Two fixes for Camanji rate limit UX:
1. api/streaming.py — pass fallback_model from profile config to AIAgent
The agent already supports fallback_model (a dict with provider/model/base_url)
for automatic rate-limit recovery, but streaming.py never read it from config
or passed it to AIAgent. Now reads get_config().get('fallback_model') at
call time (not module-level snapshot) and passes it through.
Also reads platform_toolsets.cli from the active profile's config at call
time so profiles with custom toolset lists use the right tools.
Camanji has fallback_model: {provider: openrouter, model: anthropic/claude-sonnet-4.6}
so hitting the direct-Anthropic rate limit will now automatically retry via
OpenRouter before giving up.
2. api/streaming.py + static/messages.js — show error inline, not 'Connection lost'
Previously: agent threw -> put('error', msg) -> SSE connection closed ->
browser's network-level 'error' event fired -> generic 'Connection lost'.
The actual error message was invisible to the user.
Fix: renamed server-side error event to 'apperror' (distinct from the SSE
spec's network error event). Added source.addEventListener('apperror', ...)
in messages.js that renders the error as a styled assistant message:
⏱️ Rate limit reached: <full message>
*Rate limit reached. Fallback model exhausted. Try again in a moment.*
Also added source.addEventListener('warning', ...) for non-fatal notices
(future use: fallback-activated status bar update).
Tests: 426 passed, 0 failed.
A session with messages belongs to the profile it was created under. Switching
profiles while a conversation is in progress should not retag that session or
update its workspace/model in place — that would corrupt the session's context.
New behavior:
- Session has NO messages (empty): profile switch updates it in place (model,
workspace). Works exactly as before — nothing was started yet.
- Session HAS messages (in progress): profile switch calls newSession() to
start a fresh session tagged to the new profile. The old session is left
untouched. Toast: 'Switched to profile: X — new conversation started'.
- Agent busy: blocked as before, no change.
Also: S._profileDefaultWorkspace is now consumed (set to null) inside
newSession() after the first use, so it doesn't keep forcing the same
workspace on every subsequent new session after a switch.
Root cause: resolve_model_provider() had a branch:
if config_provider and config_provider != 'openrouter' and prefix in _PROVIDER_MODELS:
return bare, prefix, None
When Camanji profile (config_provider='anthropic') picked openai/gpt-5.4-mini
from the OpenRouter dropdown, prefix='openai' matched _PROVIDER_MODELS and
config_provider was not 'openrouter', so it returned ('gpt-5.4-mini', 'openai', None).
The agent then demanded OPENAI_API_KEY directly -- not found -- RuntimeError --
stream crashed -- 'Connection lost'.
Fix: if prefix != config_provider (cross-provider selection), always route through
openrouter with the full provider/model string. Only strip the prefix and call a
direct provider API when the config_provider EXACTLY matches the model prefix.
Cases verified:
openrouter + openai/gpt-5.4-mini -> (openai/gpt-5.4-mini, openrouter) ✓
anthropic + openai/gpt-5.4-mini -> (openai/gpt-5.4-mini, openrouter) ✓ FIXED
anthropic + anthropic/claude-... -> (claude-..., anthropic) ✓
anthropic + claude-sonnet-4-6 bare -> (claude-sonnet-4-6, anthropic) ✓
openrouter + anthropic/claude-... -> (anthropic/claude-..., openrouter) ✓
Tests: 426 passed, 0 failed.
Root cause: three interacting bugs caused the model picker to show the wrong
model or flicker after a profile switch.
Bug 1 — syncTopbar() fought switchToProfile().
After switchToProfile() set the picker to the profile's model, syncTopbar()
was called (via renderSessionList -> loadSession, then explicitly at the end)
and overwrote it with S.session.model -- the old session's model.
Fix: added S._pendingProfileModel flag. switchToProfile() sets it;
syncTopbar() checks it first, applies the override, then clears it.
S.session.model is also updated to the resolved value so subsequent
syncTopbar() calls are consistent.
Bug 2 — Raw option injected at top of list for mismatched model IDs.
Profile configs store model IDs like 'claude-sonnet-4-6' (hermes-agent
format: hyphens, no namespace prefix) but the dropdown has
'anthropic/claude-sonnet-4.6' (OpenRouter format: dots, with prefix).
The old code did sel.value = id, found no match, then injected a new
<option> at the top of the list -- creating a lowercase duplicate that
didn't match any real provider group entry.
Fix: _findModelInDropdown() normalises both sides (strip prefix, hyphens->dots,
lowercase) and finds the best matching existing option. No new options are ever
injected for profile switching.
Bug 3 — populateModelDropdown() injected raw option on cold load.
Same issue: if default_model from /api/models didn't exactly match a dropdown
value, an extra option was added. Fixed by using _applyModelToDropdown()
which only selects existing options.
New helpers in ui.js:
_findModelInDropdown(modelId, sel) -- smart fuzzy match, returns matched value
_applyModelToDropdown(modelId, sel) -- sets picker, returns resolved value
Tests: 426 passed, 0 failed.
Three interrelated fixes:
1. api/workspace.py — clean workspace isolation with auto-migration
_clean_workspace_list(): sanitizes any workspace list by:
- Removing test artifacts (webui-mvp-test, test-workspace paths)
- Removing paths that no longer exist on disk
- Removing cross-profile leaks (paths under ~/.hermes/profiles/*)
- Renaming 'default' workspace label to 'Home' (avoids confusion
with the 'default' profile name)
_migrate_global_workspaces(): one-time migration for upgrading users.
Reads the legacy global workspaces.json, runs _clean_workspace_list,
rewrites it cleaned. This runs automatically on first load after upgrade
for the default profile only.
load_workspaces(): now cleans every read and persists cleaned version
if anything changed. Named profiles always start fresh (no global leak).
Empty results fall back to 'Home' entry pointing at profile's workspace.
Default label for auto-generated single-entry lists is 'Home', not 'default'.
2. api/models.py — legacy session profile backfill (already committed,
this commit adds the sessions.js filter tightening counterpart)
3. static/sessions.js — strict profile filter
Removed the '!s.profile' escape hatch from the profile filter.
Server now backfills profile='default' on legacy sessions, so every
session has an explicit tag. Filter is now exact:
s.profile === S.activeProfile
Named profiles see zero legacy clutter. Default profile sees its own
sessions. 'All profiles' toggle still shows everything.
Migration story for users pulling this update:
- Existing sessions (profile=null) -> attributed to 'default' at read time
- Global workspaces.json -> cleaned of test artifacts and cross-profile paths
on first server start after upgrade
- Named profile workspace files -> cleaned on first read, persisted clean
- No manual intervention needed
Tests: 426 passed, 0 failed.
Root cause: sessions created before Sprint 22 have no profile tag (profile=None).
The client filter was '!s.profile || s.profile === S.activeProfile' -- the
'!s.profile' guard made ALL 33 legacy sessions visible under every profile,
so switching to Camanji still showed the entire default session history.
Fix:
- api/models.py all_sessions(): backfill profile='default' on sessions with
no profile tag before returning. This is in-memory only (no disk writes) --
legacy sessions just get attributed to the default profile at read time.
Applied to both the index-path and the full-scan fallback path.
- static/sessions.js: tighten the client filter to s.profile === S.activeProfile
(remove the '!s.profile' escape hatch -- now redundant since server fills it).
Every session now has an explicit profile, so the filter is precise.
Result: switching to Camanji shows only Camanji sessions. Default profile shows
legacy + default-tagged sessions. 'All profiles' toggle still shows everything.
S.activeProfile defaults to 'default' in the S object so first render is safe.
Tests: 426 passed, 0 failed.
1. _profile_default_workspace() now checks terminal.cwd
Profile config.yaml files don't have a 'workspace' or 'default_workspace' key
— they store the working directory as terminal.cwd (the hermes-agent CLI
setting). Added it as the third fallback after 'workspace' and
'default_workspace', so switching to camanji correctly resolves
~/Camanji, webui resolves ~/webui-mvp, etc.
2. Workspace dropdown opens upward (bottom: calc(100% + 4px))
The dropdown is now anchored at the bottom of the sidebar. Opening it
downward (top: 100%) caused it to clip off screen. Flipped to open upward
with an upward shadow so it expands into the session list area instead.
Tests: 426 passed, 0 failed.
Two changes:
1. Workspace updates correctly on profile switch
switchToProfile() now applies data.default_workspace from the switch
response to the current session via /api/session/update, updates
S.session.workspace in-memory, and stores S._profileDefaultWorkspace
so the next new session also inherits the profile's workspace.
newSession() in sessions.js picks up S._profileDefaultWorkspace when
creating a new session after a profile switch.
2. Workspace chip removed from topbar
The workspace was shown in two places: the topbar chip (wsChip) AND
the sidebar bottom display (sidebarWsDisplay with name + full path).
The topbar chip was redundant, cluttered the topbar, and pushed other
chips (profile, model, clear, settings) off screen.
Removed wsChip from the topbar entirely. The sidebar display is now
the sole workspace UI, consistent and unambiguous.
Moved wsDropdown to live inside the sidebar position:relative wrapper
so it opens downward from sidebarWsDisplay. Updated the click-outside
listener to close on clicks outside sidebarWsDisplay/wsDropdown.
Removed stale wsChip update code from syncTopbar() in ui.js.
Tests: 426 passed, 0 failed.
Root cause: _DEFAULT_HERMES_HOME was evaluated at module import time from
os.getenv('HERMES_HOME'). HERMES_HOME is a MUTABLE env var -- init_profile_state()
at server startup calls _set_hermes_home() which writes to os.environ['HERMES_HOME'].
If the sticky active_profile file pointed to e.g. 'webui', HERMES_HOME was set to
~/.hermes/profiles/webui BEFORE api/profiles.py imported. So _DEFAULT_HERMES_HOME
resolved to ~/.hermes/profiles/webui. Then switch_profile('webui') computed:
home = ~/.hermes/profiles/webui / 'profiles' / 'webui'
= ~/.hermes/profiles/webui/profiles/webui -- doesn't exist -> 404 ValueError
Fix: replace the one-liner assignment with _resolve_base_hermes_home() which:
1. Checks HERMES_BASE_HOME env var (explicit override)
2. Checks HERMES_HOME -- but if it looks like a profiles/ subdir (parent.name ==
'profiles'), walks up two levels to the actual base
3. Falls back to Path.home() / '.hermes'
This means the server can start with HERMES_HOME pointing to any profile and
_DEFAULT_HERMES_HOME will still correctly point to ~/.hermes.
Also fix: api() helper in workspace.js was throwing new Error(await res.text())
which surfaced raw JSON to the UI: 'Switch failed: {"error":"Profile X does not exist."}'
Now parses the JSON and extracts j.error so the toast shows clean human-readable text.
Regression tests added in test_sprint23.py:
- test_profile_switch_base_home_not_subdir: static analysis verifying the resolver
- test_api_helper_returns_clean_error_message: verifies api() parses JSON errors
- test_profile_switch_resolve_base_home_logic: verifies the profiles/ subdir detection
Tests: 426 passed, 0 failed.
BUG-1 (critical): api/profiles.py _DEFAULT_HERMES_HOME used Path.home()/.hermes
hardcoded, ignoring the HERMES_HOME env var. conftest.py sets HERMES_HOME to a
test-isolated state dir -- but profiles.py bypassed it and read/wrote real ~/.hermes
during every test run (active_profile file, .env loading). Fixed by reading
os.getenv('HERMES_HOME', ...) at module load time.
BUG-7 (medium): api/workspace.py load_workspaces() fell back to the global
workspaces.json for ALL profiles when their profile-local file didn't exist yet.
New named profiles silently inherited the default profile's workspace list instead
of starting clean. Fixed: the global file fallback now only applies to the default
profile (migration path); named profiles start with a fresh default entry.
BUG-4 (high): test_sessions_list_includes_profile had a vacuous 'if matching:'
guard -- if the session wasn't found the assert was silently skipped and the test
passed. Fixed with hard assert. Also changed to use /api/session?session_id=
directly instead of scanning /api/sessions (which filters out empty Untitled
sessions with 0 messages, causing the test to always see an empty match list).
BUG-5 / test ordering regression: test_profile_switch_returns_default_model_and_workspace
failed with 409 because test_chat_stream_opens_successfully (runs earlier in the
suite) starts a real LLM stream that stays alive in STREAMS. Added a wait loop
(up to 30s) polling /health active_streams before attempting the profile switch.
BUG-8 (low): Removed dead import _profile_default_workspace in switch_profile()
-- was imported but never used (get_last_workspace() already delegates to it).
Also: test_profile_active_endpoint hardcoded assert data['name'] == 'default'
which fails if a prior run left a non-default active_profile on disk. Changed
to assert name is a non-empty string (the endpoint contract), not a specific value.
Tests: 423 passed, 0 failed.
Fix five coherence bugs in profile switching:
1. Model picker ignored profile default (localStorage stale key)
2. Workspace list was global (not profile-scoped)
3. DEFAULT_WORKSPACE was a boot-time singleton
4. Session list showed all profiles (no filtering)
5. switchToProfile() didn't refresh workspaces or sessions
Backend: workspace storage is now profile-local for named profiles,
switch_profile() returns default_model and default_workspace.
Frontend: switchToProfile() clears stale model pref, refreshes
workspace list and session list, sessions.js filters by active profile
with 'Show N from other profiles' toggle.
8 new tests. 400 pass / 23 fail (identical to baseline).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
BUG-3 (high): /api/profile/delete missing RuntimeError catch. When
deleting the active profile while an agent was running, delete_profile_api()
called switch_profile('default') which raises RuntimeError('Cannot switch
profiles while agent is running'). This propagated to the 500 handler
giving the user 'Internal server error' with no context. Added the same
except RuntimeError -> 409 pattern that /api/profile/switch already uses.
INFO-1 (defense-in-depth): /api/profile/create had no server-side name
validation before delegating to hermes_cli.validate_profile_name. Added
server-side ^[a-z0-9][a-z0-9_-]{0,63}$ check, consistent with client-side
regex in submitProfileCreate(). Prevents path-traversal-ish names from
reaching hermes_cli even if the client-side guard is bypassed.
INFO-2 (defense-in-depth): clone_from parameter was passed directly to
hermes_cli with no validation. Applied the same name regex check to
clone_from before delegating.
BUG-11 (low): toggleProfileDropdown() and toggleWsDropdown() could both
be open simultaneously. Added cross-dropdown close calls: opening the
profile dropdown now closes the workspace dropdown, and vice versa.
Tests: 415 passed, 0 failed.
Add full profile management to the web UI, matching the hermes-agent CLI
profile system. Profiles are isolated HERMES_HOME instances with their own
config, skills, memory, cron, and API keys.
Backend: new api/profiles.py wrapping hermes_cli.profiles, dynamic config
reloading, 5 new API endpoints, profile-aware path resolution, HERMES_HOME
env save/restore in streaming, module-level cache patching for skills_tool
and cron/jobs.
Frontend: profile chip in topbar with dropdown, Profiles sidebar panel with
CRUD UI, boot-time profile fetch, cascade refresh on switch.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
BUG-1 (critical): CSS cascade — .sidebar{position:relative} and
.rightpanel{position:relative} at line 528/530 appeared after the
@media(max-width:640px) block and silently overrode the position:fixed
overlay behavior needed for the mobile slide-in. Wrapped both in
@media(min-width:641px) so they only apply on desktop.
BUG-2 (medium): mobileSwitchPanel() in boot.js always reopened the
sidebar overlay after closing it, with a stale comment saying 'close
after a moment' but no actual auto-close. For the 'chat' panel, the
content lives in the main area — reopening the sidebar obstructs it.
Fixed: only open sidebar for non-chat panels; chat tap closes sidebar.
BUG-3 (medium): Dockerfile was missing 'pip install -r requirements.txt'.
pyyaml (required by api/config.py) is not in the python:3.12-slim base
image — the container would fail at startup with ImportError.
SEC-2 (medium): No .dockerignore — COPY . /app included .git/, tests/,
and .env* in every image. Added .dockerignore excluding these.
NIT-3: docker-compose.yml used ${HERMES_HOME:-~/.hermes} but Docker
Compose does not shell-expand ~ in default values. Changed to
${HERMES_HOME:-${HOME}/.hermes}.
Tests: 415 passed, 0 failed (same as pre-fix).
Mobile responsive (Issue #21):
- Hamburger sidebar: slide-in overlay on mobile (<640px) with backdrop.
Tap hamburger in topbar to open, tap outside to close. Full session
list, project chips, all panel content accessible.
- Bottom navigation bar: 5-tab fixed bar (Chat, Tasks, Skills, Memory,
Spaces) replaces sidebar nav tabs on mobile. iOS-style layout.
Tapping a tab opens the sidebar overlay with that panel active.
- Right panel slide-over: Files button in topbar chips opens workspace
panel as a slide-over from the right on mobile/tablet.
- Touch targets: all interactive elements get min 44x44px touch areas.
Session items, approval buttons, composer buttons all sized for fingers.
- Composer positioned above bottom nav bar with proper spacing.
- Sidebar nav tabs and bottom section hidden on mobile (replaced by
bottom nav + topbar chips).
- Clicking a session auto-closes the sidebar overlay.
- Desktop layout completely unchanged — all mobile elements are
display:none by default, only shown inside @media(max-width:640px).
Docker (Issue #7):
- Dockerfile: python:3.12-slim, HERMES_WEBUI_HOST=0.0.0.0, port 8787.
- docker-compose.yml: named volume for state persistence, optional
~/.hermes mount for agent features, password env var documented.
- README: Docker quick start section with compose and manual commands.
Tests: 392 passed, 23 pre-existing failures, 0 regressions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
rfind('@keyframes') searched backward from 'send-pop-in' but with both
keyframes on the same CSS line, it landed on mic-pulse instead.
Fix: use find('@keyframes send-pop-in') directly (forward search) via
a shared _extract_keyframe() helper. Same fix applied to both
test_send_pop_in_uses_scale and test_send_pop_in_uses_opacity.
- index.html: btnSend hidden by default (display:none), icon-only (upward
arrow SVG, no text label), title attribute for accessibility
- style.css: new send-btn design — 34px circle, blue fill (#7cb9ff),
subtle glow box-shadow, scale() hover/active for tactile feel,
.send-btn.visible with @keyframes send-pop-in (scale+opacity spring
using cubic-bezier(.34,1.56,.64,1) for a satisfying pop). Mobile
override updated to preserve circle dimensions.
- ui.js: updateSendBtn() — shows button with pop-in animation when
textarea has content OR files are attached and agent is not busy;
hides instantly when content is cleared. Hooked into setBusy() and
renderTray() so button state tracks all content sources correctly.
- boot.js: input event listener calls updateSendBtn() on every keystroke.
- messages.js: autoResize() calls updateSendBtn() so button disappears
immediately after send clears the textarea.
- tests/test_sprint21.py: 33 tests covering HTML structure, CSS design
(circle shape, colors, animations, keyframes), JS logic (updateSendBtn,
setBusy, renderTray, autoResize integration), and regressions
(363 total, all pass).
Previously, tapping the mic button would reset the textarea each time,
clobbering anything the user had already typed or previously dictated.
Fix:
- Capture _prefix = ta.value when recording starts (btn.onclick)
- onresult writes _prefix + (final || interim) so live interim text
appears after the existing content, not replacing it
- onend commits _prefix + _finalText with smart space insertion:
if the prefix doesn't end with a space or newline, a space is added
before the new transcript so words don't run together
- _prefix is reset to '' in _setRecording(false) so each new recording
session starts with a fresh snapshot
Behaviour now: tap mic, speak, tap again (or wait for auto-stop) ->
transcript is appended to whatever was in the textarea. Tap mic again
-> continues appending further. Text stays fully editable before send.
tests/test_sprint20.py: 6 new tests covering prefix capture, onresult
prepend, onend commit, reset, and smart spacing (52 total, 382 overall).
- index.html: add #btnMic (hidden by default, shown if browser supports
SpeechRecognition) and #micStatus listening indicator inside .composer-box
- boot.js: IIFE-scoped mic handler wired to Web Speech API
* recognition.continuous=false (auto-stops after ~2s silence)
* recognition.interimResults=true (live transcript preview in textarea)
* Toggles .recording class + shows #micStatus while active
* Handles 'not-allowed', 'no-speech', 'network' errors via showToast()
* btnSend.onclick stops active recognition before sending
* Entire feature disabled/hidden gracefully when API unavailable
- style.css: .mic-btn, .mic-btn.recording (red pulse animation),
.mic-status, .mic-dot, @keyframes mic-pulse
- tests/test_sprint20.py: 46 tests covering HTML structure, CSS rules,
JS logic, error handling, and regression checks (376 total, all pass)
No API keys, no external libraries, no server changes. Browser-only.
Works in Chrome, Edge, Safari (partial). Firefox unsupported (hides button).
Tracebacks exposed file paths, module names, and potentially secret
values from local variables. Now logged server-side only; clients
receive a generic error message.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sprint 19 added 10 new tests (not 9), bringing the total to 328 (not 327).
All 328 tests pass with 0 failures -- the "304 passing, 23 pre-existing
failures" note was stale from an earlier state of the test suite.
Files updated:
- CHANGELOG.md: v0.21 header, tests line, footer
- TESTING.md: automated tests header, footer
- ROADMAP.md: header note, Sprint History table
The previous logic treated a blank password field as intent to clear auth,
which meant saving any other setting (model, send key, etc.) would silently
disable password protection.
New behavior:
- Blank password field + Save Settings = no change to auth (do nothing)
- Password field with content + Save = set/change password (unchanged)
- 'Disable Auth' button = explicit confirmation-gated clear (new)
UI changes:
- index.html: updated description text to 'Leave blank to keep current
setting'; added 'Disable Auth' button (amber, shown only when auth active)
- panels.js: saveSettings() skips password logic entirely when field is blank;
loadSettingsPanel() shows/hides both btnDisableAuth and btnSignOut based on
auth_enabled; new disableAuth() function sends _clear_password:true after
confirm() prompt and hides both auth buttons on success
Server: no logic changes needed; _clear_password handling in save_settings()
is now only triggered by the explicit Disable Auth action.
'/' and '/index.html' were in PUBLIC_PATHS, so setting a password
and refreshing the root URL would show the app blank (JS loaded
but all API calls returned 401) instead of redirecting to /login.
Root and index.html must be protected paths so the browser gets a
302 -> /login when auth is active and no valid session cookie exists.
Three security issues found during review:
1. password_hash exposed via GET /api/settings
load_settings() returned all fields including the stored hash.
Fix: strip password_hash from the response in routes.py.
2. password_hash directly settable via POST /api/settings
'password_hash' was in _SETTINGS_ALLOWED_KEYS, so an attacker
could POST {password_hash: 'X'} to hijack auth without knowing
the current password.
Fix: exclude password_hash from _SETTINGS_ALLOWED_KEYS.
(Use _set_password for the legitimate hash-and-store path.)
3. Security headers missing from /api/auth/login and /api/auth/logout
These endpoints built their responses manually (bypassing j()),
so they omitted X-Content-Type-Options etc.
Fix: call _security_headers() before end_headers() on both.
Tests updated: renamed test to assert key absent (not just None),
added new test verifying direct password_hash POST is blocked.
Auth system (off by default, zero friction for localhost):
- New api/auth.py module: password hashing (SHA-256 + STATE_DIR salt),
signed HMAC session cookies (24h TTL), auth middleware
- Enable via HERMES_WEBUI_PASSWORD env var or Settings panel
- Minimal dark-themed login page at /login (self-contained HTML)
- POST /api/auth/login, /api/auth/logout, GET /api/auth/status
- Settings panel: "Access Password" field + "Sign Out" button
- password_hash added to settings.json (null = auth disabled)
Security hardening:
- Security headers on all responses: X-Content-Type-Options: nosniff,
X-Frame-Options: DENY, Referrer-Policy: same-origin
- POST body size limit: 20MB cap in read_body() to prevent DoS
Closes#23. 9 new tests. Total: 304 passed, 0 regressions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix stale tree cache: clear _dirCache and _expandedDirs on root nav
- Fix clearPreview: prompt before discarding unsaved preview edits
- Update UI version label from v0.17.1 to v0.20
- Add Sprint 18 entry to CHANGELOG.md
- Update SPRINTS.md current state to v0.20
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- File preview auto-close: clearPreview() extracted as named function
and called from loadDir(). Navigating directories (breadcrumbs, up
button, folder clicks) now automatically closes the right panel
file preview instead of leaving stale content visible.
- 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.
Indentation shows nesting depth. Empty directories show "(empty)".
S._expandedDirs tracks open state, S._dirCache caches fetched entries.
Tests: 295 passed, 23 pre-existing failures, 0 regressions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
