- Wire next-themes ThemeProvider in layout with class strategy, defaultTheme=dark
- Define all Gemini colors as CSS custom properties (--gem-*) in globals.css
with light (:root) and dark (.dark) variants
- Replace all hardcoded hex colors across 7 Gemini components with var() refs
- Add Sun/Moon toggle button in GeminiTopbar (right side, before Settings)
- Theme persists to localStorage via next-themes (key: gem-theme)
- Dark theme renders identically to before (same hex values)
- Light theme: white bg, light gray surfaces, same blue-purple accent gradient
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Instead of pre-creating an empty placeholder assistant message when
streaming starts (which races with GeminiTypingIndicator rendering),
wait until the first SSE token arrives to create the message. This
guarantees only one row is ever visible: either the typing indicator
(before tokens) or the GeminiMessage (after first token).
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
{ticket_id:str} was matching /api/tickets/summary before the literal route.
Changing to {ticket_id:uuid} restricts matching to UUID format only.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Replace module-level _current_model global with contextvars.ContextVar
to prevent concurrent requests from overwriting each other's search
strategy (flash vs pro)
- Add GET /api/tickets/summary returning {total, by_status, by_priority}
aggregated from Gongdan API, registered before parameterized ticket routes
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Skip rendering the empty placeholder assistant message while isLoading
is true — the GeminiTypingIndicator already shows the gem icon with
bouncing dots. Once tokens arrive and content is non-empty, the message
renders normally via GeminiMessage.
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
FCR-1: Set ignoreBuildErrors to false in next.config.mjs
FCR-2: Default API_URL to production backend so static builds work correctly;
.env.local overrides to localhost for local dev
FCR-3: Remove createConversation call in handleSend; generate UUID client-side
and let backend streamChat auto-create the conversation to avoid duplicate writes
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Create deploy-frontend.yml workflow using Azure/static-web-apps-deploy@v1.
Add output: 'export' to next.config.mjs for static site generation.
Static Web App created in Operation resource group (soc-frontend, Free tier).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add frontend/lib/api.ts with typed API client for conversations, tickets, and SSE chat streaming
- Replace simulateAIResponse() with real SSE streaming via POST /api/chat/stream
- Replace MOCK_CONVERSATIONS with GET /api/conversations
- Replace MOCK_TICKETS with GET /api/tickets
- Lift activeTools and selectedModel state from GeminiInput to GeminiChat for API integration
- Load conversation messages on demand via GET /api/conversations/{id}
- Backend URL configured via NEXT_PUBLIC_API_URL in .env.local
Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
ticketNumber (e.g. TK-2026-296691) was being used as id, causing
GET /api/tickets/{id} to 404 on upstream Gongdan API which expects UUID.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Azure Oryx could not find packages installed to .python_packages/.
Add a startup.sh script that sets PYTHONPATH to include the bundled
package directory before launching gunicorn. Update workflow to set
the Web App startup command to use startup.sh.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The previous workflow installed dependencies with pip --target and zipped
them into the deployment package. Azure Oryx runtime could not find
the packages because it looks for antenv/ or __oryx_packages__/, not
.python_packages/. Switch to deploying source-only zip with az webapp
deploy, letting SCM_DO_BUILD_DURING_DEPLOYMENT=true trigger Oryx to
run pip install on the server and create the antenv virtualenv.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Use azure/login@v2 with OIDC (Federated Identity) instead of publish-profile
- Remove auto-generated main_soc-backend.yml (wrong paths)
- Fix deployment package to include backend/ directory properly
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add web_search tool with Jina Search/Reader/Rerank
- Flash mode: top 3, 8s timeout, no Reader/Rerank
- Pro mode: top 10, 20s timeout, concurrent Reader + Rerank top 5
- Add Redis async cache (TTL=300s) for search results
- Register "search" in ALL_TOOLS mapping
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add complete Python backend (Litestar + LangGraph) with chat, conversations, tickets APIs
- Add GitHub Actions workflow for auto-deploying backend to Azure Web App (soc-backend)
- Add gunicorn to requirements.txt for production serving
- Update CLAUDE.md and EXTERNAL_SERVICES.md with latest config
- Remove obsolete claudehd.md (merged into gpthd.md)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
