow:0 0 0 0 rgba(233,69,96,.3);}50%{box-shadow:0 0 0 6px rgba(233,69,96,0);}}
+  .mic-status{font-size:11px;color:#e94560;padding:4px 12px;display:flex;align-items:center;gap:6px;}
+  .mic-dot{width:6px;height:6px;border-radius:50%;background:#e94560;animation:mic-pulse 1.2s ease-in-out infinite;flex-shrink:0;}
   .status-text{font-size:11px;color:var(--muted);padding-left:4px;}
-  .send-btn{padding:7px 18px;border-radius:10px;font-size:13px;font-weight:600;background:linear-gradient(135deg,#5ba8f5,#7cb9ff);border:none;color:#0a1628;cursor:pointer;display:flex;align-items:center;gap:6px;transition:all .15s;flex-shrink:0;letter-spacing:.01em;}
-  .send-btn:hover{background:linear-gradient(135deg,#7cb9ff,#a0d0ff);transform:translateY(-1px);}
-  .send-btn:active{transform:translateY(0);}
-  .send-btn:disabled{opacity:.4;cursor:not-allowed;}
+  .send-btn{width:34px;height:34px;border-radius:50%;background:#7cb9ff;border:none;color:#0a1628;cursor:pointer;display:flex;align-items:center;justify-content:center;flex-shrink:0;transition:background .15s,transform .15s,box-shadow .15s;box-shadow:0 2px 8px rgba(124,185,255,.35);}
+  .send-btn:hover{background:#a0d0ff;transform:scale(1.08);box-shadow:0 4px 14px rgba(124,185,255,.5);}
+  .send-btn:active{transform:scale(0.95);box-shadow:0 1px 4px rgba(124,185,255,.25);}
+  .send-btn:disabled{opacity:.35;cursor:not-allowed;transform:none;box-shadow:none;}
+  .send-btn.visible{animation:send-pop-in .18s cubic-bezier(.34,1.56,.64,1) forwards;}
+  @keyframes send-pop-in{from{opacity:0;transform:scale(.55);}to{opacity:1;transform:scale(1);}}
   .upload-bar-wrap{display:none;height:3px;background:rgba(255,255,255,.06);border-radius:0 0 16px 16px;overflow:hidden;}
   .upload-bar-wrap.active{display:block;}
   .upload-bar{height:100%;background:linear-gradient(90deg,var(--blue),#a0d0ff);width:0%;transition:width .3s ease;}
@@ -205,10 +212,20 @@
   .file-action-btn{width:20px;height:20px;background:rgba(0,0,0,.4);border:none;border-radius:4px;color:var(--muted);cursor:pointer;font-size:11px;display:flex;align-items:center;justify-content:center;}
   .file-action-btn:hover{color:var(--accent);}
   .close-preview{cursor:pointer;opacity:.6;}.close-preview:hover{opacity:1;}
+  /* Breadcrumb navigation */
+  .breadcrumb-bar{display:flex;align-items:center;gap:2px;padding:6px 12px;font-size:12px;border-bottom:1px solid var(--border);flex-shrink:0;overflow:hidden;white-space:nowrap;}
+  .breadcrumb-seg{padding:1px 3px;border-radius:3px;}
+  .breadcrumb-link{color:var(--muted);cursor:pointer;transition:color .12s;}
+  .breadcrumb-link:hover{color:var(--text);background:rgba(255,255,255,.06);}
+  .breadcrumb-current{color:var(--text);font-weight:500;}
+  .breadcrumb-sep{color:var(--border);margin:0 1px;font-size:11px;}
   .file-tree{flex:1;overflow-y:auto;padding:8px;}
   .file-item{display:flex;align-items:center;gap:6px;padding:6px 10px;border-radius:7px;cursor:pointer;font-size:12px;color:var(--muted);transition:all .12s;min-width:0;}
   .file-item:hover{background:rgba(255,255,255,.07);color:var(--text);}
   .file-item.active{background:rgba(124,185,255,.12);color:var(--blue);}
+  .file-tree-toggle{font-size:10px;color:var(--muted);flex-shrink:0;width:10px;text-align:center;line-height:1;}
+  .file-item.file-empty{color:var(--muted);opacity:.5;font-style:italic;cursor:default;font-size:11px;}
+  .file-item.file-empty:hover{background:none;color:var(--muted);}
   .preview-area{flex:1;overflow:auto;padding:14px;flex-direction:column;gap:8px;display:none;opacity:0;transition:opacity .15s;}
   .preview-area.visible{display:flex;opacity:1;}
   .preview-path{font-size:11px;color:var(--muted);padding-bottom:8px;border-bottom:1px solid var(--border);flex-shrink:0;}
@@ -243,49 +260,98 @@
   ::-webkit-scrollbar-track{background:transparent}
   ::-webkit-scrollbar-thumb{background:rgba(255,255,255,.1);border-radius:99px;transition:background .2s}
   ::-webkit-scrollbar-thumb:hover{background:rgba(255,255,255,.22)}
-  @media(max-width:900px){.rightpanel{display:none}}
+  /* ── Desktop: hide mobile-only elements ── */
+  .mobile-hamburger{display:none;}
+  .mobile-files-btn{display:none!important;}
+  .mobile-overlay{display:none;}
+  .mobile-bottom-nav{display:none;}
+
+  @media(max-width:900px){.rightpanel{display:none}.mobile-files-btn{display:inline-flex!important;}}
+
   @media(max-width:640px){
-    .sidebar{display:none}
-    /* Topbar: stack title + chips vertically, allow wrapping */
-    .topbar{padding:8px 12px;gap:6px;flex-wrap:wrap;}
-    .topbar-left{min-width:0;flex:1 1 100%;}
+    /* ── Sidebar: slide-in overlay instead of hidden ── */
+    .sidebar{position:fixed;left:-300px;top:0;bottom:0;width:280px;z-index:200;
+      transition:left .25s ease;box-shadow:4px 0 24px rgba(0,0,0,.4);}
+    .sidebar.mobile-open{left:0;}
+    .sidebar .resize-handle{display:none;}
+    /* Hamburger button */
+    .mobile-hamburger{display:flex;align-items:center;justify-content:center;
+      background:none;border:none;color:var(--muted);cursor:pointer;padding:4px;
+      flex-shrink:0;-webkit-tap-highlight-color:transparent;}
+    .mobile-hamburger:hover{color:var(--text);}
+    /* Overlay backdrop */
+    .mobile-overlay{display:none;position:fixed;inset:0;background:rgba(0,0,0,.5);
+      z-index:199;-webkit-tap-highlight-color:transparent;}
+    .mobile-overlay.visible{display:block;}
+    /* Files button in topbar */
+    .mobile-files-btn{display:inline-flex!important;}
+    /* Right panel: slide-over from right */
+    .rightpanel{display:flex!important;position:fixed;right:-320px;top:0;bottom:0;
+      width:300px;z-index:200;transition:right .25s ease;
+      box-shadow:-4px 0 24px rgba(0,0,0,.4);}
+    .rightpanel.mobile-open{right:0;}
+    .rightpanel .resize-handle{display:none;}
+    /* Bottom navigation bar */
+    .mobile-bottom-nav{display:flex;position:fixed;bottom:0;left:0;right:0;
+      background:var(--sidebar);border-top:1px solid var(--border);
+      z-index:150;padding:4px 0 env(safe-area-inset-bottom,0);
+      justify-content:space-around;align-items:center;}
+    .mobile-nav-btn{display:flex;flex-direction:column;align-items:center;gap:2px;
+      background:none;border:none;color:var(--muted);font-size:9px;padding:6px 4px;
+      cursor:pointer;min-width:44px;min-height:44px;justify-content:center;
+      -webkit-tap-highlight-color:transparent;transition:color .15s;}
+    .mobile-nav-btn.active{color:var(--blue);}
+    .mobile-nav-btn:hover{color:var(--text);}
+    .mobile-nav-btn svg{flex-shrink:0;}
+    /* Hide sidebar nav tabs (replaced by bottom nav) */
+    .sidebar-nav{display:none;}
+    /* Hide sidebar bottom section on mobile (model select, workspace) */
+    .sidebar-bottom{display:none;}
+    /* Topbar adjustments */
+    .topbar{padding:8px 12px;gap:8px;}
     .topbar-title{font-size:14px;}
-    .topbar-meta{font-size:10px;}
-    .topbar-chips{flex-wrap:wrap;gap:4px;}
-    .topbar-chips .chip,.topbar-chips .ws-chip,.topbar-chips button{font-size:11px!important;padding:3px 8px!important;}
-    /* Messages area */
+    .topbar-meta{display:none;}
+    .topbar-chips{flex-wrap:nowrap;gap:4px;overflow-x:auto;-webkit-overflow-scrolling:touch;}
+    .topbar-chips .chip,.topbar-chips .ws-chip,.topbar-chips button{font-size:11px!important;padding:3px 8px!important;white-space:nowrap;}
+    /* Messages area — account for bottom nav */
+    .messages{padding-bottom:60px;}
     .messages-inner{padding:12px 10px 20px;}
     .msg-body{padding-left:0;max-width:100%;}
     .msg-role{font-size:12px;}
-    /* Composer */
-    .composer-wrap{padding:8px 10px 12px!important;}
+    /* Composer — above bottom nav */
+    .composer-wrap{padding:8px 10px 12px!important;margin-bottom:56px;}
     .composer-box{border-radius:12px;}
     .composer-box textarea{font-size:16px;min-height:40px;}
-    .send-btn{padding:6px 14px;font-size:13px;}
+    .send-btn{width:32px;height:32px;}
+    /* Touch targets — minimum 44px */
+    .icon-btn,.mic-btn{min-width:44px;min-height:44px;}
+    .session-item{min-height:44px;padding:10px 12px;}
     /* Empty state */
     .empty-state h2{font-size:18px;}
     .empty-state p{font-size:13px;}
     .suggestion-grid{max-width:100%!important;}
-    .suggestion-btn{font-size:12px;padding:8px 10px;}
+    .suggestion{font-size:12px;padding:10px 12px;}
     /* Approval card */
     .approval-card{padding:0 10px 8px;}
     .approval-btns{gap:6px;}
-    .approval-btn{padding:5px 10px;font-size:11px;}
+    .approval-btn{padding:8px 12px;font-size:12px;min-height:44px;}
     /* Tool cards */
     .tool-card{margin-left:0!important;font-size:12px;}
     /* Settings modal */
     .settings-panel{width:95vw;max-width:95vw;}
+    /* Login page responsive */
+    .card{width:90vw;max-width:320px;padding:28px 24px;}
   }
 
 /* ── Workspace dropdown (topbar) ── */
 .ws-chip{user-select:none;}
-.ws-dropdown{display:none;position:absolute;top:calc(100% + 6px);right:0;min-width:240px;background:#1a2535;border:1px solid var(--border2);border-radius:10px;box-shadow:0 8px 24px rgba(0,0,0,.4);z-index:200;overflow:hidden;max-height:320px;overflow-y:auto;}
+.ws-dropdown{display:none;position:absolute;bottom:calc(100% + 4px);left:0;right:0;min-width:200px;background:#1a2535;border:1px solid var(--border2);border-radius:10px;box-shadow:0 -4px 24px rgba(0,0,0,.4);z-index:200;overflow:hidden;max-height:320px;overflow-y:auto;}
 .ws-dropdown.open{display:block;}
-.ws-opt{padding:9px 14px;cursor:pointer;transition:background .12s;}
+.ws-opt{padding:10px 14px;cursor:pointer;transition:background .12s;display:flex;flex-direction:column;gap:4px;align-items:flex-start;}
 .ws-opt:hover{background:rgba(255,255,255,.07);}
 .ws-opt.active{background:rgba(124,185,255,.1);}
-.ws-opt-name{font-size:13px;color:var(--text);font-weight:500;}
-.ws-opt-path{font-size:11px;color:var(--muted);overflow:hidden;text-overflow:ellipsis;white-space:nowrap;}
+.ws-opt-name{display:block;font-size:13px;color:var(--text);font-weight:500;line-height:1.25;white-space:normal;overflow:hidden;text-overflow:ellipsis;}
+.ws-opt-path{display:block;font-size:10px;color:var(--muted);line-height:1.3;overflow:hidden;text-overflow:ellipsis;white-space:normal;opacity:.72;word-break:break-word;}
 .ws-divider{height:1px;background:var(--border);margin:4px 0;}
 .ws-manage{color:var(--muted);font-size:12px;}
 /* ── Workspace management panel ── */
@@ -297,6 +363,33 @@
 .ws-row-actions{display:flex;gap:4px;flex-shrink:0;}
 .ws-action-btn{padding:4px 9px;border-radius:6px;font-size:11px;font-weight:600;border:1px solid var(--border2);background:rgba(255,255,255,.05);color:var(--muted);cursor:pointer;transition:all .15s;white-space:nowrap;}
 .ws-action-btn:hover{background:rgba(255,255,255,.1);color:var(--text);}
+/* ── Profile dropdown + management panel ── */
+.profile-chip{user-select:none;color:rgba(168,139,250,.9)!important;}
+.profile-dropdown{display:none;position:absolute;top:calc(100% + 6px);right:0;min-width:260px;background:#1a2535;border:1px solid var(--border2);border-radius:10px;box-shadow:0 8px 24px rgba(0,0,0,.4);z-index:200;overflow:hidden;max-height:380px;overflow-y:auto;}
+.profile-dropdown.open{display:block;}
+.profile-opt{padding:9px 14px;cursor:pointer;transition:background .12s;}
+.profile-opt:hover{background:rgba(255,255,255,.07);}
+.profile-opt.active{background:rgba(168,139,250,.08);}
+.profile-opt-name{font-size:13px;color:var(--text);font-weight:500;}
+.profile-opt-meta{font-size:11px;color:var(--muted);margin-top:2px;}
+.profile-opt-badge{display:inline-block;width:7px;height:7px;border-radius:50%;margin-right:5px;vertical-align:middle;}
+.profile-opt-badge.running{background:#4caf50;box-shadow:0 0 4px rgba(76,175,80,.5);}
+.profile-opt-badge.stopped{background:rgba(255,255,255,.2);}
+.profile-card{padding:10px 0;border-bottom:1px solid var(--border);}
+.profile-card:last-of-type{border-bottom:none;}
+.profile-card-header{display:flex;align-items:center;justify-content:space-between;gap:8px;}
+.profile-card-name{font-size:13px;font-weight:600;color:var(--text);}
+.profile-card-name.is-active{color:rgba(168,139,250,.9);}
+.profile-card-meta{font-size:11px;color:var(--muted);margin-top:3px;padding-left:12px;}
+.profile-card-actions{display:flex;gap:4px;flex-shrink:0;}
+/* ── Slash command autocomplete dropdown ── */
+.cmd-dropdown{display:none;position:absolute;bottom:100%;left:0;right:0;background:#1a2535;border:1px solid var(--border2);border-radius:10px;box-shadow:0 -8px 24px rgba(0,0,0,.4);z-index:200;max-height:240px;overflow-y:auto;margin-bottom:4px;}
+.cmd-dropdown.open{display:block;}
+.cmd-item{padding:8px 14px;cursor:pointer;transition:background .12s;}
+.cmd-item:hover,.cmd-item.selected{background:rgba(255,255,255,.07);}
+.cmd-item-name{font-size:13px;color:var(--text);font-weight:500;}
+.cmd-item-arg{color:var(--muted);font-weight:400;font-style:italic;}
+.cmd-item-desc{font-size:11px;color:var(--muted);margin-top:1px;}
 .ws-action-btn.danger:hover{background:rgba(233,69,96,.12);color:var(--accent);border-color:rgba(233,69,96,.3);}
 .ws-add-row{display:flex;gap:8px;align-items:center;padding:10px 0 4px;}
 /* ── Message action buttons (copy, edit, retry) ── */
@@ -352,7 +445,7 @@
 .msg-role > span{line-height:1;}
 
 /* Composer wrap: slightly less padding on smaller heights */
-.composer-wrap{border-top:1px solid rgba(255,255,255,.07);padding:10px 20px 14px;}
+.composer-wrap{border-top:1px solid rgba(255,255,255,.07);padding:10px 20px 14px;position:relative;z-index:10;}
 
 /* Cron status badges: pill shape refinement */
 .cron-status{border-radius:99px;font-size:10px;letter-spacing:.04em;}
@@ -451,9 +544,14 @@
   transition:background .15s;
 }
 .resize-handle:hover,.resize-handle.dragging{background:rgba(124,185,255,.35);}
-.sidebar{position:relative;}
+/* Desktop-only: position:relative for sidebar/rightpanel resize handles.
+   Must be scoped to min-width:641px so it doesn't override the mobile
+   position:fixed slide-in overlay set in the max-width:640px @media block above. */
+@media(min-width:641px){
+  .sidebar{position:relative;}
+  .rightpanel{position:relative;}
+}
 .sidebar .resize-handle{right:-2px;}
-.rightpanel{position:relative;}
 .rightpanel .resize-handle{left:-2px;}
 /* Prevent text selection during drag */
 body.resizing{user-select:none;cursor:col-resize;}
@@ -464,6 +562,26 @@ body.resizing{user-select:none;cursor:col-resize;}
 /* Show more button inside tool card result */
 .tool-card-more{background:none;border:none;color:var(--blue);font-size:10px;cursor:pointer;padding:3px 0 0;opacity:.7;display:block;}
 .tool-card-more:hover{opacity:1;}
+/* Subagent cards: indented with accent border */
+.tool-card-subagent{border-left:2px solid rgba(124,185,255,.3);margin-left:8px;}
+/* Token usage badge below assistant messages */
+.msg-usage{font-size:11px;color:var(--muted);opacity:.6;margin-top:2px;padding-left:42px;}
+.msg-usage:hover{opacity:1;}
+/* Skill picker (cron create form) */
+.skill-picker-wrap{position:relative;}
+.skill-picker-dropdown{position:absolute;left:0;right:0;top:100%;background:var(--sidebar);border:1px solid var(--border2);border-radius:6px;z-index:1100;max-height:180px;overflow-y:auto;box-shadow:0 4px 12px rgba(0,0,0,.3);}
+.skill-opt{padding:6px 10px;cursor:pointer;font-size:12px;color:var(--muted);transition:background .1s;}
+.skill-opt:hover{background:rgba(255,255,255,.08);color:var(--text);}
+.skill-picker-tags{display:flex;flex-wrap:wrap;gap:4px;margin-top:4px;}
+.skill-tag{background:rgba(124,185,255,.12);border:1px solid rgba(124,185,255,.25);border-radius:12px;padding:2px 8px;font-size:11px;color:var(--blue);display:flex;align-items:center;gap:4px;}
+.remove-tag{cursor:pointer;opacity:.6;font-size:13px;line-height:1;}
+.remove-tag:hover{opacity:1;color:var(--accent);}
+/* Skill linked files section */
+.skill-linked-files{margin-top:16px;border-top:1px solid var(--border);padding-top:12px;}
+.skill-linked-section{margin-bottom:8px;}
+.skill-linked-section h4{font-size:10px;text-transform:uppercase;letter-spacing:.05em;color:var(--muted);margin-bottom:4px;}
+.skill-linked-file{display:block;font-size:12px;padding:3px 6px;border-radius:4px;cursor:pointer;color:var(--blue);text-decoration:none;}
+.skill-linked-file:hover{background:rgba(255,255,255,.06);}
 .tool-card-row{margin:0;padding:1px 0;}
 .tool-card{background:rgba(255,255,255,.03);border:1px solid rgba(255,255,255,.07);border-radius:6px;margin:2px 0 2px 40px;overflow:hidden;transition:border-color .15s;}
 .tool-card:hover{border-color:rgba(255,255,255,.12);}
@@ -491,9 +609,9 @@ body.resizing{user-select:none;cursor:col-resize;}
 
 /* ── Settings overlay ── */
 .settings-overlay{position:fixed;inset:0;background:rgba(0,0,0,.5);z-index:1000;display:flex;align-items:center;justify-content:center;}
-.settings-panel{background:var(--bg);border:1px solid var(--border);border-radius:12px;padding:0;width:380px;max-width:90vw;max-height:80vh;overflow-y:auto;box-shadow:0 12px 40px rgba(0,0,0,.5);}
+.settings-panel{background:var(--bg);border:1px solid var(--border);border-radius:12px;padding:0;width:380px;max-width:90vw;max-height:80vh;overflow:visible;box-shadow:0 12px 40px rgba(0,0,0,.5);display:flex;flex-direction:column;}
 .settings-header{display:flex;align-items:center;justify-content:space-between;padding:16px 20px 12px;border-bottom:1px solid var(--border);}
-.settings-body{padding:20px;}
+.settings-body{padding:20px;overflow-y:auto;flex:1;}
 .settings-field{margin-bottom:16px;}
 .settings-field label{display:block;font-size:11px;font-weight:600;letter-spacing:.05em;text-transform:uppercase;color:var(--muted);margin-bottom:6px;}
 /* Save button inside the settings panel */
@@ -557,4 +675,37 @@ body.resizing{user-select:none;cursor:col-resize;}
 .tool-cards-toggle button{background:none;border:none;color:var(--blue);font-size:10px;cursor:pointer;opacity:.6;padding:0;}
 .tool-cards-toggle button:hover{opacity:1;text-decoration:underline;}
 
+/* ── Thinking/reasoning card ── */
+.thinking-card{background:rgba(201,168,76,.06);border:1px solid rgba(201,168,76,.2);border-radius:10px;margin:4px 0 2px 40px;overflow:hidden;transition:border-color .15s;}
+.thinking-card:hover{border-color:rgba(201,168,76,.35);}
+.thinking-card-header{display:flex;align-items:center;gap:6px;padding:6px 12px;cursor:pointer;font-size:12px;color:var(--gold);user-select:none;}
+.thinking-card-icon{font-size:14px;}
+.thinking-card-label{font-weight:600;letter-spacing:.02em;}
+.thinking-card-toggle{margin-left:auto;font-size:10px;transition:transform .15s;}
+.thinking-card.open .thinking-card-toggle{transform:rotate(90deg);}
+.thinking-card-body{display:none;padding:0 12px 10px;max-height:300px;overflow-y:auto;}
+.thinking-card.open .thinking-card-body{display:block;}
+.thinking-card-body pre{font-family:'SF Mono',ui-monospace,monospace;font-size:11px;line-height:1.5;color:var(--muted);white-space:pre-wrap;word-break:break-word;margin:0;}
+
 .bg-error-banner{background:rgba(229,62,62,.15);border:1px solid rgba(229,62,62,.3);color:#fca5a5;padding:8px 16px;font-size:12px;display:flex;align-items:center;justify-content:space-between;gap:12px;border-radius:0;}
+
+/* ── CLI session items in sidebar ── */
+.session-item.cli-session {
+  border-left-color: var(--gold);
+  padding-right: 36px; /* make room for session-actions overlay */
+}
+.session-item.cli-session::after {
+  content: 'cli';
+  font-size: 9px;
+  font-weight: 600;
+  text-transform: uppercase;
+  letter-spacing: .04em;
+  color: var(--gold);
+  opacity: .5;
+  margin-left: auto;
+  flex-shrink: 0;
+  pointer-events: none; /* don't block clicks on session-actions beneath */
+}
+.session-item.cli-session:hover::after {
+  display: none; /* hide badge on hover so session-actions icons are fully reachable */
+}

static/ui.js

@@ -1,4 +1,4 @@
-const S={session:null,messages:[],entries:[],busy:false,pendingFiles:[],toolCalls:[],activeStreamId:null};
+const S={session:null,messages:[],entries:[],busy:false,pendingFiles:[],toolCalls:[],activeStreamId:null,currentDir:'.',activeProfile:'default'};
 const INFLIGHT={};  // keyed by session_id while request in-flight
 const MSG_QUEUE=[];  // messages queued while a request is in-flight
 const $=id=>document.getElementById(id);
@@ -7,6 +7,38 @@ const esc=s=>String(s??'').replace(/[&<>"']/g,c=>({'&':'&amp;','<':'&lt;','>':'&
 // Dynamic model labels -- populated by populateModelDropdown(), fallback to static map
 let _dynamicModelLabels={};
 
+// ── Smart model resolver ────────────────────────────────────────────────────
+// Finds the best matching option value in a <select> for a given model ID.
+// Handles mismatches like 'claude-sonnet-4-6' vs 'anthropic/claude-sonnet-4.6'.
+// Returns the matched option's value (already in the list), or null if no match.
+function _findModelInDropdown(modelId, sel){
+  if(!modelId||!sel) return null;
+  const opts=Array.from(sel.options).map(o=>o.value);
+  // 1. Exact match
+  if(opts.includes(modelId)) return modelId;
+  // 2. Normalize: lowercase, strip namespace prefix, replace hyphens→dots
+  const norm=s=>s.toLowerCase().replace(/^[^/]+\//,'').replace(/-/g,'.');
+  const target=norm(modelId);
+  const exact=opts.find(o=>norm(o)===target);
+  if(exact) return exact;
+  // 3. Prefix/substring: target starts with or contains a significant chunk
+  const base=target.replace(/\.\d+$/,'');  // strip trailing version number
+  const partial=opts.find(o=>norm(o).startsWith(base)||norm(o).includes(base));
+  return partial||null;
+}
+
+// Set the model picker to the best match for modelId.
+// Returns the resolved value that was actually set, or null if nothing matched.
+function _applyModelToDropdown(modelId, sel){
+  if(!modelId||!sel) return null;
+  const resolved=_findModelInDropdown(modelId,sel);
+  if(resolved){
+    sel.value=resolved;
+    return resolved;
+  }
+  return null;
+}
+
 async function populateModelDropdown(){
   const sel=$('modelSelect');
   if(!sel) return;
@@ -30,15 +62,7 @@ async function populateModelDropdown(){
     }
     // Set default model from server if no localStorage preference
     if(data.default_model && !localStorage.getItem('hermes-webui-model')){
-      sel.value=data.default_model;
-      // If the default isn't in the list, add it
-      if(sel.value!==data.default_model){
-        const opt=document.createElement('option');
-        opt.value=data.default_model;
-        opt.textContent=data.default_model.split('/').pop();
-        sel.insertBefore(opt,sel.firstChild);
-        sel.value=data.default_model;
-      }
+      _applyModelToDropdown(data.default_model, sel);
     }
   }catch(e){
     // API unavailable -- keep the hardcoded HTML options as fallback
@@ -58,6 +82,8 @@ let _scrollPinned=true;
     _scrollPinned=nearBottom;
   });
 })();
+function _fmtTokens(n){if(!n||n<0)return'0';if(n>=1e6)return(n/1e6).toFixed(1)+'M';if(n>=1e3)return(n/1e3).toFixed(1)+'k';return String(n);}
+
 function scrollIfPinned(){
   if(!_scrollPinned) return;
   const el=$('messages');
@@ -81,6 +107,22 @@ function getModelLabel(modelId){
 
 function renderMd(raw){
   let s=raw||'';
+  // Pre-pass: convert safe inline HTML tags the model may emit into their
+  // markdown equivalents so the pipeline can render them correctly.
+  // Only runs OUTSIDE fenced code blocks and backtick spans (stash + restore).
+  // Unsafe tags (anything not in the allowlist) are left as-is and will be
+  // HTML-escaped by esc() when they reach an innerHTML assignment -- no XSS risk.
+  const fence_stash=[];
+  s=s.replace(/(```[\s\S]*?```|`[^`\n]+`)/g,m=>{fence_stash.push(m);return '\x00F'+(fence_stash.length-1)+'\x00';});
+  // Safe tag → markdown equivalent (these produce the same output as **text** etc.)
+  s=s.replace(/<strong>([\s\S]*?)<\/strong>/gi,(_,t)=>'**'+t+'**');
+  s=s.replace(/<b>([\s\S]*?)<\/b>/gi,(_,t)=>'**'+t+'**');
+  s=s.replace(/<em>([\s\S]*?)<\/em>/gi,(_,t)=>'*'+t+'*');
+  s=s.replace(/<i>([\s\S]*?)<\/i>/gi,(_,t)=>'*'+t+'*');
+  s=s.replace(/<code>([^<]*?)<\/code>/gi,(_,t)=>'`'+t+'`');
+  s=s.replace(/<br\s*\/?>/gi,'\n');
+  // Restore stashed code blocks
+  s=s.replace(/\x00F(\d+)\x00/g,(_,i)=>fence_stash[+i]);
   // Mermaid blocks: render as diagram containers (processed after DOM insertion)
   s=s.replace(/```mermaid\n?([\s\S]*?)```/g,(_,code)=>{
     const id='mermaid-'+Math.random().toString(36).slice(2,10);
@@ -88,12 +130,27 @@ function renderMd(raw){
   });
   s=s.replace(/```([\w+-]*)\n?([\s\S]*?)```/g,(_,lang,code)=>{const h=lang?`<div class="pre-header">${esc(lang)}</div>`:'';return `${h}<pre><code>${esc(code.replace(/\n$/,''))}</code></pre>`;});
   s=s.replace(/`([^`\n]+)`/g,(_,c)=>`<code>${esc(c)}</code>`);
+  // inlineMd: process bold/italic/code/links within a single line of text.
+  // Used inside list items and blockquotes where the text may already contain
+  // HTML from the pre-pass → bold pipeline, so we cannot call esc() directly.
+  function inlineMd(t){
+    t=t.replace(/\*\*\*(.+?)\*\*\*/g,(_,x)=>`<strong><em>${esc(x)}</em></strong>`);
+    t=t.replace(/\*\*(.+?)\*\*/g,(_,x)=>`<strong>${esc(x)}</strong>`);
+    t=t.replace(/\*([^*\n]+)\*/g,(_,x)=>`<em>${esc(x)}</em>`);
+    t=t.replace(/`([^`\n]+)`/g,(_,x)=>`<code>${esc(x)}</code>`);
+    t=t.replace(/\[([^\]]+)\]\((https?:\/\/[^\)]+)\)/g,(_,lb,u)=>`<a href="${esc(u)}" target="_blank" rel="noopener">${esc(lb)}</a>`);
+    // Escape any plain text that isn't already wrapped in a tag we produced
+    // by escaping bare < > that aren't part of our own tags
+    const SAFE_INLINE=/^<\/?(strong|em|code|a)([\s>]|$)/i;
+    t=t.replace(/<\/?[a-z][^>]*>/gi,tag=>SAFE_INLINE.test(tag)?tag:esc(tag));
+    return t;
+  }
   s=s.replace(/\*\*\*(.+?)\*\*\*/g,(_,t)=>`<strong><em>${esc(t)}</em></strong>`);
   s=s.replace(/\*\*(.+?)\*\*/g,(_,t)=>`<strong>${esc(t)}</strong>`);
   s=s.replace(/\*([^*\n]+)\*/g,(_,t)=>`<em>${esc(t)}</em>`);
-  s=s.replace(/^### (.+)$/gm,(_,t)=>`<h3>${esc(t)}</h3>`).replace(/^## (.+)$/gm,(_,t)=>`<h2>${esc(t)}</h2>`).replace(/^# (.+)$/gm,(_,t)=>`<h1>${esc(t)}</h1>`);
+  s=s.replace(/^### (.+)$/gm,(_,t)=>`<h3>${inlineMd(t)}</h3>`).replace(/^## (.+)$/gm,(_,t)=>`<h2>${inlineMd(t)}</h2>`).replace(/^# (.+)$/gm,(_,t)=>`<h1>${inlineMd(t)}</h1>`);
   s=s.replace(/^---+$/gm,'<hr>');
-  s=s.replace(/^> (.+)$/gm,(_,t)=>`<blockquote>${esc(t)}</blockquote>`);
+  s=s.replace(/^> (.+)$/gm,(_,t)=>`<blockquote>${inlineMd(t)}</blockquote>`);
   // B8: improved list handling supporting up to 2 levels of indentation
   s=s.replace(/((?:^(?:  )?[-*+] .+\n?)+)/gm,block=>{
     const lines=block.trimEnd().split('\n');
@@ -101,8 +158,8 @@ function renderMd(raw){
     for(const l of lines){
       const indent=/^ {2,}/.test(l);
       const text=l.replace(/^ {0,4}[-*+] /,'');
-      if(indent) html+=`<li style="margin-left:16px">${esc(text)}</li>`;
-      else html+=`<li>${esc(text)}</li>`;
+      if(indent) html+=`<li style="margin-left:16px">${inlineMd(text)}</li>`;
+      else html+=`<li>${inlineMd(text)}</li>`;
     }
     return html+'</ul>';
   });
@@ -111,7 +168,7 @@ function renderMd(raw){
     let html='<ol>';
     for(const l of lines){
       const text=l.replace(/^ {0,4}\d+\. /,'');
-      html+=`<li>${esc(text)}</li>`;
+      html+=`<li>${inlineMd(text)}</li>`;
     }
     return html+'</ol>';
   });
@@ -128,6 +185,12 @@ function renderMd(raw){
     const body=rows.slice(2).map(r=>`<tr>${parseRow(r)}</tr>`).join('');
     return `<table><thead>${header}</thead><tbody>${body}</tbody></table>`;
   });
+  // Escape any remaining HTML tags that are NOT from our own markdown output.
+  // Our pipeline only emits: <strong>,<em>,<code>,<pre>,<h1-6>,<ul>,<ol>,<li>,
+  // <table>,<thead>,<tbody>,<tr>,<th>,<td>,<hr>,<blockquote>,<p>,<br>,<a>,
+  // <div class="..."> (mermaid/pre-header). Everything else is untrusted input.
+  const SAFE_TAGS=/^<\/?(strong|em|code|pre|h[1-6]|ul|ol|li|table|thead|tbody|tr|th|td|hr|blockquote|p|br|a|div)([\s>]|$)/i;
+  s=s.replace(/<\/?[a-z][^>]*>/gi,tag=>SAFE_TAGS.test(tag)?tag:esc(tag));
   const parts=s.split(/\n{2,}/);
   s=parts.map(p=>{p=p.trim();if(!p)return '';if(/^<(h[1-6]|ul|ol|pre|hr|blockquote)/.test(p))return p;return `<p>${p.replace(/\n/g,'<br>')}</p>`;}).join('\n');
   return s;
@@ -150,9 +213,25 @@ function setStatus(t){
     if(dismiss)dismiss.style.display=(!transient && !S.busy)?'inline':'none';
   }
 }
+function updateSendBtn(){
+  const btn=$('btnSend');
+  if(!btn) return;
+  const hasContent=$('msg').value.trim().length>0||S.pendingFiles.length>0;
+  const shouldShow=hasContent&&!S.busy;
+  if(shouldShow&&btn.style.display==='none'){
+    btn.style.display='';
+    // Remove then re-add class to retrigger animation each time
+    btn.classList.remove('visible');
+    requestAnimationFrame(()=>btn.classList.add('visible'));
+  } else if(!shouldShow&&btn.style.display!=='none'){
+    btn.style.display='none';
+    btn.classList.remove('visible');
+  }
+}
 function setBusy(v){
   S.busy=v;
   $('btnSend').disabled=v;
+  updateSendBtn();
   const dots=$('activityDots');
   if(dots) dots.style.display=v?'flex':'none';
   if(!v){
@@ -267,15 +346,23 @@ function syncTopbar(){
   document.title=sessionTitle+' \u2014 Hermes';
   const vis=S.messages.filter(m=>m&&m.role&&m.role!=='tool');
   $('topbarMeta').textContent=`${vis.length} messages`;
-  const m=S.session.model||'';
-  $('modelSelect').value=m;  // set dropdown first so chip reads consistent value
-  // If session model isn't in the dropdown, add it dynamically
-  if(m && $('modelSelect').value!==m){
-    const opt=document.createElement('option');
-    opt.value=m;
-    opt.textContent=getModelLabel(m);
-    $('modelSelect').appendChild(opt);
-    $('modelSelect').value=m;
+  // If a profile switch just happened, apply its model rather than the session's stale value.
+  // S._pendingProfileModel is set by switchToProfile() and cleared here after one application.
+  const modelOverride=S._pendingProfileModel;
+  if(modelOverride){
+    S._pendingProfileModel=null;
+    _applyModelToDropdown(modelOverride,$('modelSelect'));
+  } else {
+    const m=S.session.model||'';
+    const applied=_applyModelToDropdown(m,$('modelSelect'));
+    // If the model isn't in the list at all, add it so the session value is preserved
+    if(!applied && m){
+      const opt=document.createElement('option');
+      opt.value=m;
+      opt.textContent=getModelLabel(m);
+      $('modelSelect').appendChild(opt);
+      $('modelSelect').value=m;
+    }
   }
   // Show Clear button only when session has messages
   const clearBtn=$('btnClearConv');
@@ -283,13 +370,6 @@ function syncTopbar(){
   const displayModel=$('modelSelect').value||m;
   $('modelChip').textContent=getModelLabel(displayModel);
   const ws=S.session.workspace||'';
-  $('wsChip').textContent=ws.split('/').slice(-2).join('/')||ws;
-  // Update workspace chip in topbar with friendly name from workspace list
-  const wsChipEl=$('wsChip');
-  if(wsChipEl){
-    const wsFriendly=getWorkspaceFriendlyName(ws);
-    wsChipEl.textContent='\u{1F4C1} '+wsFriendly+' \u25BE';
-  }
   // Update sidebar workspace display
   const sidebarName=$('sidebarWsName');
   const sidebarPath=$('sidebarWsPath');
@@ -300,6 +380,9 @@ function syncTopbar(){
     sidebarPath.textContent=ws;
   }
   // modelSelect already set above
+  // Update profile chip label
+  const profileLabel=$('profileChipLabel');
+  if(profileLabel) profileLabel.textContent=S.activeProfile||'default';
 }
 
 function msgContent(m){
@@ -328,11 +411,22 @@ function renderMessages(){
   for(let vi=0;vi<visWithIdx.length;vi++){
     const {m,rawIdx}=visWithIdx[vi];
     let content=m.content||'';
-    if(Array.isArray(content))content=content.filter(p=>p&&p.type==='text').map(p=>p.text||p.content||'').join('\n');
+    // Extract thinking/reasoning blocks from structured content (Claude extended thinking, o3)
+    let thinkingText='';
+    if(Array.isArray(content)){
+      thinkingText=content.filter(p=>p&&(p.type==='thinking'||p.type==='reasoning')).map(p=>p.thinking||p.reasoning||p.text||'').join('\n');
+      content=content.filter(p=>p&&p.type==='text').map(p=>p.text||p.content||'').join('\n');
+    }
     const isUser=m.role==='user';
     const isLastAssistant=!isUser&&vi===visWithIdx.length-1;
+    // Render thinking card before the assistant message (collapsed by default)
+    if(thinkingText&&!isUser){
+      const thinkRow=document.createElement('div');thinkRow.className='msg-row thinking-card-row';
+      thinkRow.innerHTML=`<div class="thinking-card"><div class="thinking-card-header" onclick="this.parentElement.classList.toggle('open')"><span class="thinking-card-icon">&#128161;</span><span class="thinking-card-label">Thinking</span><span class="thinking-card-toggle">&#9656;</span></div><div class="thinking-card-body"><pre>${esc(thinkingText)}</pre></div></div>`;
+      inner.appendChild(thinkRow);
+    }
     const row=document.createElement('div');row.className='msg-row';
-    row.dataset.msgIdx=rawIdx;
+    row.dataset.msgIdx=rawIdx;row.dataset.role=m.role||'assistant';
     let filesHtml='';
     if(m.attachments&&m.attachments.length)
       filesHtml=`<div class="msg-files">${m.attachments.map(f=>`<div class="msg-file-badge">&#128206; ${esc(f)}</div>`).join('')}</div>`;
@@ -394,6 +488,23 @@ function renderMessages(){
       else inner.appendChild(frag);
     }
   }
+  // Render usage badge on the last assistant message row (if enabled and usage data exists)
+  if(window._showTokenUsage&&S.session&&(S.session.input_tokens||S.session.output_tokens)){
+    const rows=inner.querySelectorAll('.msg-row');
+    let lastAssist=null;
+    for(let i=rows.length-1;i>=0;i--){if(rows[i].dataset.role==='assistant'){lastAssist=rows[i];break;}}
+    if(lastAssist&&!lastAssist.querySelector('.msg-usage')){
+      const usage=document.createElement('div');
+      usage.className='msg-usage';
+      const inTok=S.session.input_tokens||0;
+      const outTok=S.session.output_tokens||0;
+      const cost=S.session.estimated_cost;
+      let text=`${_fmtTokens(inTok)} in · ${_fmtTokens(outTok)} out`;
+      if(cost) text+=` · ~$${cost<0.01?cost.toFixed(4):cost.toFixed(2)}`;
+      usage.textContent=text;
+      lastAssist.appendChild(usage);
+    }
+  }
   scrollToBottom();
   // Apply syntax highlighting after DOM is built
   requestAnimationFrame(()=>{highlightCode();addCopyButtons();renderMermaidBlocks();});
@@ -407,7 +518,8 @@ function toolIcon(name){
   const icons={terminal:'⬛',read_file:'📄',write_file:'✏️',search_files:'🔍',
     web_search:'🌐',web_extract:'🌐',execute_code:'⚙️',patch:'🔧',
     memory:'🧠',skill_manage:'📚',todo:'✅',cronjob:'⏱️',delegate_task:'🤖',
-    send_message:'💬',browser_navigate:'🌐',vision_analyze:'👁️'};
+    send_message:'💬',browser_navigate:'🌐',vision_analyze:'👁️',
+    subagent_progress:'🔀'};
   return icons[name]||'🔧';
 }
 
@@ -428,13 +540,22 @@ function buildToolCard(tc){
   }
   const hasMore=tc.snippet&&tc.snippet.length>displaySnippet.length;
   const runIndicator=tc.done===false?'<span class="tool-card-running-dot"></span>':'';
+  const isSubagent=tc.name==='subagent_progress';
+  const isDelegation=tc.name==='delegate_task';
+  const cardClass='tool-card'+(tc.done===false?' tool-card-running':'')+(isSubagent?' tool-card-subagent':'');
+  // Clean up subagent preview: strip leading 🔀 emoji since the icon already shows it
+  let displayName=tc.name;
+  if(isSubagent) displayName='Subagent';
+  if(isDelegation) displayName='Delegate task';
+  let previewText=tc.preview||displaySnippet||'';
+  if(isSubagent) previewText=previewText.replace(/^🔀\s*/,'');
   row.innerHTML=`
-    <div class="tool-card${tc.done===false?' tool-card-running':''}">
+    <div class="${cardClass}">
       <div class="tool-card-header" onclick="this.closest('.tool-card').classList.toggle('open')">
         ${runIndicator}
         <span class="tool-card-icon">${icon}</span>
-        <span class="tool-card-name">${esc(tc.name)}</span>
-        <span class="tool-card-preview">${esc(tc.preview||displaySnippet||'')}</span>
+        <span class="tool-card-name">${esc(displayName)}</span>
+        <span class="tool-card-preview">${esc(previewText)}</span>
         ${hasDetail?'<span class="tool-card-toggle">▸</span>':''}
       </div>
       ${hasDetail?`<div class="tool-card-detail">
@@ -668,27 +789,88 @@ function fileIcon(name, type){
   return '📄';
 }
 
+function renderBreadcrumb(){
+  const bar=$('breadcrumbBar');
+  const upBtn=$('btnUpDir');
+  if(!bar)return;
+  if(S.currentDir==='.'){
+    bar.style.display='none';
+    if(upBtn)upBtn.style.display='none';
+    return;
+  }
+  bar.style.display='flex';
+  if(upBtn)upBtn.style.display='';
+  bar.innerHTML='';
+  // Root segment
+  const root=document.createElement('span');
+  root.className='breadcrumb-seg breadcrumb-link';
+  root.textContent='~';
+  root.onclick=()=>loadDir('.');
+  bar.appendChild(root);
+  // Path segments
+  const parts=S.currentDir.split('/');
+  let accumulated='';
+  for(let i=0;i<parts.length;i++){
+    const sep=document.createElement('span');
+    sep.className='breadcrumb-sep';sep.textContent='/';
+    bar.appendChild(sep);
+    accumulated+=(accumulated?'/':'')+parts[i];
+    const seg=document.createElement('span');
+    seg.textContent=parts[i];
+    if(i<parts.length-1){
+      seg.className='breadcrumb-seg breadcrumb-link';
+      const target=accumulated;
+      seg.onclick=()=>loadDir(target);
+    } else {
+      seg.className='breadcrumb-seg breadcrumb-current';
+    }
+    bar.appendChild(seg);
+  }
+}
+
+// Track expanded directories for tree view
+if(!S._expandedDirs) S._expandedDirs=new Set();
+// Cache of fetched directory contents: path -> entries[]
+if(!S._dirCache) S._dirCache={};
+
 function renderFileTree(){
   const box=$('fileTree');box.innerHTML='';
-  for(const item of S.entries){
+  // Cache current dir entries
+  S._dirCache[S.currentDir||'.']=S.entries;
+  _renderTreeItems(box, S.entries, 0);
+}
+
+function _renderTreeItems(container, entries, depth){
+  for(const item of entries){
     const el=document.createElement('div');el.className='file-item';
+    el.style.paddingLeft=(8+depth*16)+'px';
+
+    if(item.type==='dir'){
+      // Toggle arrow for directories
+      const arrow=document.createElement('span');
+      arrow.className='file-tree-toggle';
+      const isExpanded=S._expandedDirs.has(item.path);
+      arrow.textContent=isExpanded?'\u25BE':'\u25B8';
+      el.appendChild(arrow);
+    }
 
     // Icon
     const iconEl=document.createElement('span');
     iconEl.className='file-icon';iconEl.textContent=fileIcon(item.name,item.type);
     el.appendChild(iconEl);
 
-    // Name -- takes all remaining space, truncates with ellipsis
+    // Name
     const nameEl=document.createElement('span');
     nameEl.className='file-name';nameEl.textContent=item.name;nameEl.title='Double-click to rename';
-    // Inline rename on double-click
     nameEl.ondblclick=(e)=>{
       e.stopPropagation();
+      // For directories, double-click navigates (breadcrumb view)
+      if(item.type==='dir'){loadDir(item.path);return;}
       const inp=document.createElement('input');
       inp.className='file-rename-input';inp.value=item.name;
       inp.onclick=(e2)=>e2.stopPropagation();
       const finish=async(save)=>{
-        inp.onblur=null;  // prevent double-call: Enter triggers blur after replaceWith
+        inp.onblur=null;
         if(save){
           const newName=inp.value.trim();
           if(newName&&newName!==item.name){
@@ -697,7 +879,9 @@ function renderFileTree(){
                 session_id:S.session.session_id,path:item.path,new_name:newName
               })});
               showToast(`Renamed to ${newName}`);
-              await loadDir('.');
+              // Invalidate cache and re-render
+              delete S._dirCache[S.currentDir];
+              await loadDir(S.currentDir);
             }catch(err){showToast('Rename failed: '+err.message);}
           }
         }
@@ -713,7 +897,7 @@ function renderFileTree(){
     };
     el.appendChild(nameEl);
 
-    // Size -- only for files, right-aligned, shrinks but never wraps
+    // Size -- only for files
     if(item.type==='file'&&item.size){
       const sizeEl=document.createElement('span');
       sizeEl.className='file-size';
@@ -721,16 +905,54 @@ function renderFileTree(){
       el.appendChild(sizeEl);
     }
 
-    // Delete button -- for files, shown on hover
+    // Delete button -- for files
     if(item.type==='file'){
       const del=document.createElement('button');
-      del.className='file-del-btn';del.title='Delete';del.textContent='×';
+      del.className='file-del-btn';del.title='Delete';del.textContent='\u00d7';
       del.onclick=async(e)=>{e.stopPropagation();await deleteWorkspaceFile(item.path,item.name);};
       el.appendChild(del);
     }
 
-    el.onclick=async()=>item.type==='dir'?loadDir(item.path):openFile(item.path);
-    box.appendChild(el);
+    if(item.type==='dir'){
+      // Single-click toggles expand/collapse
+      el.onclick=async(e)=>{
+        e.stopPropagation();
+        if(S._expandedDirs.has(item.path)){
+          S._expandedDirs.delete(item.path);
+          if(typeof _saveExpandedDirs==='function')_saveExpandedDirs();
+          renderFileTree();
+        }else{
+          S._expandedDirs.add(item.path);
+          if(typeof _saveExpandedDirs==='function')_saveExpandedDirs();
+          // Fetch children if not cached
+          if(!S._dirCache[item.path]){
+            try{
+              const data=await api(`/api/list?session_id=${encodeURIComponent(S.session.session_id)}&path=${encodeURIComponent(item.path)}`);
+              S._dirCache[item.path]=data.entries||[];
+            }catch(e2){S._dirCache[item.path]=[];}
+          }
+          renderFileTree();
+        }
+      };
+    }else{
+      el.onclick=async()=>openFile(item.path);
+    }
+
+    container.appendChild(el);
+
+    // Render children if directory is expanded
+    if(item.type==='dir'&&S._expandedDirs.has(item.path)){
+      const children=S._dirCache[item.path]||[];
+      if(children.length){
+        _renderTreeItems(container, children, depth+1);
+      }else{
+        const empty=document.createElement('div');
+        empty.className='file-item file-empty';
+        empty.style.paddingLeft=(8+(depth+1)*16)+'px';
+        empty.textContent='(empty)';
+        container.appendChild(empty);
+      }
+    }
   }
 }
 
@@ -742,7 +964,7 @@ async function deleteWorkspaceFile(relPath, name){
     showToast(`Deleted ${name}`);
     // Close preview if we just deleted the viewed file
     if($('previewPathText').textContent===relPath)$('btnClearPreview').onclick();
-    await loadDir('.');
+    await loadDir(S.currentDir);
   }catch(e){setStatus('Delete failed: '+e.message);}
 }
 
@@ -750,12 +972,12 @@ async function promptNewFile(){
   if(!S.session)return;
   const name=prompt('New file name (e.g. notes.md):','');
   if(!name||!name.trim())return;
+  const relPath=S.currentDir==='.'?name.trim():(S.currentDir+'/'+name.trim());
   try{
-    await api('/api/file/create',{method:'POST',body:JSON.stringify({session_id:S.session.session_id,path:name.trim(),content:''})});
+    await api('/api/file/create',{method:'POST',body:JSON.stringify({session_id:S.session.session_id,path:relPath,content:''})});
     showToast(`Created ${name.trim()}`);
-    await loadDir('.');
-    // Open the new file immediately
-    openFile(name.trim());
+    await loadDir(S.currentDir);
+    openFile(relPath);
   }catch(e){setStatus('Create failed: '+e.message);}
 }
 
@@ -763,17 +985,19 @@ async function promptNewFolder(){
   if(!S.session)return;
   const name=prompt('New folder name:','');
   if(!name||!name.trim())return;
+  const relPath=S.currentDir==='.'?name.trim():(S.currentDir+'/'+name.trim());
   try{
-    await api('/api/file/create-dir',{method:'POST',body:JSON.stringify({session_id:S.session.session_id,path:name.trim()})});
+    await api('/api/file/create-dir',{method:'POST',body:JSON.stringify({session_id:S.session.session_id,path:relPath})});
     showToast(`Created folder ${name.trim()}`);
-    await loadDir('.');
+    await loadDir(S.currentDir);
   }catch(e){setStatus('Create folder failed: '+e.message);}
 }
 
 function renderTray(){
   const tray=$('attachTray');tray.innerHTML='';
-  if(!S.pendingFiles.length){tray.classList.remove('has-files');return;}
+  if(!S.pendingFiles.length){tray.classList.remove('has-files');updateSendBtn();return;}
   tray.classList.add('has-files');
+  updateSendBtn();
   S.pendingFiles.forEach((f,i)=>{
     const chip=document.createElement('div');chip.className='attach-chip';
     chip.innerHTML=`&#128206; ${esc(f.name)} <button title="Remove">&#10005;</button>`;

static/workspace.js

@@ -1,19 +1,74 @@
 async function api(path,opts={}){
   const url=new URL(path,location.origin);
   const res=await fetch(url.href,{credentials:'include',headers:{'Content-Type':'application/json'},...opts});
-  if(!res.ok)throw new Error(await res.text());
+  if(!res.ok){
+    const text=await res.text();
+    // Parse JSON error body and surface the human-readable message,
+    // rather than showing raw JSON like {"error":"Profile 'x' does not exist."}
+    try{const j=JSON.parse(text);throw new Error(j.error||j.message||text);}
+    catch(e){if(e instanceof SyntaxError)throw new Error(text);throw e;}
+  }
   const ct=res.headers.get('content-type')||'';
   return ct.includes('application/json')?res.json():res.text();
 }
 
+// Persist/restore expanded directory state per workspace in localStorage
+function _wsExpandKey(){
+  const ws=S.session&&S.session.workspace;
+  return ws?'hermes-webui-expanded:'+ws:null;
+}
+function _saveExpandedDirs(){
+  const key=_wsExpandKey();if(!key)return;
+  try{localStorage.setItem(key,JSON.stringify([...(S._expandedDirs||new Set())]));}catch(e){}
+}
+function _restoreExpandedDirs(){
+  const key=_wsExpandKey();
+  if(!key){S._expandedDirs=new Set();return;}
+  try{
+    const raw=localStorage.getItem(key);
+    S._expandedDirs=raw?new Set(JSON.parse(raw)):new Set();
+  }catch(e){S._expandedDirs=new Set();}
+}
+
 async function loadDir(path){
   if(!S.session)return;
   try{
+    if(!path||path==='.'){
+      S._dirCache={};
+      _restoreExpandedDirs();  // restore per-workspace expanded state on root load
+    }
+    S.currentDir=path||'.';
     const data=await api(`/api/list?session_id=${encodeURIComponent(S.session.session_id)}&path=${encodeURIComponent(path)}`);
-    S.entries=data.entries||[];renderFileTree();
+    S.entries=data.entries||[];renderBreadcrumb();renderFileTree();
+    // Pre-fetch contents of restored expanded dirs so they render without a second click
+    if(!path||path==='.'){
+      for(const dirPath of (S._expandedDirs||[])){
+        if(!S._dirCache[dirPath]){
+          try{
+            const dc=await api(`/api/list?session_id=${encodeURIComponent(S.session.session_id)}&path=${encodeURIComponent(dirPath)}`);
+            S._dirCache[dirPath]=dc.entries||[];
+          }catch(e2){S._dirCache[dirPath]=[];}
+        }
+      }
+      if(S._expandedDirs&&S._expandedDirs.size>0)renderFileTree();
+    }
+    if(typeof clearPreview==='function'){
+      if(typeof _previewDirty!=='undefined'&&_previewDirty){
+        if(confirm('You have unsaved changes in the preview. Discard and navigate?'))clearPreview();
+      }else{
+        clearPreview();
+      }
+    }
   }catch(e){console.warn('loadDir',e);}
 }
 
+function navigateUp(){
+  if(!S.session||S.currentDir==='.')return;
+  const parts=S.currentDir.split('/');
+  parts.pop();
+  loadDir(parts.length?parts.join('/'):'.');
+}
+
 // File extension sets for preview routing (must match server-side sets)
 const IMAGE_EXTS  = new Set(['.png','.jpg','.jpeg','.gif','.svg','.webp','.ico','.bmp']);
 const MD_EXTS     = new Set(['.md','.markdown','.mdown']);

tests/test_regressions.py

@@ -438,3 +438,37 @@ def test_newSession_clears_live_tool_cards(cleanup_test_sessions):
     next_fn = src.find("async function ", new_sess_idx + 10)
     new_sess_body = src[new_sess_idx:next_fn]
     assert "clearLiveToolCards" in new_sess_body,         "newSession() must call clearLiveToolCards() to clear stale live cards"
+
+
+# ── R16: Stack traces must not leak to clients in 500 responses ────────────
+
+def test_500_response_has_no_trace_field():
+    """R16: HTTP 500 responses must not include a 'trace' field.
+    Leaking tracebacks exposes file paths, module names, and potentially
+    secret values from local variables.
+    """
+    # POST to /api/chat/start with missing required fields to trigger an error
+    data, status = post("/api/chat/start", {})
+    # Should be an error response (4xx or 5xx)
+    assert "trace" not in data, \
+        "Server must not leak stack traces to clients"
+
+def test_upload_error_has_no_trace_field():
+    """R16b: Upload 500 responses must not include a 'trace' field."""
+    # Send a POST to /api/upload with invalid content to trigger the error handler
+    req = urllib.request.Request(
+        BASE + "/api/upload",
+        data=b"not-multipart-data",
+        headers={"Content-Type": "text/plain", "Content-Length": "18"},
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=10) as r:
+            body = json.loads(r.read())
+            code = r.status
+    except urllib.error.HTTPError as e:
+        body = json.loads(e.read())
+        code = e.code
+    assert code >= 400, "Invalid upload should return an error status"
+    assert "trace" not in body, \
+        "Upload errors must not leak stack traces to clients"
+    assert "error" in body, "Error responses must include an 'error' key"

tests/test_sprint16.py

@@ -0,0 +1,709 @@
+"""
+Sprint 16 Tests: safe HTML rendering in renderMd(), active session styling,
+session sidebar polish (SVG icons, overlay actions).
+"""
+import html as _html
+import pathlib
+import re
+import urllib.request
+
+BASE = "http://127.0.0.1:8788"
+REPO_ROOT = pathlib.Path(__file__).parent.parent
+
+
+# ── Helpers ──────────────────────────────────────────────────────────────────
+
+def get_text(path):
+    with urllib.request.urlopen(BASE + path, timeout=10) as r:
+        return r.read().decode("utf-8"), r.status
+
+
+def esc(s):
+    """Mirror of esc() in ui.js — HTML-escapes a string."""
+    return _html.escape(str(s), quote=True)
+
+
+SAFE_TAGS = re.compile(
+    r"^<\/?(strong|em|code|pre|h[1-6]|ul|ol|li|table|thead|tbody|tr|th|td"
+    r"|hr|blockquote|p|br|a|div)([\s>]|$)",
+    re.I,
+)
+SAFE_INLINE = re.compile(r"^<\/?(strong|em|code|a)([\s>]|$)", re.I)
+
+
+def inline_md(t):
+    """Mirror of inlineMd() in ui.js — for use inside list items / blockquotes."""
+    t = re.sub(r"\*\*\*(.+?)\*\*\*", lambda m: "<strong><em>" + esc(m.group(1)) + "</em></strong>", t)
+    t = re.sub(r"\*\*(.+?)\*\*",     lambda m: "<strong>" + esc(m.group(1)) + "</strong>", t)
+    t = re.sub(r"\*([^*\n]+)\*",     lambda m: "<em>" + esc(m.group(1)) + "</em>", t)
+    t = re.sub(r"`([^`\n]+)`",        lambda m: "<code>" + esc(m.group(1)) + "</code>", t)
+    t = re.sub(
+        r"\[([^\]]+)\]\((https?://[^\)]+)\)",
+        lambda m: f'<a href="{esc(m.group(2))}" target="_blank" rel="noopener">{esc(m.group(1))}</a>',
+        t,
+    )
+    t = re.sub(r"</?[a-zA-Z][^>]*>", lambda m: m.group() if SAFE_INLINE.match(m.group()) else esc(m.group()), t)
+    return t
+
+
+def render_md(raw):
+    """
+    Python mirror of renderMd() in static/ui.js.
+    Kept in sync with the JS implementation so tests catch regressions
+    if the JS logic drifts from the documented behaviour.
+    """
+    s = raw or ""
+
+    # Pre-pass: stash code blocks/spans, convert safe HTML → markdown equivalents
+    fence_stash = []
+
+    def stash(m):
+        fence_stash.append(m.group())
+        return "\x00F" + str(len(fence_stash) - 1) + "\x00"
+
+    s = re.sub(r"(```[\s\S]*?```|`[^`\n]+`)", stash, s)
+    s = re.sub(r"<strong>([\s\S]*?)</strong>", lambda m: "**" + m.group(1) + "**", s, flags=re.I)
+    s = re.sub(r"<b>([\s\S]*?)</b>",           lambda m: "**" + m.group(1) + "**", s, flags=re.I)
+    s = re.sub(r"<em>([\s\S]*?)</em>",          lambda m: "*"  + m.group(1) + "*",  s, flags=re.I)
+    s = re.sub(r"<i>([\s\S]*?)</i>",            lambda m: "*"  + m.group(1) + "*",  s, flags=re.I)
+    s = re.sub(r"<code>([^<]*?)</code>",         lambda m: "`"  + m.group(1) + "`",  s, flags=re.I)
+    s = re.sub(r"<br\s*/?>", "\n", s, flags=re.I)
+    s = re.sub(r"\x00F(\d+)\x00", lambda m: fence_stash[int(m.group(1))], s)
+
+    # Fenced code blocks
+    def fenced(m):
+        lang, code = m.group(1), m.group(2).rstrip("\n")
+        h = f'<div class="pre-header">{esc(lang)}</div>' if lang else ""
+        return h + "<pre><code>" + esc(code) + "</code></pre>"
+    s = re.sub(r"```([\w+-]*)\n?([\s\S]*?)```", fenced, s)
+    s = re.sub(r"`([^`\n]+)`", lambda m: "<code>" + esc(m.group(1)) + "</code>", s)
+
+    # Inline formatting (top-level, outside list items)
+    s = re.sub(r"\*\*\*(.+?)\*\*\*", lambda m: "<strong><em>" + esc(m.group(1)) + "</em></strong>", s)
+    s = re.sub(r"\*\*(.+?)\*\*",     lambda m: "<strong>" + esc(m.group(1)) + "</strong>", s)
+    s = re.sub(r"\*([^*\n]+)\*",     lambda m: "<em>" + esc(m.group(1)) + "</em>", s)
+
+    # Block elements using inlineMd for their content
+    s = re.sub(r"^### (.+)$", lambda m: "<h3>" + inline_md(m.group(1)) + "</h3>", s, flags=re.M)
+    s = re.sub(r"^## (.+)$",  lambda m: "<h2>" + inline_md(m.group(1)) + "</h2>", s, flags=re.M)
+    s = re.sub(r"^# (.+)$",   lambda m: "<h1>" + inline_md(m.group(1)) + "</h1>", s, flags=re.M)
+    s = re.sub(r"^---+$", "<hr>", s, flags=re.M)
+    s = re.sub(r"^> (.+)$", lambda m: "<blockquote>" + inline_md(m.group(1)) + "</blockquote>", s, flags=re.M)
+
+    def handle_ul(block):
+        lines = block.strip().split("\n")
+        out = "<ul>"
+        for l in lines:
+            indent = bool(re.match(r"^ {2,}", l))
+            text = re.sub(r"^ {0,4}[-*+] ", "", l)
+            style = ' style="margin-left:16px"' if indent else ""
+            out += f"<li{style}>{inline_md(text)}</li>"
+        return out + "</ul>"
+
+    s = re.sub(r"((?:^(?:  )?[-*+] .+\n?)+)", lambda m: handle_ul(m.group()), s, flags=re.M)
+
+    def handle_ol(block):
+        lines = block.strip().split("\n")
+        out = "<ol>"
+        for l in lines:
+            text = re.sub(r"^ {0,4}\d+\. ", "", l)
+            out += f"<li>{inline_md(text)}</li>"
+        return out + "</ol>"
+
+    s = re.sub(r"((?:^(?:  )?\d+\. .+\n?)+)", lambda m: handle_ol(m.group()), s, flags=re.M)
+
+    # Safety net: escape unknown tags in remaining text
+    s = re.sub(r"</?[a-zA-Z][^>]*>", lambda m: m.group() if SAFE_TAGS.match(m.group()) else esc(m.group()), s)
+
+    # Paragraph wrap
+    parts = s.split("\n\n")
+    def wrap(p):
+        p = p.strip()
+        if not p: return ""
+        if re.match(r"^<(h[1-6]|ul|ol|pre|hr|blockquote)", p): return p
+        return "<p>" + p.replace("\n", "<br>") + "</p>"
+    s = "\n".join(wrap(p) for p in parts)
+    return s
+
+
+# ── Static analysis: verify key structures exist in ui.js ────────────────────
+
+def test_render_md_pre_pass_converts_strong(cleanup_test_sessions):
+    """ui.js renderMd() must have pre-pass that converts <strong> to **."""
+    src = REPO_ROOT / "static" / "ui.js"
+    code = src.read_text()
+    assert "<strong>" in code and "**" in code, "pre-pass for <strong> not found"
+    # Verify the specific conversion pattern
+    assert re.search(r"<strong>.*?\*\*", code, re.S), \
+        "renderMd pre-pass should convert <strong>...</strong> to **...**"
+
+
+def test_render_md_has_safety_net(cleanup_test_sessions):
+    """ui.js must have a safety-net that escapes unknown HTML tags after the pipeline."""
+    src = REPO_ROOT / "static" / "ui.js"
+    code = src.read_text()
+    assert "SAFE_TAGS" in code, "SAFE_TAGS allowlist regex not found in ui.js"
+    assert "esc(tag)" in code, "safety-net esc(tag) call not found in ui.js"
+
+
+def test_render_md_stashes_code_blocks(cleanup_test_sessions):
+    """ui.js pre-pass must stash code blocks before replacing safe HTML tags."""
+    src = REPO_ROOT / "static" / "ui.js"
+    code = src.read_text()
+    assert "fence_stash" in code, "fence_stash not found in renderMd pre-pass"
+
+
+def test_render_md_handles_br_tag(cleanup_test_sessions):
+    """ui.js must convert <br> to newline in pre-pass."""
+    src = REPO_ROOT / "static" / "ui.js"
+    code = src.read_text()
+    assert re.search(r"<br\\s\*", code) or "<br" in code, "<br> handling not found"
+
+
+def test_render_md_no_placeholder_remnants(cleanup_test_sessions):
+    """Old Unicode placeholder approach (\\uE001-\\uE005) must be gone."""
+    src = REPO_ROOT / "static" / "ui.js"
+    code = src.read_text()
+    for old_ph in ["\\uE001", "\\uE002", "\\uE003", "\\uE004", "\\uE005"]:
+        assert old_ph not in code, \
+            f"Old placeholder {old_ph} still present — broken implementation not cleaned up"
+
+
+def test_render_md_safe_tag_allowlist_complete(cleanup_test_sessions):
+    """SAFE_TAGS allowlist must include all tags the pipeline emits."""
+    src = REPO_ROOT / "static" / "ui.js"
+    code = src.read_text()
+    required = ["strong", "em", "code", "pre", "ul", "ol", "li",
+                "table", "blockquote", "hr", "br", "a", "div"]
+    safe_tags_match = re.search(r"SAFE_TAGS\s*=\s*/(.+?)/i", code)
+    assert safe_tags_match, "SAFE_TAGS regex not found"
+    pattern = safe_tags_match.group(1)
+    for tag in required:
+        assert tag in pattern, f"Tag '{tag}' missing from SAFE_TAGS allowlist"
+
+
+# ── Behavioural: renderMd logic via Python mirror ─────────────────────────────
+
+def test_render_md_markdown_bold(cleanup_test_sessions):
+    """**word** markdown renders as <strong>word</strong>."""
+    out = render_md("Hello **world**")
+    assert "<strong>world</strong>" in out
+
+
+def test_render_md_html_strong_passthrough(cleanup_test_sessions):
+    """<strong>word</strong> in AI output renders as bold."""
+    out = render_md("Hello <strong>world</strong>")
+    assert "<strong>world</strong>" in out
+
+
+def test_render_md_html_b_tag(cleanup_test_sessions):
+    """<b>word</b> renders as <strong>word</strong>."""
+    out = render_md("Hello <b>world</b>")
+    assert "<strong>world</strong>" in out
+
+
+def test_render_md_html_em_passthrough(cleanup_test_sessions):
+    """<em>word</em> renders as italic."""
+    out = render_md("Hello <em>world</em>")
+    assert "<em>world</em>" in out
+
+
+def test_render_md_html_i_tag(cleanup_test_sessions):
+    """<i>word</i> renders as <em>word</em>."""
+    out = render_md("Hello <i>word</i>")
+    assert "<em>word</em>" in out
+
+
+def test_render_md_html_code_passthrough(cleanup_test_sessions):
+    """<code>text</code> renders as inline code."""
+    out = render_md("use <code>print()</code>")
+    assert "<code>print()</code>" in out
+
+
+def test_render_md_html_br_becomes_newline(cleanup_test_sessions):
+    """<br> in AI output becomes a newline (rendered as <br> inside <p> later)."""
+    out = render_md("line one<br>line two")
+    assert "line one\nline two" in out or "line one<br>line two" in out
+
+
+def test_render_md_mixed_markdown_and_html(cleanup_test_sessions):
+    """Markdown and HTML formatting can coexist in the same response."""
+    out = render_md("**markdown** and <strong>html</strong>")
+    assert "<strong>markdown</strong>" in out
+    assert "<strong>html</strong>" in out
+
+
+def test_render_md_html_strong_in_list_item(cleanup_test_sessions):
+    """THE SCREENSHOT BUG: <strong> tags inside list items must render as bold,
+    not as escaped literal text like &lt;strong&gt;."""
+    out = render_md(
+        "- <strong>All items</strong> get `border-radius: 0 8px 8px 0`\n"
+        "- <strong>Active item</strong> uses <code>#e8a030</code>\n"
+        "- <strong>Project items</strong> show their color\n"
+        "- <strong>Regular items</strong> stay muted"
+    )
+    assert "&lt;strong&gt;" not in out, \
+        "Escaped <strong> literal found in list output — bold not rendering"
+    assert "<strong>All items</strong>" in out
+    assert "<strong>Active item</strong>" in out
+    assert "<code>border-radius: 0 8px 8px 0</code>" in out
+    assert "<code>#e8a030</code>" in out
+
+
+def test_render_md_exact_screenshot_content(cleanup_test_sessions):
+    """Exact text from the ui-changes-unrendered-html-tags.png screenshot.
+    This is the canonical regression test for the inlineMd fix.
+    All four bullet points must render <strong> and <code> as HTML, not literal text."""
+    out = render_md(
+        "- <strong>All items</strong> now have <code>border-radius: 0 8px 8px 0</code>"
+        " \u2014 straight left edge everywhere, rounded on the right\n"
+        "- <strong>Active item</strong> is now gold/amber (<code>#e8a030</code>)"
+        " \u2014 same warm gold used in the logo \u2014 instead of blue,"
+        " so it stands out distinctly from everything else\n"
+        "- <strong>Project items</strong> still show their project color on the left"
+        " border, but only when they're not the active item (active always wins with gold)\n"
+        "- <strong>Regular items</strong> (no project) still have no left border color"
+    )
+    # None of the safe tags should appear as literal escaped text
+    assert "&lt;strong&gt;" not in out, \
+        "Literal &lt;strong&gt; found — <strong> is not rendering as bold"
+    assert "&lt;/strong&gt;" not in out, \
+        "Literal &lt;/strong&gt; found — closing tag is not rendering"
+    assert "&lt;code&gt;" not in out, \
+        "Literal &lt;code&gt; found — <code> is not rendering as inline code"
+    # Each item's bold label must render correctly
+    assert "<strong>All items</strong>" in out
+    assert "<strong>Active item</strong>" in out
+    assert "<strong>Project items</strong>" in out
+    assert "<strong>Regular items</strong>" in out
+    # The code spans in items 1 and 2 must render correctly
+    assert "<code>border-radius: 0 8px 8px 0</code>" in out
+    assert "<code>#e8a030</code>" in out
+    # The surrounding prose text must be preserved
+    assert "straight left edge everywhere" in out
+    assert "same warm gold used in the logo" in out
+    assert "active always wins with gold" in out
+
+
+def test_render_md_markdown_bold_in_list_item(cleanup_test_sessions):
+    """**bold** markdown inside list items must render as <strong>."""
+    out = render_md("- **First** item\n- **Second** item with `code`")
+    assert "<strong>First</strong>" in out
+    assert "<strong>Second</strong>" in out
+    assert "<code>code</code>" in out
+
+
+def test_render_md_html_strong_in_blockquote(cleanup_test_sessions):
+    """<strong> inside blockquote must render as bold."""
+    out = render_md("> <strong>Note:</strong> pay attention")
+    assert "&lt;strong&gt;" not in out
+    assert "<strong>Note:</strong>" in out
+
+
+def test_render_md_html_strong_in_heading(cleanup_test_sessions):
+    """<strong> inside a heading must render as bold."""
+    out = render_md("## <strong>Important</strong> Section")
+    assert "&lt;strong&gt;" not in out
+    assert "<strong>Important</strong>" in out
+
+
+def test_render_md_xss_in_list_still_blocked(cleanup_test_sessions):
+    """XSS attempts in list items must still be escaped."""
+    out = render_md("- <img src=x onerror=alert(1)> bad")
+    assert "<img" not in out
+    assert "&lt;img" in out
+
+
+def test_render_md_xss_in_blockquote_still_blocked(cleanup_test_sessions):
+    """XSS in blockquote must still be escaped."""
+    out = render_md("> <script>alert(1)</script>")
+    assert "<script>" not in out
+    assert "&lt;script" in out
+
+
+def test_render_md_code_span_in_list_protected(cleanup_test_sessions):
+    """Backtick code span in list item must escape its content."""
+    out = render_md("- Use `<br>` for breaks")
+    assert "<code>&lt;br&gt;</code>" in out
+
+
+def test_render_md_code_block_protects_html(cleanup_test_sessions):
+    """HTML inside a backtick code span must NOT be converted — shown as literal."""
+    out = render_md("keep `<strong>literal</strong>` safe")
+    assert "&lt;strong&gt;" in out, "HTML inside code span should be escaped"
+    assert "<strong>literal</strong>" not in out, "HTML inside code span should NOT render as bold"
+
+
+def test_render_md_fenced_code_protects_html(cleanup_test_sessions):
+    """HTML inside a fenced code block must not be converted by the pre-pass.
+    The fenced block is stashed before tag replacement runs, so the raw HTML
+    is preserved intact for the pipeline's esc() to escape when rendering
+    the <pre><code> block. We verify the stash/restore mechanism works by
+    checking the content is unchanged after the pre-pass (i.e. still contains
+    the original tag text, not converted to **not bold**)."""
+    src = "```\n<strong>not bold</strong>\n```"
+    out = render_md(src)
+    # Pre-pass stash preserves the raw content -- it should NOT have been
+    # converted to **not bold** (which would render as bold outside the fence)
+    assert "**not bold**" not in out, \
+        "Fenced code content was incorrectly converted to markdown by the pre-pass"
+    # The raw content should still be present (stash/restore worked)
+    assert "<strong>not bold</strong>" in out or "&lt;strong&gt;" in out, \
+        "Fenced code content was lost after stash/restore"
+
+
+# ── Security: XSS must be blocked ─────────────────────────────────────────────
+
+def test_render_md_xss_img_tag_escaped(cleanup_test_sessions):
+    """<img src=x onerror=alert(1)> must be HTML-escaped, not rendered."""
+    out = render_md("<img src=x onerror=alert(1)>")
+    assert "<img" not in out, "Raw <img> tag must not appear in output"
+    assert "&lt;img" in out, "<img> must be HTML-escaped"
+
+
+def test_render_md_xss_script_tag_escaped(cleanup_test_sessions):
+    """<script>alert(1)</script> must be HTML-escaped."""
+    out = render_md("<script>alert(1)</script>")
+    assert "<script>" not in out, "Raw <script> tag must not appear in output"
+    assert "&lt;script" in out, "<script> must be HTML-escaped"
+
+
+def test_render_md_xss_iframe_escaped(cleanup_test_sessions):
+    """<iframe> must be HTML-escaped."""
+    out = render_md("<iframe src='evil.com'></iframe>")
+    assert "<iframe" not in out
+    assert "&lt;iframe" in out
+
+
+def test_render_md_xss_svg_onerror_escaped(cleanup_test_sessions):
+    """<svg onload=...> must be HTML-escaped."""
+    out = render_md("<svg onload=alert(1)>")
+    assert "<svg" not in out
+    assert "&lt;svg" in out
+
+
+def test_render_md_xss_in_bold_text_escaped(cleanup_test_sessions):
+    """**<img onerror=...>** — XSS inside markdown bold must be escaped."""
+    out = render_md("**<img src=x onerror=alert(1)>**")
+    assert "<img" not in out, "XSS inside **bold** must be escaped"
+    assert "&lt;img" in out
+
+
+def test_render_md_xss_in_html_strong_escaped(cleanup_test_sessions):
+    """<strong><img ...></strong> — nested XSS inside HTML strong must be escaped."""
+    out = render_md("<strong><img src=x onerror=alert(1)></strong>")
+    # <strong> converts to ** which then escapes the inner content via esc()
+    assert "<img" not in out, "XSS nested inside <strong> must be escaped"
+
+
+def test_render_md_xss_object_tag_escaped(cleanup_test_sessions):
+    """<object data=...> must be HTML-escaped."""
+    out = render_md("<object data='evil.swf'></object>")
+    assert "<object" not in out
+    assert "&lt;object" in out
+
+
+# ── Sprint 16 sidebar: static structure checks ───────────────────────────────
+
+# ── Exhaustive inlineMd / renderMd edge-case tests ───────────────────────────
+
+# --- Unordered list variants ---
+
+def test_list_bold_only(cleanup_test_sessions):
+    """Single bold word in list item."""
+    out = render_md("- **bold**")
+    assert "<strong>bold</strong>" in out
+    assert "&lt;" not in out
+
+def test_list_italic_only(cleanup_test_sessions):
+    """Single italic word in list item."""
+    out = render_md("- *italic*")
+    assert "<em>italic</em>" in out
+
+def test_list_code_only(cleanup_test_sessions):
+    """Single code span in list item."""
+    out = render_md("- `code`")
+    assert "<code>code</code>" in out
+
+def test_list_bold_and_code_mixed(cleanup_test_sessions):
+    """Bold and code together in one list item."""
+    out = render_md("- **run** `pip install foo`")
+    assert "<strong>run</strong>" in out
+    assert "<code>pip install foo</code>" in out
+
+def test_list_html_strong_and_code_mixed(cleanup_test_sessions):
+    """HTML <strong> and <code> together — the exact screenshot scenario."""
+    out = render_md("- <strong>Key</strong>: use <code>value</code>")
+    assert "<strong>Key</strong>" in out
+    assert "<code>value</code>" in out
+    assert "&lt;strong&gt;" not in out
+    assert "&lt;code&gt;" not in out
+
+def test_list_html_em(cleanup_test_sessions):
+    """HTML <em> in list item renders as italic."""
+    out = render_md("- <em>emphasized</em> text")
+    assert "<em>emphasized</em>" in out
+    assert "&lt;em&gt;" not in out
+
+def test_list_html_b_tag(cleanup_test_sessions):
+    """HTML <b> in list item renders as bold."""
+    out = render_md("- <b>bold via b tag</b>")
+    assert "<strong>bold via b tag</strong>" in out
+    assert "&lt;b&gt;" not in out
+
+def test_list_html_i_tag(cleanup_test_sessions):
+    """HTML <i> in list item renders as italic."""
+    out = render_md("- <i>italic via i tag</i>")
+    assert "<em>italic via i tag</em>" in out
+    assert "&lt;i&gt;" not in out
+
+def test_list_multiple_items_each_formatted(cleanup_test_sessions):
+    """Multiple list items each with different formatting."""
+    out = render_md(
+        "- **bold item**\n"
+        "- *italic item*\n"
+        "- `code item`\n"
+        "- plain item"
+    )
+    assert "<strong>bold item</strong>" in out
+    assert "<em>italic item</em>" in out
+    assert "<code>code item</code>" in out
+    assert "<li>plain item</li>" in out
+
+def test_list_item_bold_mid_sentence(cleanup_test_sessions):
+    """Bold in middle of a list item sentence."""
+    out = render_md("- Set the **timeout** to 30 seconds")
+    assert "<strong>timeout</strong>" in out
+    assert "Set the" in out
+    assert "to 30 seconds" in out
+
+def test_list_item_multiple_bold_spans(cleanup_test_sessions):
+    """Multiple bold spans in one list item."""
+    out = render_md("- **A** and **B** are both important")
+    assert "<strong>A</strong>" in out
+    assert "<strong>B</strong>" in out
+
+def test_ordered_list_bold(cleanup_test_sessions):
+    """Bold text inside ordered list items."""
+    out = render_md("1. **First** step\n2. **Second** step\n3. Plain step")
+    assert "<ol>" in out
+    assert "<strong>First</strong>" in out
+    assert "<strong>Second</strong>" in out
+    assert "<li>Plain step</li>" in out
+
+def test_ordered_list_html_strong(cleanup_test_sessions):
+    """HTML <strong> inside ordered list items renders correctly."""
+    out = render_md("1. <strong>Install</strong> the package\n2. <strong>Configure</strong> the settings")
+    assert "<ol>" in out
+    assert "<strong>Install</strong>" in out
+    assert "<strong>Configure</strong>" in out
+    assert "&lt;strong&gt;" not in out
+
+def test_ordered_list_code_spans(cleanup_test_sessions):
+    """Code spans inside ordered list items."""
+    out = render_md("1. Run `npm install`\n2. Run `npm start`")
+    assert "<code>npm install</code>" in out
+    assert "<code>npm start</code>" in out
+
+def test_indented_list_item_bold(cleanup_test_sessions):
+    """Bold inside indented (nested) list item."""
+    out = render_md("- top level\n  - **nested bold**")
+    assert "<strong>nested bold</strong>" in out
+    assert "margin-left:16px" in out
+
+# --- Blockquote variants ---
+
+def test_blockquote_plain(cleanup_test_sessions):
+    """Plain blockquote wraps in <blockquote>."""
+    out = render_md("> simple quote")
+    assert "<blockquote>simple quote</blockquote>" in out
+
+def test_blockquote_bold(cleanup_test_sessions):
+    """**bold** inside blockquote renders correctly."""
+    out = render_md("> **important** note")
+    assert "<strong>important</strong>" in out
+
+def test_blockquote_html_strong(cleanup_test_sessions):
+    """<strong> inside blockquote renders as bold."""
+    out = render_md("> <strong>Warning:</strong> read this")
+    assert "<strong>Warning:</strong>" in out
+    assert "&lt;strong&gt;" not in out
+
+def test_blockquote_code_span(cleanup_test_sessions):
+    """Code span inside blockquote renders correctly."""
+    out = render_md("> Use `git commit` to save")
+    assert "<code>git commit</code>" in out
+
+def test_blockquote_mixed_formatting(cleanup_test_sessions):
+    """Mixed bold and code in blockquote."""
+    out = render_md("> **Note:** run `pip install foo` first")
+    assert "<strong>Note:</strong>" in out
+    assert "<code>pip install foo</code>" in out
+
+def test_blockquote_xss_blocked(cleanup_test_sessions):
+    """XSS in blockquote content must be escaped."""
+    out = render_md("> <img src=x onerror=alert(1)>")
+    assert "&lt;img" in out
+    assert "<img" not in out
+
+# --- Heading variants ---
+
+def test_heading_h1_bold(cleanup_test_sessions):
+    """Bold inside h1 renders correctly."""
+    out = render_md("# **Main** Title")
+    assert "<h1><strong>Main</strong> Title</h1>" in out
+
+def test_heading_h2_html_strong(cleanup_test_sessions):
+    """HTML <strong> inside h2 renders correctly."""
+    out = render_md("## <strong>Section</strong> Name")
+    assert "<h2><strong>Section</strong> Name</h2>" in out
+    assert "&lt;strong&gt;" not in out
+
+def test_heading_h3_code(cleanup_test_sessions):
+    """Code span inside h3 renders correctly."""
+    out = render_md("### The `renderMd` function")
+    assert "<h3>The <code>renderMd</code> function</h3>" in out
+
+def test_heading_xss_blocked(cleanup_test_sessions):
+    """XSS attempt in heading must be escaped."""
+    out = render_md("## <script>alert(1)</script>")
+    assert "<script>" not in out
+    assert "&lt;script" in out
+
+# --- Paragraph / top-level formatting ---
+
+def test_paragraph_bold_renders(cleanup_test_sessions):
+    """Bold in a plain paragraph renders correctly."""
+    out = render_md("The **quick brown fox** jumps.")
+    assert "<strong>quick brown fox</strong>" in out
+
+def test_paragraph_html_strong_renders(cleanup_test_sessions):
+    """HTML <strong> in a plain paragraph renders correctly."""
+    out = render_md("The <strong>quick brown fox</strong> jumps.")
+    assert "<strong>quick brown fox</strong>" in out
+    assert "&lt;strong&gt;" not in out
+
+def test_paragraph_html_code_renders(cleanup_test_sessions):
+    """HTML <code> in a plain paragraph renders correctly."""
+    out = render_md("Call <code>foo()</code> to start.")
+    assert "<code>foo()</code>" in out
+    assert "&lt;code&gt;" not in out
+
+def test_paragraph_br_creates_line_break(cleanup_test_sessions):
+    """<br> in paragraph becomes a line break inside <p>."""
+    out = render_md("Line one<br>Line two")
+    # br converts to \n which inside <p> becomes <br>
+    assert "Line one" in out and "Line two" in out
+
+def test_multiple_paragraphs_separated(cleanup_test_sessions):
+    """Double newline creates separate <p> elements."""
+    out = render_md("First paragraph.\n\nSecond paragraph.")
+    assert out.count("<p>") == 2
+
+# --- Table variants ---
+
+def test_table_structure_in_ui_js(cleanup_test_sessions):
+    """ui.js must contain table rendering logic with thead/tbody structure."""
+    src = (REPO_ROOT / "static" / "ui.js").read_text()
+    assert "<table>" in src or "table>" in src, "table rendering not found in ui.js"
+    assert "thead" in src, "thead not found in table renderer"
+    assert "tbody" in src, "tbody not found in table renderer"
+    assert "parseRow" in src, "parseRow helper not found in table renderer"
+
+# --- br tag specifically ---
+
+def test_br_in_list_item(cleanup_test_sessions):
+    """<br> inside a list item becomes a newline."""
+    out = render_md("- Line one<br>Line two")
+    assert "Line one" in out
+    assert "Line two" in out
+
+def test_br_self_closing_in_paragraph(cleanup_test_sessions):
+    """<br/> self-closing form is also handled."""
+    out = render_md("Before<br/>After")
+    assert "Before" in out and "After" in out
+
+# --- No double-escaping ---
+
+def test_no_double_escaping_ampersand(cleanup_test_sessions):
+    """A literal & in text must become &amp; exactly once, not &amp;amp;."""
+    out = render_md("foo & bar")
+    assert "&amp;amp;" not in out
+    assert "&amp;" in out or "foo & bar" in out  # either fine (paragraph wrap may not escape)
+
+def test_no_double_escaping_lt_in_code(cleanup_test_sessions):
+    """< inside a code span must become &lt; exactly once."""
+    out = render_md("`a < b`")
+    assert "&lt;lt;" not in out
+    assert "&lt;" in out
+
+def test_strong_text_not_double_escaped(cleanup_test_sessions):
+    """Content of <strong> must not be double-escaped."""
+    out = render_md("<strong>hello & world</strong>")
+    # The & inside strong content should be escaped once
+    assert "&amp;amp;" not in out
+    assert "<strong>" in out
+
+# --- inlineMd helper present in source ---
+
+def test_inline_md_helper_in_ui_js(cleanup_test_sessions):
+    """ui.js must define inlineMd() helper function."""
+    src = (REPO_ROOT / "static" / "ui.js").read_text()
+    assert "function inlineMd(" in src, "inlineMd() helper not found in ui.js"
+
+def test_inline_md_used_in_list_handler(cleanup_test_sessions):
+    """List handler in ui.js must call inlineMd() not esc() for item text."""
+    src = (REPO_ROOT / "static" / "ui.js").read_text()
+    # Find the list block handler
+    ul_idx = src.find("html+='<ul>'") or src.find('html+=`<ul>`') or src.find("let html='<ul>'")
+    assert ul_idx >= 0 or "inlineMd(text)" in src, "inlineMd not called in list handler"
+    # Verify inlineMd is called, not bare esc
+    assert "inlineMd(text)" in src, "inlineMd(text) call not found — list items may not render formatting"
+
+def test_inline_md_used_in_blockquote_handler(cleanup_test_sessions):
+    """Blockquote handler in ui.js must call inlineMd() not esc() for content."""
+    src = (REPO_ROOT / "static" / "ui.js").read_text()
+    assert "inlineMd(t)" in src, "inlineMd not called in blockquote/heading handler"
+
+
+def test_sessions_js_has_svg_icons(cleanup_test_sessions):
+    """sessions.js must define ICONS object with SVG strings for sidebar buttons."""
+    src = REPO_ROOT / "static" / "sessions.js"
+    code = src.read_text()
+    assert "const ICONS=" in code or "const ICONS =" in code, "ICONS constant not found"
+    for icon in ["pin", "folder", "archive", "trash", "dup"]:
+        assert icon + ":" in code or f"'{icon}'" in code, f"ICONS.{icon} not found"
+    assert "<svg" in code, "SVG content not found in ICONS"
+
+
+def test_sessions_js_has_overlay_actions(cleanup_test_sessions):
+    """sessions.js must use .session-actions overlay div for action buttons."""
+    src = REPO_ROOT / "static" / "sessions.js"
+    code = src.read_text()
+    assert "session-actions" in code, ".session-actions overlay not found in sessions.js"
+
+
+def test_style_css_has_session_actions_overlay(cleanup_test_sessions):
+    """style.css must define .session-actions with position:absolute."""
+    src = REPO_ROOT / "static" / "style.css"
+    code = src.read_text()
+    assert ".session-actions" in code, ".session-actions not found in style.css"
+    assert "position:absolute" in code or "position: absolute" in code, \
+        ".session-actions must use position:absolute for overlay"
+
+
+def test_style_css_active_session_uses_gold(cleanup_test_sessions):
+    """Active session style should use gold/amber color (#e8a030) not just blue."""
+    src = REPO_ROOT / "static" / "style.css"
+    code = src.read_text()
+    assert "#e8a030" in code, \
+        "Active session gold color (#e8a030) not found in style.css"
+
+
+def test_sessions_js_active_skips_project_border(cleanup_test_sessions):
+    """sessions.js must not override active session border-left with project color."""
+    src = REPO_ROOT / "static" / "sessions.js"
+    code = src.read_text()
+    # The fix: only set borderLeftColor if NOT the active session
+    assert "isActive" in code, "isActive check not found in sessions.js"
+    assert "borderLeftColor" in code, "borderLeftColor not found in sessions.js"

tests/test_sprint17.py

@@ -0,0 +1,96 @@
+"""
+Sprint 17 Tests: send_key setting, commands.js static file, workspace subdir listing.
+"""
+import json, urllib.error, urllib.request
+
+BASE = "http://127.0.0.1:8788"
+
+
+def get(path):
+    with urllib.request.urlopen(BASE + path, timeout=10) as r:
+        return json.loads(r.read()), r.status
+
+
+def post(path, body=None):
+    data = json.dumps(body or {}).encode()
+    req = urllib.request.Request(BASE + path, data=data,
+                                headers={"Content-Type": "application/json"})
+    try:
+        with urllib.request.urlopen(req, timeout=10) as r:
+            return json.loads(r.read()), r.status
+    except urllib.error.HTTPError as e:
+        return json.loads(e.read()), e.code
+
+
+def make_session(created_list):
+    d, _ = post("/api/session/new", {})
+    sid = d["session"]["session_id"]
+    created_list.append(sid)
+    return sid, d["session"]
+
+
+# ── Settings: send_key ──────────────────────────────────────────────────────
+
+def test_settings_send_key_default():
+    """GET /api/settings returns send_key with default value 'enter'."""
+    data, status = get("/api/settings")
+    assert status == 200
+    assert data.get("send_key") == "enter"
+
+
+def test_settings_save_send_key():
+    """POST /api/settings with send_key persists and round-trips."""
+    try:
+        # Save ctrl+enter
+        _, status = post("/api/settings", {"send_key": "ctrl+enter"})
+        assert status == 200
+        # Verify it persisted
+        data, _ = get("/api/settings")
+        assert data["send_key"] == "ctrl+enter"
+    finally:
+        # Always restore default
+        post("/api/settings", {"send_key": "enter"})
+    data, _ = get("/api/settings")
+    assert data["send_key"] == "enter"
+
+
+def test_settings_invalid_send_key_rejected():
+    """POST /api/settings with invalid send_key value is silently ignored."""
+    # Set a known good value first
+    post("/api/settings", {"send_key": "enter"})
+    # Try to set an invalid value
+    data, status = post("/api/settings", {"send_key": "invalid_value"})
+    assert status == 200
+    # Should still be 'enter' (invalid value ignored)
+    assert data["send_key"] == "enter"
+
+
+def test_settings_unknown_key_ignored():
+    """POST /api/settings ignores unknown keys."""
+    data, status = post("/api/settings", {"unknown_key": "value", "send_key": "enter"})
+    assert status == 200
+    assert "unknown_key" not in data
+
+
+# ── Static file: commands.js ────────────────────────────────────────────────
+
+def test_static_commands_js_served():
+    """GET /static/commands.js returns 200 and contains COMMANDS registry."""
+    req = urllib.request.Request(BASE + "/static/commands.js")
+    with urllib.request.urlopen(req, timeout=10) as r:
+        body = r.read().decode()
+        assert r.status == 200
+        assert "COMMANDS" in body
+        assert "executeCommand" in body
+
+
+# ── Workspace: subdir listing ───────────────────────────────────────────────
+
+def test_list_workspace_root():
+    """GET /api/list with path=. returns entries for workspace root."""
+    created = []
+    sid, _ = make_session(created)
+    data, status = get(f"/api/list?session_id={sid}&path=.")
+    assert status == 200
+    assert "entries" in data
+    assert isinstance(data["entries"], list)

tests/test_sprint19.py

@@ -0,0 +1,118 @@
+"""
+Sprint 19 Tests: auth/login, security headers, request size limit.
+"""
+import json, urllib.error, urllib.request
+
+BASE = "http://127.0.0.1:8788"
+
+
+def get(path, headers=None):
+    req = urllib.request.Request(BASE + path)
+    if headers:
+        for k, v in headers.items():
+            req.add_header(k, v)
+    with urllib.request.urlopen(req, timeout=10) as r:
+        return json.loads(r.read()), r.status, dict(r.headers)
+
+
+def post(path, body=None, headers=None):
+    data = json.dumps(body or {}).encode()
+    req = urllib.request.Request(BASE + path, data=data,
+                                headers={"Content-Type": "application/json"})
+    if headers:
+        for k, v in headers.items():
+            req.add_header(k, v)
+    try:
+        with urllib.request.urlopen(req, timeout=10) as r:
+            return json.loads(r.read()), r.status, dict(r.headers)
+    except urllib.error.HTTPError as e:
+        return json.loads(e.read()), e.code, dict(e.headers)
+
+
+# ── Auth status (no password configured in test env) ──────────────────────
+
+def test_auth_status_disabled():
+    """Auth should be disabled by default (no password set)."""
+    d, status, _ = get("/api/auth/status")
+    assert status == 200
+    assert d["auth_enabled"] is False
+
+
+def test_login_when_auth_disabled():
+    """Login should succeed trivially when auth is not enabled."""
+    d, status, _ = post("/api/auth/login", {"password": "anything"})
+    assert status == 200
+    assert d["ok"] is True
+
+
+def test_all_routes_accessible_without_auth():
+    """When auth is disabled, all routes should work without cookies."""
+    d, status, _ = get("/api/sessions")
+    assert status == 200
+    assert "sessions" in d
+
+
+def test_login_page_served():
+    """GET /login should return the login page HTML."""
+    req = urllib.request.Request(BASE + "/login")
+    with urllib.request.urlopen(req, timeout=10) as r:
+        html = r.read().decode()
+        assert r.status == 200
+        assert "Sign in" in html
+        assert "Hermes" in html
+
+
+# ── Security headers ─────────────────────────────────────────────────────
+
+def test_security_headers_on_json():
+    """JSON responses should include security headers."""
+    d, status, headers = get("/api/auth/status")
+    assert status == 200
+    assert headers.get("X-Content-Type-Options") == "nosniff"
+    assert headers.get("X-Frame-Options") == "DENY"
+    assert headers.get("Referrer-Policy") == "same-origin"
+
+
+def test_security_headers_on_health():
+    """Health endpoint should include security headers."""
+    d, status, headers = get("/health")
+    assert status == 200
+    assert headers.get("X-Content-Type-Options") == "nosniff"
+
+
+def test_cache_control_no_store():
+    """API responses should have Cache-Control: no-store."""
+    d, status, headers = get("/api/sessions")
+    assert headers.get("Cache-Control") == "no-store"
+
+
+# ── Settings password field ──────────────────────────────────────────────
+
+def test_settings_password_hash_not_exposed():
+    """GET /api/settings must never expose the stored password hash."""
+    d, status, _ = get("/api/settings")
+    assert status == 200
+    assert "password_hash" not in d  # security: never send hash to client
+
+
+def test_settings_save_preserves_other_fields():
+    """Saving settings should not break existing fields."""
+    # Get current settings
+    current, _, _ = get("/api/settings")
+    # Save with just send_key
+    d, status, _ = post("/api/settings", {"send_key": "enter"})
+    assert status == 200
+    # Verify other fields still present
+    updated, _, _ = get("/api/settings")
+    assert "default_model" in updated
+    assert "default_workspace" in updated
+
+
+def test_settings_password_hash_not_directly_settable():
+    """POST /api/settings with password_hash must not overwrite the stored hash."""
+    # Attempt to set a raw hash directly (attack vector)
+    post("/api/settings", {"password_hash": "deadbeef" * 8})
+    # Settings response must not expose it regardless
+    updated, status, _ = get("/api/settings")
+    assert status == 200
+    assert "password_hash" not in updated

tests/test_sprint20.py

@@ -0,0 +1,422 @@
+"""
+Sprint 20 Tests: Voice input (mic button) via Web Speech API.
+
+These tests verify the static assets contain the correct HTML structure,
+CSS rules, and JS logic for the mic feature — all of which runs purely in
+the browser with no server-side component.
+"""
+import re
+import urllib.request
+import json
+
+BASE = "http://127.0.0.1:8788"
+
+
+def get_text(path):
+    with urllib.request.urlopen(BASE + path, timeout=10) as r:
+        return r.read().decode(), r.status
+
+
+# ── index.html ────────────────────────────────────────────────────────────
+
+
+def test_mic_button_present_in_html():
+    """index.html must contain the mic button with id='btnMic'."""
+    html, status = get_text("/")
+    assert status == 200
+    assert 'id="btnMic"' in html
+
+
+def test_mic_button_has_mic_btn_class():
+    """btnMic must carry the mic-btn CSS class for styling hooks."""
+    html, _ = get_text("/")
+    assert 'class="icon-btn mic-btn"' in html
+
+
+def test_mic_button_hidden_by_default():
+    """btnMic starts hidden (display:none) — JS shows it only if supported."""
+    html, _ = get_text("/")
+    # The button element should have display:none in its style attribute
+    assert 'id="btnMic"' in html
+    btn_match = re.search(r'id="btnMic"[^>]*>', html)
+    assert btn_match, "btnMic element not found"
+    assert 'display:none' in btn_match.group(0)
+
+
+def test_mic_button_has_title():
+    """btnMic should have a descriptive title for accessibility."""
+    html, _ = get_text("/")
+    btn_match = re.search(r'id="btnMic"[^>]*>', html)
+    assert btn_match
+    assert 'title=' in btn_match.group(0)
+
+
+def test_mic_status_div_present():
+    """index.html must contain the #micStatus listening indicator."""
+    html, _ = get_text("/")
+    assert 'id="micStatus"' in html
+
+
+def test_mic_status_hidden_by_default():
+    """#micStatus starts hidden — only shown during active recording."""
+    html, _ = get_text("/")
+    status_match = re.search(r'id="micStatus"[^>]*>', html)
+    assert status_match, "#micStatus element not found"
+    assert 'display:none' in status_match.group(0)
+
+
+def test_mic_status_has_mic_dot():
+    """#micStatus must contain a .mic-dot element for the pulse animation."""
+    html, _ = get_text("/")
+    # mic-dot should appear after micStatus
+    idx_status = html.find('id="micStatus"')
+    idx_dot = html.find('mic-dot', idx_status)
+    assert idx_status != -1 and idx_dot != -1
+    assert idx_dot > idx_status
+
+
+def test_mic_status_has_listening_text():
+    """#micStatus should display a 'Listening' label."""
+    html, _ = get_text("/")
+    assert 'Listening' in html
+
+
+def test_mic_button_svg_microphone_shape():
+    """btnMic SVG must include the rect (mic body) and path (mic arc)."""
+    html, _ = get_text("/")
+    # Find mic button section
+    btn_start = html.find('id="btnMic"')
+    btn_end = html.find('</button>', btn_start) + len('</button>')
+    btn_html = html[btn_start:btn_end]
+    assert '<rect' in btn_html, "mic SVG missing rect (mic body)"
+    assert '<path' in btn_html, "mic SVG missing path (arc)"
+    assert '<line' in btn_html, "mic SVG missing line (stand)"
+
+
+def test_mic_button_inside_composer_left():
+    """btnMic must be inside .composer-left, next to the attach button."""
+    html, _ = get_text("/")
+    composer_left_start = html.find('class="composer-left"')
+    composer_left_end = html.find('</div>', composer_left_start)
+    section = html[composer_left_start:composer_left_end]
+    assert 'btnAttach' in section
+    assert 'btnMic' in section
+
+
+# ── style.css ────────────────────────────────────────────────────────────
+
+
+def test_mic_btn_css_rule_exists():
+    """style.css must define .mic-btn rule."""
+    css, status = get_text("/static/style.css")
+    assert status == 200
+    assert '.mic-btn' in css
+
+
+def test_mic_btn_recording_state_css():
+    """.mic-btn.recording must be defined for active recording visual state."""
+    css, _ = get_text("/static/style.css")
+    assert '.mic-btn.recording' in css
+
+
+def test_mic_recording_color_red():
+    """.mic-btn.recording must use the red accent color #e94560."""
+    css, _ = get_text("/static/style.css")
+    recording_idx = css.find('.mic-btn.recording')
+    # Find the rule block after the selector
+    brace_open = css.find('{', recording_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert '#e94560' in rule or 'e94560' in rule
+
+
+def test_mic_recording_has_animation():
+    """.mic-btn.recording must use an animation for the pulse effect."""
+    css, _ = get_text("/static/style.css")
+    recording_idx = css.find('.mic-btn.recording')
+    brace_open = css.find('{', recording_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'animation' in rule
+
+
+def test_mic_pulse_keyframes_defined():
+    """@keyframes mic-pulse must be defined for the pulsing animation."""
+    css, _ = get_text("/static/style.css")
+    assert 'mic-pulse' in css
+    assert '@keyframes' in css
+
+
+def test_mic_status_css_rule_exists():
+    """style.css must define .mic-status rule."""
+    css, _ = get_text("/static/style.css")
+    assert '.mic-status' in css
+
+
+def test_mic_dot_css_rule_exists():
+    """style.css must define .mic-dot rule with animation."""
+    css, _ = get_text("/static/style.css")
+    assert '.mic-dot' in css
+    dot_idx = css.find('.mic-dot')
+    brace_open = css.find('{', dot_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'animation' in rule
+
+
+def test_mic_btn_has_transition():
+    """.mic-btn must define a transition for smooth state changes."""
+    css, _ = get_text("/static/style.css")
+    mic_btn_idx = css.find('.mic-btn{')
+    if mic_btn_idx == -1:
+        mic_btn_idx = css.find('.mic-btn ')
+    brace_open = css.find('{', mic_btn_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'transition' in rule
+
+
+# ── boot.js ──────────────────────────────────────────────────────────────
+
+
+def test_boot_js_serves_ok():
+    """boot.js must be served successfully."""
+    _, status = get_text("/static/boot.js")
+    assert status == 200
+
+
+def test_boot_js_speech_recognition_check():
+    """boot.js must check for SpeechRecognition (with webkit fallback)."""
+    js, _ = get_text("/static/boot.js")
+    assert 'SpeechRecognition' in js
+    assert 'webkitSpeechRecognition' in js
+
+
+def test_boot_js_recognition_config():
+    """boot.js must configure recognition.continuous, interimResults, and lang."""
+    js, _ = get_text("/static/boot.js")
+    assert 'recognition.continuous' in js
+    assert 'recognition.interimResults' in js
+    assert 'recognition.lang' in js
+
+
+def test_boot_js_recognition_not_continuous():
+    """recognition.continuous must be false (auto-stop after silence)."""
+    js, _ = get_text("/static/boot.js")
+    assert 'recognition.continuous=false' in js or 'recognition.continuous = false' in js
+
+
+def test_boot_js_recognition_interim_results():
+    """recognition.interimResults must be true (live transcription preview)."""
+    js, _ = get_text("/static/boot.js")
+    assert 'recognition.interimResults=true' in js or 'recognition.interimResults = true' in js
+
+
+def test_boot_js_recognition_lang_en():
+    """recognition.lang must be set to en-US."""
+    js, _ = get_text("/static/boot.js")
+    assert "recognition.lang='en-US'" in js or 'recognition.lang = "en-US"' in js or "recognition.lang='en-US'" in js
+
+
+def test_boot_js_onresult_handler():
+    """boot.js must define recognition.onresult to handle transcription."""
+    js, _ = get_text("/static/boot.js")
+    assert 'recognition.onresult' in js
+
+
+def test_boot_js_onend_handler():
+    """boot.js must define recognition.onend to reset state when recording stops."""
+    js, _ = get_text("/static/boot.js")
+    assert 'recognition.onend' in js
+
+
+def test_boot_js_onerror_handler():
+    """boot.js must define recognition.onerror for graceful error handling."""
+    js, _ = get_text("/static/boot.js")
+    assert 'recognition.onerror' in js
+
+
+def test_boot_js_not_allowed_error_message():
+    """onerror must handle 'not-allowed' with a user-friendly message."""
+    js, _ = get_text("/static/boot.js")
+    assert 'not-allowed' in js
+    assert 'permission' in js.lower() or 'denied' in js.lower() or 'access' in js.lower()
+
+
+def test_boot_js_no_speech_error_message():
+    """onerror must handle 'no-speech' with a user-friendly message."""
+    js, _ = get_text("/static/boot.js")
+    assert 'no-speech' in js
+
+
+def test_boot_js_network_error_message():
+    """onerror must handle 'network' error."""
+    js, _ = get_text("/static/boot.js")
+    assert "'network'" in js or '"network"' in js
+
+
+def test_boot_js_mic_active_flag():
+    """boot.js must track recording state via _micActive flag."""
+    js, _ = get_text("/static/boot.js")
+    assert '_micActive' in js
+
+
+def test_boot_js_mic_recording_class_toggle():
+    """boot.js must toggle 'recording' CSS class on the mic button."""
+    js, _ = get_text("/static/boot.js")
+    assert "'recording'" in js or '"recording"' in js
+
+
+def test_boot_js_mic_status_toggle():
+    """boot.js must show/hide #micStatus during recording."""
+    js, _ = get_text("/static/boot.js")
+    assert 'micStatus' in js
+
+
+def test_boot_js_send_stops_mic():
+    """btnSend onclick must stop mic before sending (send guard)."""
+    js, _ = get_text("/static/boot.js")
+    # The send button onclick should check _micActive and stop recording
+    send_onclick_idx = js.find("$('btnSend').onclick")
+    assert send_onclick_idx != -1
+    # Find the handler code — check that _micActive check appears near send assignment
+    handler_end = js.find(';', send_onclick_idx)
+    handler = js[send_onclick_idx:handler_end + 1]
+    assert '_micActive' in handler or 'stopMic' in handler.lower()
+
+
+def test_boot_js_btn_mic_onclick():
+    """boot.js must attach an onclick handler to btnMic."""
+    js, _ = get_text("/static/boot.js")
+    assert 'btn.onclick' in js or "btnMic.onclick" in js or "$('btnMic').onclick" in js
+
+
+def test_boot_js_recognition_start():
+    """boot.js must call recognition.start() to begin recording."""
+    js, _ = get_text("/static/boot.js")
+    assert 'recognition.start()' in js
+
+
+def test_boot_js_recognition_stop():
+    """boot.js must call recognition.stop() to end recording."""
+    js, _ = get_text("/static/boot.js")
+    assert 'recognition.stop()' in js
+
+
+def test_boot_js_iife_guard():
+    """Mic logic must be wrapped in an IIFE so it doesn't pollute global scope."""
+    js, _ = get_text("/static/boot.js")
+    # IIFE pattern: (function(){...})() or (() => {...})()
+    assert '(function(){' in js or '(function () {' in js
+
+
+def test_boot_js_browser_unsupported_return():
+    """boot.js must bail out (return) early when SpeechRecognition is unavailable."""
+    js, _ = get_text("/static/boot.js")
+    # The IIFE should have an early return when SpeechRecognition is falsy
+    assert 'if(!SpeechRecognition)' in js or 'if (!SpeechRecognition)' in js
+
+
+def test_boot_js_shows_mic_button_when_supported():
+    """boot.js must set display='' on btnMic when SpeechRecognition is available."""
+    js, _ = get_text("/static/boot.js")
+    assert "btn.style.display=''" in js or 'btn.style.display = ""' in js
+
+
+def test_boot_js_show_toast_on_error():
+    """boot.js must call showToast() for mic errors."""
+    js, _ = get_text("/static/boot.js")
+    assert 'showToast' in js
+
+
+def test_boot_js_autoresize_called():
+    """boot.js must call autoResize() after updating textarea from transcript."""
+    js, _ = get_text("/static/boot.js")
+    assert 'autoResize()' in js
+
+
+# ── Append behaviour (fix: mic appends to existing text, not replace) ────
+
+
+def test_boot_js_prefix_variable_declared():
+    """boot.js must declare _prefix variable to snapshot pre-existing textarea content."""
+    js, _ = get_text("/static/boot.js")
+    assert "_prefix" in js
+
+
+def test_boot_js_prefix_captured_on_start():
+    """_prefix must be set from ta.value when the user starts recording."""
+    js, _ = get_text("/static/boot.js")
+    # _prefix assignment must happen in the btn.onclick else branch (before recognition.start)
+    btn_onclick_idx = js.find("btn.onclick")
+    btn_onclick_end = js.find("};", btn_onclick_idx)
+    onclick_body = js[btn_onclick_idx:btn_onclick_end]
+    assert "_prefix=ta.value" in onclick_body or "_prefix = ta.value" in onclick_body
+
+
+def test_boot_js_onresult_prepends_prefix():
+    """onresult must include _prefix when writing to textarea (append, not replace)."""
+    js, _ = get_text("/static/boot.js")
+    onresult_idx = js.find("recognition.onresult")
+    onresult_end = js.find("};", onresult_idx)
+    onresult_body = js[onresult_idx:onresult_end]
+    # ta.value must be set to _prefix + something, not just the transcript alone
+    assert "_prefix" in onresult_body
+
+
+def test_boot_js_onend_commits_with_prefix():
+    """onend must commit _prefix + _finalText so appended text survives after recognition ends."""
+    js, _ = get_text("/static/boot.js")
+    onend_idx = js.find("recognition.onend")
+    onend_end = js.find("};", onend_idx)
+    onend_body = js[onend_idx:onend_end]
+    assert "_prefix" in onend_body
+
+
+def test_boot_js_prefix_reset_on_stop():
+    """_prefix must be reset when recording stops so next session starts clean."""
+    js, _ = get_text("/static/boot.js")
+    # _setRecording(false) clears both _finalText and _prefix
+    set_rec_idx = js.find("function _setRecording")
+    set_rec_end = js.find("}", set_rec_idx) + 1
+    fn_body = js[set_rec_idx:set_rec_end]
+    assert "_prefix" in fn_body
+
+
+def test_boot_js_auto_space_between_prefix_and_transcript():
+    """onend must insert a space between existing text and new transcript when needed."""
+    js, _ = get_text("/static/boot.js")
+    onend_idx = js.find("recognition.onend")
+    onend_end = js.find("};", onend_idx)
+    onend_body = js[onend_idx:onend_end]
+    # Should handle spacing — look for trimStart or endsWith(' ') check
+    has_spacing = ("trimStart" in onend_body or "endsWith(' ')" in onend_body
+                   or "endsWith(\" \")" in onend_body or "endsWith('\\n')" in onend_body)
+    assert has_spacing, "onend should handle spacing between prefix and new transcript"
+
+
+# ── Regression: existing behaviour unchanged ──────────────────────────────
+
+
+def test_attach_button_still_wired():
+    """btnAttach onclick must still be wired up (no regression)."""
+    js, _ = get_text("/static/boot.js")
+    assert "$('btnAttach').onclick" in js
+
+
+def test_file_input_onchange_still_wired():
+    """fileInput onchange must still be wired up (no regression)."""
+    js, _ = get_text("/static/boot.js")
+    assert "$('fileInput').onchange" in js
+
+
+def test_index_html_still_has_send_button():
+    """btnSend must still be present in index.html (no regression)."""
+    html, _ = get_text("/")
+    assert 'id="btnSend"' in html
+
+
+def test_index_html_still_has_attach_button():
+    """btnAttach must still be present in index.html (no regression)."""
+    html, _ = get_text("/")
+    assert 'id="btnAttach"' in html

tests/test_sprint20b.py

@@ -0,0 +1,343 @@
+"""
+Sprint 21 Tests: Send button polish — hidden until content, pop-in animation,
+icon-only circle design.
+"""
+import re
+import urllib.request
+
+BASE = "http://127.0.0.1:8788"
+
+
+def get_text(path):
+    with urllib.request.urlopen(BASE + path, timeout=10) as r:
+        return r.read().decode(), r.status
+
+
+# ── index.html ────────────────────────────────────────────────────────────
+
+
+def test_send_button_present():
+    """btnSend must still exist in the DOM."""
+    html, status = get_text("/")
+    assert status == 200
+    assert 'id="btnSend"' in html
+
+
+def test_send_button_hidden_by_default():
+    """btnSend must start hidden (display:none) — only shown when there is content."""
+    html, _ = get_text("/")
+    btn_match = re.search(r'id="btnSend"[^>]*>', html)
+    assert btn_match, "btnSend element not found"
+    assert 'display:none' in btn_match.group(0)
+
+
+def test_send_button_no_text_label():
+    """Send button must be icon-only — no visible 'Send' text label."""
+    html, _ = get_text("/")
+    # Find the full button element (from opening tag to closing tag)
+    btn_open_end = html.find('>', html.find('id="btnSend"')) + 1
+    btn_end = html.find('</button>', btn_open_end) + len('</button>')
+    btn_inner = html[btn_open_end:btn_end]
+    # Strip SVG content and any remaining tags; check visible text
+    no_svg = re.sub(r'<svg[^>]*>.*?</svg>', '', btn_inner, flags=re.DOTALL)
+    visible_text = re.sub(r'<[^>]+>', '', no_svg).strip()
+    assert visible_text == '', f"Send button has visible text: {visible_text!r}"
+
+
+def test_send_button_has_svg_icon():
+    """Send button must have an SVG icon."""
+    html, _ = get_text("/")
+    btn_start = html.find('id="btnSend"')
+    btn_end = html.find('</button>', btn_start) + len('</button>')
+    btn_html = html[btn_start:btn_end]
+    assert '<svg' in btn_html
+
+
+def test_send_button_has_title_attribute():
+    """btnSend must have a title attribute for accessibility (replaces text label)."""
+    html, _ = get_text("/")
+    btn_match = re.search(r'id="btnSend"[^>]*>', html)
+    assert btn_match
+    assert 'title=' in btn_match.group(0)
+
+
+def test_send_button_svg_arrow_up():
+    """Send button SVG should use an upward arrow (line + polyline or path)."""
+    html, _ = get_text("/")
+    btn_start = html.find('id="btnSend"')
+    btn_end = html.find('</button>', btn_start) + len('</button>')
+    btn_html = html[btn_start:btn_end]
+    # Must have some directional shape element
+    has_shape = ('<line' in btn_html or '<polyline' in btn_html or
+                 '<polygon' in btn_html or '<path' in btn_html)
+    assert has_shape, "Send button SVG missing directional shape"
+
+
+# ── style.css ────────────────────────────────────────────────────────────
+
+
+def test_send_btn_is_circle():
+    """send-btn must use border-radius:50% for the circle shape."""
+    css, status = get_text("/static/style.css")
+    assert status == 200
+    send_idx = css.find('.send-btn{')
+    brace_open = css.find('{', send_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'border-radius:50%' in rule or 'border-radius: 50%' in rule
+
+
+def test_send_btn_fixed_dimensions():
+    """send-btn must have explicit width and height (icon-circle, not text-padded)."""
+    css, _ = get_text("/static/style.css")
+    send_idx = css.find('.send-btn{')
+    brace_open = css.find('{', send_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'width:' in rule or 'width :' in rule
+    assert 'height:' in rule or 'height :' in rule
+
+
+def test_send_btn_no_old_padding():
+    """send-btn must not use text padding layout (old pill style removed)."""
+    css, _ = get_text("/static/style.css")
+    send_idx = css.find('.send-btn{')
+    brace_open = css.find('{', send_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    # Old style used padding:7px 18px — should be gone
+    assert 'padding:7px' not in rule and 'padding: 7px' not in rule
+
+
+def test_send_btn_blue_background():
+    """send-btn background must use the blue accent (#7cb9ff or similar)."""
+    css, _ = get_text("/static/style.css")
+    send_idx = css.find('.send-btn{')
+    brace_open = css.find('{', send_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert '7cb9ff' in rule or '5ba8f5' in rule or 'var(--blue)' in rule
+
+
+def test_send_btn_has_transition():
+    """send-btn must have transition for smooth hover/active states."""
+    css, _ = get_text("/static/style.css")
+    send_idx = css.find('.send-btn{')
+    brace_open = css.find('{', send_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'transition' in rule
+
+
+def test_send_btn_has_box_shadow():
+    """send-btn must have a box-shadow glow effect."""
+    css, _ = get_text("/static/style.css")
+    send_idx = css.find('.send-btn{')
+    brace_open = css.find('{', send_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'box-shadow' in rule
+
+
+def test_send_btn_hover_has_scale():
+    """send-btn:hover must use transform:scale for a satisfying hover effect."""
+    css, _ = get_text("/static/style.css")
+    hover_idx = css.find('.send-btn:hover{')
+    brace_open = css.find('{', hover_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'scale' in rule
+
+
+def test_send_btn_active_shrinks():
+    """send-btn:active must scale down slightly for tactile press feedback."""
+    css, _ = get_text("/static/style.css")
+    active_idx = css.find('.send-btn:active{')
+    brace_open = css.find('{', active_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'scale' in rule
+
+
+def test_send_btn_disabled_rule_exists():
+    """send-btn:disabled must still be styled."""
+    css, _ = get_text("/static/style.css")
+    assert '.send-btn:disabled' in css
+
+
+def test_send_btn_visible_class_defined():
+    """.send-btn.visible class must be defined for the pop-in animation."""
+    css, _ = get_text("/static/style.css")
+    assert '.send-btn.visible' in css
+
+
+def test_send_pop_in_keyframes_defined():
+    """@keyframes send-pop-in must be defined."""
+    css, _ = get_text("/static/style.css")
+    assert 'send-pop-in' in css
+    assert '@keyframes' in css
+
+
+def _extract_keyframe(css, name):
+    """Extract the full @keyframes block for the given animation name."""
+    # Find '@keyframes <name>' directly (forward search) to avoid hitting
+    # an earlier keyframe when multiple are defined on the same line.
+    kf_start = css.find('@keyframes ' + name)
+    assert kf_start != -1, f"@keyframes {name} not found in CSS"
+    depth = 0
+    kf_end = kf_start
+    for i, ch in enumerate(css[kf_start:], kf_start):
+        if ch == '{':
+            depth += 1
+        elif ch == '}':
+            depth -= 1
+            if depth == 0:
+                kf_end = i
+                break
+    return css[kf_start:kf_end]
+
+
+def test_send_pop_in_uses_scale():
+    """send-pop-in keyframe must animate from a scaled-down state."""
+    css, _ = get_text("/static/style.css")
+    kf_rule = _extract_keyframe(css, 'send-pop-in')
+    assert 'scale' in kf_rule
+
+
+def test_send_pop_in_uses_opacity():
+    """send-pop-in keyframe must fade in (opacity transition)."""
+    css, _ = get_text("/static/style.css")
+    kf_rule = _extract_keyframe(css, 'send-pop-in')
+    assert 'opacity' in kf_rule
+
+
+def test_send_btn_mobile_override_no_padding():
+    """Mobile override for send-btn must not add text padding (keeps circle shape)."""
+    css, _ = get_text("/static/style.css")
+    # Find the @media block
+    media_idx = css.find('@media')
+    send_mobile_idx = css.find('.send-btn', media_idx)
+    if send_mobile_idx == -1:
+        return  # No mobile override, fine
+    brace_open = css.find('{', send_mobile_idx)
+    brace_close = css.find('}', brace_open)
+    rule = css[brace_open:brace_close]
+    assert 'padding:' not in rule and 'font-size' not in rule
+
+
+# ── ui.js ─────────────────────────────────────────────────────────────────
+
+
+def test_ui_js_update_send_btn_function():
+    """ui.js must define updateSendBtn() function."""
+    js, status = get_text("/static/ui.js")
+    assert status == 200
+    assert 'function updateSendBtn' in js
+
+
+def test_update_send_btn_checks_content():
+    """updateSendBtn must check textarea value length."""
+    js, _ = get_text("/static/ui.js")
+    fn_idx = js.find('function updateSendBtn')
+    fn_end = js.find('\n}', fn_idx) + 2
+    fn_body = js[fn_idx:fn_end]
+    assert 'msg' in fn_body
+    assert '.value' in fn_body
+    assert '.length' in fn_body or '.trim()' in fn_body
+
+
+def test_update_send_btn_checks_pending_files():
+    """updateSendBtn must also show send button when files are attached."""
+    js, _ = get_text("/static/ui.js")
+    fn_idx = js.find('function updateSendBtn')
+    fn_end = js.find('\n}', fn_idx) + 2
+    fn_body = js[fn_idx:fn_end]
+    assert 'pendingFiles' in fn_body
+
+
+def test_update_send_btn_uses_visible_class():
+    """updateSendBtn must add .visible class to trigger the pop-in animation."""
+    js, _ = get_text("/static/ui.js")
+    fn_idx = js.find('function updateSendBtn')
+    fn_end = js.find('\n}', fn_idx) + 2
+    fn_body = js[fn_idx:fn_end]
+    assert 'visible' in fn_body
+
+
+def test_update_send_btn_uses_display_none():
+    """updateSendBtn must hide the button with display:none when no content."""
+    js, _ = get_text("/static/ui.js")
+    fn_idx = js.find('function updateSendBtn')
+    fn_end = js.find('\n}', fn_idx) + 2
+    fn_body = js[fn_idx:fn_end]
+    assert 'display' in fn_body
+    assert 'none' in fn_body
+
+
+def test_set_busy_calls_update_send_btn():
+    """setBusy must call updateSendBtn() so button hides while agent is responding."""
+    js, _ = get_text("/static/ui.js")
+    busy_idx = js.find('function setBusy')
+    busy_end = js.find('\n}', busy_idx) + 2
+    busy_body = js[busy_idx:busy_end]
+    assert 'updateSendBtn' in busy_body
+
+
+def test_render_tray_calls_update_send_btn():
+    """renderTray must call updateSendBtn() so button appears when files are attached."""
+    js, _ = get_text("/static/ui.js")
+    tray_idx = js.find('function renderTray')
+    tray_end = js.find('\n}', tray_idx) + 2
+    tray_body = js[tray_idx:tray_end]
+    assert 'updateSendBtn' in tray_body
+
+
+# ── boot.js ──────────────────────────────────────────────────────────────
+
+
+def test_boot_js_input_calls_update_send_btn():
+    """boot.js input event listener must call updateSendBtn()."""
+    js, status = get_text("/static/boot.js")
+    assert status == 200
+    assert 'updateSendBtn' in js
+
+
+# ── messages.js ───────────────────────────────────────────────────────────
+
+
+def test_auto_resize_calls_update_send_btn():
+    """autoResize() must call updateSendBtn() so button hides after send clears textarea."""
+    js, status = get_text("/static/messages.js")
+    assert status == 200
+    assert 'updateSendBtn' in js
+
+
+# ── Regression: existing behaviour unchanged ──────────────────────────────
+
+
+def test_send_button_still_has_send_btn_class():
+    """btnSend must still carry class='send-btn' for CSS targeting."""
+    html, _ = get_text("/")
+    assert 'class="send-btn"' in html
+
+
+def test_ui_js_set_busy_still_disables_btn():
+    """setBusy must still set btnSend.disabled (not just hide it)."""
+    js, _ = get_text("/static/ui.js")
+    busy_idx = js.find('function setBusy')
+    busy_end = js.find('\n}', busy_idx) + 2
+    busy_body = js[busy_idx:busy_end]
+    assert "btnSend" in busy_body
+    assert 'disabled' in busy_body
+
+
+def test_index_html_attach_button_unchanged():
+    """btnAttach must still be present (no regression)."""
+    html, _ = get_text("/")
+    assert 'id="btnAttach"' in html
+
+
+def test_send_function_still_exists():
+    """send() function must still be defined in messages.js."""
+    js, _ = get_text("/static/messages.js")
+    assert 'async function send()' in js

tests/test_sprint23.py

@@ -0,0 +1,196 @@
+"""
+Sprint 23 Tests: agentic transparency — token/cost display, session usage fields,
+subagent card names, skill picker in cron, skill linked files.
+"""
+import json, urllib.error, urllib.request
+
+BASE = "http://127.0.0.1:8788"
+
+
+def get(path):
+    with urllib.request.urlopen(BASE + path, timeout=10) as r:
+        return json.loads(r.read()), r.status
+
+
+def post(path, body=None):
+    data = json.dumps(body or {}).encode()
+    req = urllib.request.Request(BASE + path, data=data,
+                                headers={"Content-Type": "application/json"})
+    try:
+        with urllib.request.urlopen(req, timeout=10) as r:
+            return json.loads(r.read()), r.status
+    except urllib.error.HTTPError as e:
+        return json.loads(e.read()), e.code
+
+
+def make_session(created_list):
+    d, _ = post("/api/session/new", {})
+    sid = d["session"]["session_id"]
+    created_list.append(sid)
+    return sid, d["session"]
+
+
+# ── Session usage fields ─────────────────────────────────────────────────
+
+def test_new_session_has_usage_fields():
+    """New session should include input_tokens, output_tokens, estimated_cost."""
+    created = []
+    try:
+        sid, sess = make_session(created)
+        post("/api/session/rename", {"session_id": sid, "title": "Usage Test"})
+        d, status = get(f"/api/session?session_id={sid}")
+        assert status == 200
+        sess = d["session"]
+        assert "input_tokens" in sess, "input_tokens field missing from session"
+        assert "output_tokens" in sess, "output_tokens field missing from session"
+        assert "estimated_cost" in sess, "estimated_cost field missing from session"
+        assert sess["input_tokens"] == 0
+        assert sess["output_tokens"] == 0
+    finally:
+        for s in created:
+            post("/api/session/delete", {"session_id": s})
+
+
+def test_session_compact_has_usage_fields():
+    """Session list should include usage fields in compact form."""
+    created = []
+    try:
+        sid, _ = make_session(created)
+        post("/api/session/rename", {"session_id": sid, "title": "Compact Usage"})
+        d, status = get("/api/sessions")
+        assert status == 200
+        match = [s for s in d["sessions"] if s["session_id"] == sid]
+        assert len(match) == 1
+        assert "input_tokens" in match[0], "input_tokens missing from session list"
+        assert "output_tokens" in match[0], "output_tokens missing from session list"
+        assert match[0]["input_tokens"] == 0
+        assert match[0]["output_tokens"] == 0
+    finally:
+        for s in created:
+            post("/api/session/delete", {"session_id": s})
+
+
+def test_session_usage_defaults_zero():
+    """New session usage fields should default to 0/None in creation response."""
+    created = []
+    try:
+        sid, sess = make_session(created)
+        assert "input_tokens" in sess, "input_tokens missing from new session response"
+        assert "output_tokens" in sess, "output_tokens missing from new session response"
+        assert sess["input_tokens"] == 0
+        assert sess["output_tokens"] == 0
+    finally:
+        for s in created:
+            post("/api/session/delete", {"session_id": s})
+
+
+# ── Skills content linked_files ──────────────────────────────────────────
+
+def test_skills_content_requires_name():
+    """GET /api/skills/content without name should return 400 (or 500 if skills module unavailable)."""
+    try:
+        d, status = get("/api/skills/content")
+        assert status in (400, 500), f"Expected 400/500 for missing name, got {status}"
+    except urllib.error.HTTPError as e:
+        assert e.code in (400, 500), f"Expected 400/500 for missing name, got {e.code}"
+
+
+def test_skills_content_has_linked_files_key():
+    """GET /api/skills/content should always return a linked_files key."""
+    try:
+        d, status = get("/api/skills")
+        if not d.get("skills"):
+            return  # no skills in test env, skip
+        name = d["skills"][0]["name"]
+        d2, status2 = get(f"/api/skills/content?name={name}")
+        assert status2 == 200
+        assert "linked_files" in d2, "linked_files key missing from skills/content response"
+        # linked_files must be a dict (possibly empty), not None
+        assert isinstance(d2["linked_files"], dict), "linked_files must be a dict"
+    except urllib.error.HTTPError:
+        pass  # skills module unavailable in this env
+
+
+def test_skills_content_file_path_traversal_rejected():
+    """GET /api/skills/content with traversal path should be rejected."""
+    from urllib.parse import quote as _quote
+    try:
+        d, status = get("/api/skills")
+        if not d.get("skills"):
+            return  # no skills in test env, skip
+        name = d["skills"][0]["name"]
+        traversal = _quote("../../etc/passwd", safe="")
+        try:
+            d2, status2 = get(f"/api/skills/content?name={name}&file={traversal}")
+            assert status2 in (400, 404, 500), f"Path traversal should be rejected, got {status2}"
+        except urllib.error.HTTPError as e:
+            assert e.code in (400, 404, 500), f"Path traversal should be rejected, got {e.code}"
+    except urllib.error.HTTPError:
+        pass  # skills module unavailable in test env
+
+
+def test_skills_content_wildcard_name_rejected():
+    """GET /api/skills/content with glob wildcard in name should be rejected when file param present."""
+    try:
+        try:
+            d2, status2 = get("/api/skills/content?name=*&file=SKILL.md")
+            assert status2 == 400, f"Wildcard name should return 400, got {status2}"
+        except urllib.error.HTTPError as e:
+            assert e.code in (400, 404), f"Wildcard name should be rejected, got {e.code}"
+    except Exception:
+        pass
+
+
+# ── Cron create with skills ───────────────────────────────────────────────
+
+def test_cron_create_accepts_skills():
+    """POST /api/crons/create should accept and store a skills array (or 500 if cron module unavailable)."""
+    created_jobs = []
+    try:
+        body = {
+            "name": "test-sprint23-skills",
+            "schedule": "0 9 * * *",
+            "prompt": "test prompt",
+            "deliver": "local",
+            "skills": ["some-skill"]
+        }
+        d, status = post("/api/crons/create", body)
+        if status in (400, 500) and ('module' in str(d.get('error','')) or 'cron' in str(d.get('error',''))):
+            return  # cron module not available in test env
+        assert status == 200, f"Expected 200 from cron create, got {status}: {d}"
+        assert d.get("ok"), f"Cron create did not return ok: {d}"
+        job_id = d.get("job", {}).get("id") or d.get("id")
+        if job_id:
+            created_jobs.append(job_id)
+        # Verify job appears in list
+        jobs_d, _ = get("/api/crons")
+        job = next((j for j in jobs_d.get("jobs", []) if j.get("name") == "test-sprint23-skills"), None)
+        assert job is not None, "Created cron job not found in job list"
+        assert job.get("skills") == ["some-skill"] or job.get("skill") == "some-skill", \
+            f"skills not stored on job: {job}"
+    finally:
+        try:
+            for jid in created_jobs:
+                post("/api/crons/delete", {"id": jid})
+            jobs_d, _ = get("/api/crons")
+            for j in jobs_d.get("jobs", []):
+                if j.get("name") == "test-sprint23-skills":
+                    post("/api/crons/delete", {"id": j["id"]})
+        except Exception:
+            pass  # cron module may not be available
+
+
+# ── Tool call integrity ──────────────────────────────────────────────────
+
+def test_tool_calls_have_real_names():
+    """Tool calls in session JSON should not have unresolved 'tool' name."""
+    created = []
+    try:
+        sid, _ = make_session(created)
+        d, status = get(f"/api/session?session_id={sid}")
+        assert status == 200
+        for tc in d["session"].get("tool_calls", []):
+            assert tc.get("name") not in ("tool", "", None), f"Unresolved tool name: {tc}"
+    finally:
+        for s in created:
+            post("/api/session/delete", {"session_id": s})