- Support image file fallback when no sprite index exists
(Immich Photo Manager, Cmux Resurrect now show their logos)
- Render external links [text](https://...) as clickable links
(fixes Third Party Contributions raw markdown)
- Smaller inline icons (20px) to fit chat bubble aesthetic
- Separate icon-chat CSS class for chat-specific sizing
- Fix side panel and full screen not covering full viewport
- Fix floating mode initial position (near chat button, not top-right)
- Reset width/height inline styles when switching modes
- Add 84-chat-layout-modes.test.mjs: 38 assertions covering
compact, side panel, full screen, floating, drag, rapid switching,
and user avatar rendering
- Add EnvironmentFile=/home/txeo/Git/yo/cv/.env to systemd unit
- Add production overrides (GO_ENV, BEHIND_PROXY, ALLOWED_ORIGINS)
- Deploy workflow now auto-updates systemd service file on each deploy
- Add GLM-4.7-Flash as default Ollama model (replaces Mistral)
- Fix WRITE_TIMEOUT (15s→120s) and HTMX timeout (5s→120s) for local LLM
- Auto-warmup model on startup in development mode
- Add /api/chat/status endpoint for model readiness polling
- Show "Initializing AI model..." indicator while model loads
- Add user avatar (mdi:account) on chat messages
- Inject company/project/course sprite icons inline in chat responses
- Replace cramped header icons with 4 icon buttons + tooltips
(Compact, Side panel, Floating, Full screen)
- Add floating/draggable chat mode with smooth drag support
- Chip questions show user bubble instantly and clear input
- Help modal prefills input instead of auto-sending
- User bubble rendered client-side for immediate feedback
Bubbles:
- Teams-style layout: bot avatar (green circle) on left, message beside it
- User messages right-aligned, no avatar (clean, like Teams)
- Rounded bubbles (border-radius: 16px) instead of square
- Distinct corner radii for conversation flow
Navigation:
- Links no longer close the chat — panel stays open for continued navigation
- Added #certifications anchor (alias to courses section)
- Fixed agent instruction to use #courses for certifications references
Theme:
- All colors use CSS variables from _themes.css
- Automatically adapts to light/dark without explicit .theme-clean overrides
- Panel uses --paper-bg (white in light, dark in dark theme)
Size modes:
- 3 discrete toggle buttons: compact, half-screen, fullscreen
- Active state highlighted, direct selection (no confusing cycling)
- Removed chat-half-left (simplified to compact/half/full)
Intelligence:
- React query now returns results (verified: 4 companies + 2 projects + skills)
Avatars:
- Robot icon (green circle) before each agent message
- Person icon (dark circle) before each user message
- New .chat-bubble wrapper with flex layout for avatar + message
Dark theme fixes:
- Panel background: #1e1e1e (not pure black)
- Agent bubbles: #2d2d2d with light text (not dark/invisible)
- Input area: #2d2d2d (not black)
- Header stays green (--accent-green) in both themes
- Chips, suggestions consistent with panel background
Text overflow:
- overflow-wrap + word-break on messages
- min-width: 0 prevents flex overflow
- User bubble properly right-aligned with avatar
4 size modes cycled via expand button in header:
- Compact: 360px (default, bottom-right corner)
- Half-right: 50vw docked to right edge, full height
- Half-left: 50vw docked to left edge, full height
- Full: 100% viewport overlay
Also fixes text overflow in chat messages (overflow-wrap, word-break).
Messages area expands to fill available height in larger modes.
Size button uses mdi icons: arrow-expand, dock-right, dock-left, arrow-collapse.
CSS transitions for smooth size changes.
doc/29-AI-CHAT-SHOWCASE.md: comprehensive technical showcase covering
the AI-powered CV navigation feature for potential clients/employers.
9 technical decisions explained with code:
1. ADK Go 1.0 as agent framework
2. Single agent, single tool design
3. Cross-section search across all CV data
4. CV navigation links (GPS for the CV)
5. Dual-provider with auto-fallback (Gemini→Ollama)
6. Model warmup on chat open
7. HTMX + plain JS (no SPA framework)
8. Rate limiting (30 req/hour/IP)
9. Graceful degradation
Linked from README.md and doc index.
Agent instruction now requires markdown links to CV anchors:
- Companies: [Olympic Broadcasting](#exp-olympic-broadcasting)
- Projects: [Immich Photo Manager](#proj-immich-photo-manager)
- Sections: [Skills](#skills), [Experience](#experience)
formatResponse converts [text](#anchor) → clickable green links
that close the chat panel, smooth-scroll to the target, and
pulse a green highlight for 2 seconds.
All existing CV anchor IDs used: exp-{companyID}, proj-{projectID},
course-{courseID}, plus section IDs (experience, projects, skills, etc.)
Dual-provider architecture:
- Both Gemini and Ollama initialize at startup (if configured)
- Primary (Gemini) tried first for every request
- On any error (429, 503, timeout), automatically falls back to Ollama
- No manual switching needed — completely transparent to the user
- Log shows: "Primary failed (gemini: ...), falling back to ollama: ..."
Warmup:
- POST /api/chat/warmup called silently when chat panel opens
- Pre-loads Ollama model in background (10-15s) while user reads welcome
- By the time user types, model is ready for instant response
- Warms up fallback provider specifically (Gemini doesn't need it)
Timeout:
- Agent context increased to 60s (Ollama first response can be slow)
- Each request creates a fresh session (stateless for fallback compat)
Ollama adapter (internal/chat/ollama.go):
- Implements model.LLM interface for ADK Go
- Talks to Ollama's OpenAI-compatible API (/v1/chat/completions)
- Full tool/function calling support (tested with Mistral Small 3.2)
- Converts ADK types to OpenAI format (messages, tools, tool_calls)
- Configurable via OLLAMA_HOST and OLLAMA_MODEL env vars
Multi-provider handler:
- MODEL_PROVIDER env: "gemini" (default) or "ollama"
- Gemini: requires GOOGLE_API_KEY (pay-as-you-go recommended)
- Ollama: connects to local or Tailscale-remote instance
Rate limiter:
- 30 requests/hour per IP on /api/chat endpoint
- Uses existing middleware.NewRateLimiter pattern
Tested: Ollama + Mistral Small 3.2 on M4 Pro 64GB — correct answers
The Hyperscript trigger/call commands couldn't reliably trigger HTMX
form submissions or call global JS functions. Moved all chat
interactions to plain JavaScript:
- toggleChatPanel(): open/close panel + icon swap
- sendChatQuestion(q): set input + htmx.trigger(form, 'submit')
- closeChatHelpAndAsk(q): close modal + open chat + send question
- htmx:afterRequest listener clears input after submit
Hyperscript kept only for site-wide patterns (closeOnBackdrop) that
work reliably.
Also: better error message for rate-limited API responses (429).
- Replace flat list with <details>/<summary> accordion (5 categories)
- Questions are clickable: close modal → open chat → send question
- closeChatHelpAndAsk() helper bridges modal and chat panel
- Green accent on category icons and question hover
- Chevron arrows for expand/collapse state
- Dark theme support for all accordion elements
- Compact layout with no wasted space
- Move chat-widget outside the floating buttons section in index.html
- Remove fixed-btn class from toggle button (was inheriting left-side
positioning from the button stack's mobile flex layout)
- Chat widget now renders independently just before body-scripts
Position fix:
- Remove _chat.css @import from main.css (was overriding with old
left:2rem cached version). Chat CSS now loaded only via head-styles.
- Button confirmed at right:2rem, bottom:6rem (above back-to-top)
Help modal:
- New chat-help-modal.html using same <dialog> pattern as shortcuts
- 6 organized categories: Experience, Technologies, Projects,
Education, Skills, How it works
- Bilingual EN/ES with example questions per category
- ? button in header opens modal via commandfor/show-modal
- Removed inline help card (modal replaces it)
Intelligence:
- Comprehensive query strategy for 8 question types
- Technology queries always use cross-section search
- Company queries use experience without filter for full listing
- Agent knows CV site is built with Go/HTMX (bonus context)
- Skills report proficiency levels when technology found
CSS:
- Button moved to right: 2rem, above back-to-top (bottom: 6rem)
- Uses CV design tokens: --black-bar, --accent-blue, --paper-bg
- Fonts: Quicksand (header), Source Sans Pro (body)
- Tooltip on the left side (tooltip-left class)
- Dark theme uses CV-consistent grays
Intelligence:
- Agent instruction emphasizes exhaustive reporting of ALL matches
- Cross-section search results must not be truncated
- Mentions CV site itself is built with Go when relevant
Tests:
- Updated positioning assertions (right side, x > viewport/2)
- Added 5 intelligence tests: Go cross-section, company count,
years of experience, React cross-section, Spanish response
- Resilient to API errors (waits for any message, not just user)
- 42 total test assertions
- Mascot identity: robot-happy-outline icon, "CV Assistant" branding
- Help popup: onboarding card explaining what the mascot can do (EN/ES)
- Suggested questions: 5 clickable chips that auto-submit (bilingual)
- Typing indicator: three bouncing dots during agent response
- Icon swap: mascot icon ↔ close icon via Hyperscript class toggle
- Dark theme support for all new elements
- Modular CSS loading in development, chat CSS always loaded separately
Chat button and panel now anchor from left: 2rem to match the
zoom, shortcuts, and other fixed buttons. Panel opens rightward
so content is always visible.
- agent.go: add section="search" that queries experience, projects,
skills, and courses simultaneously — fixes missing results when
a technology spans multiple CV sections (e.g. Java at Insa)
- head-styles.html: use modular CSS in development mode and load
chat CSS separately — fixes unstyled page when bundle is stale
- doc/28-AI-CHAT-AGENT.md: comprehensive technical documentation covering
architecture, agent design, query_cv tool, HTMX integration, graceful
degradation, security, and example conversations
- README.md: add AI Chat Agent section with examples, ADK Go badge,
updated tech stack and documentation index
- doc/00-GO-DOCUMENTATION-INDEX.md: add chat agent to doc index
Visitors can ask questions about the CV via a floating chat panel.
The agent uses Gemini to answer questions about experience, projects,
skills, and education by querying the cached CV JSON data.
- internal/chat/agent.go: LLM agent with query_cv tool that searches
CV data by section (experience, projects, skills, etc.) with keyword filtering
- internal/chat/handler.go: POST /api/chat endpoint with session management,
graceful degradation when GOOGLE_API_KEY is not set
- chat-widget.html: HTMX-powered floating chat panel with Hyperscript toggle
- _chat.css: Responsive chat UI with dark theme support
- Wired into existing architecture via dependency injection (CVHandler,
routes, main.go) — zero breaking changes, all existing tests pass
Main project URLs now point to drolosoft.com product pages with
language-aware links. GitHub repos are shown via a new badge next
to the existing LIVE badge.
juanatsap