Spaces:
Sleeping
Sleeping
Commit History
-
docs: Correct data-source key finding in audit checklist
e3af7e2 -
feat: JSON-mode structured outputs for critic scoring
- llm_client.query gains json_mode: response_format json_object on Groq/OpenRouter, responseMimeType application/json on Gemini; validated against all three live providers - Critic evaluation now requests JSON mode; existing brace-slice parsing retained as fallback - Fix stale LANGCHAIN_PROJECT name in .env.example04accf1 -
feat: Vite 7 + React 19 upgrade and SSE status streaming
- Frontend majors: vite 5->7.3.6, react 18->19.2.7, plugin-react-swc 3->4; Docker frontend builder node:20 -> node:22-slim (Vite 7 floor) - SSE: GET /workflow/{id}/events streams status snapshots on change (1s cadence, 15min connection cap); frontend uses EventSource first and falls back to the original 700ms polling on stream failure - Rewrite stale ActivityLog tests against the current component API (old tests targeted a removed 'entries' prop); add missing @testing-library/dom peer dep - suite now 10/10 - Fix two shadcn empty-interface lint errors; eslint now 0 errorsf7d988e -
feat: Harden API, pin dependencies, and enable pytest CI gate
- /health/deep: 1-token ping per configured LLM provider (key presence no longer masquerades as a working model) - Abuse guards on POST /analyze: per-IP rate limit (10/h), concurrent workflow cap (3), and 1h TTL eviction for the in-memory store - CORS: hf.space subdomains via allow_origin_regex (literal wildcard was a no-op); drop unused allow_credentials - Lifespan handler replaces deprecated @app.on_event startup hook - Cache-Control: immutable for hashed /assets, no-cache for the shell - Dependencies: requirements.in + uv-compiled fully pinned requirements.txt (captures the exact resolution validated by today's live canary); Dockerfile uses npm ci for the frontend - Tests: replace live-integration test (needed API keys, imported deleted graph_cyclic) with unit tests for loop routing; pytest added to CIe926e7e -
ci: Add CI, HF Space auto-mirror, and weekly live canary workflows
- ci.yml: flake8 critical errors + import smoke (backend), npm ci + build with non-blocking lint (frontend); existing tests are live integration tests requiring API keys, so they are not a CI gate yet - deploy-hf.yml: mirror main to the HF Space on every push via HF_TOKEN - canary.yml: weekly health checks (keeps free-tier Spaces awake) plus a full end-to-end analysis asserting LLM provider, SWOT sections, and data-source coverage — catches silent model/API rot2407b4d
-
docs: Update audit checklist progress
3723ba5 -
fix: Migrate to living LLM models and defuse stale production config
- Default models updated: Groq llama-3.1-8b-instant (deprecated 2026-06-17) -> openai/gpt-oss-20b; Gemini gemini-2.0-flash (shut down 2026-06-01) -> gemini-flash-lite-latest; OpenRouter delisted gemma-3n free model -> openai/gpt-oss-20b:free - Remove frontend/.env.production pointing at the torn-down AWS API Gateway (would have been baked into the next HF Space build) - Fix stale A2A researcher URL in .env.example - Cap langchain/langgraph/langchain-core below 1.0 to match the known-good deployed build until proper lockfile pinning lands - Add docs/audit_checklist.md from the 2026-07 technical auditf26a13c
-
Initial commit: Instant SWOT Agent
Multi-agent strategic analysis system with: - Research Gateway (A2A client to Researcher-Agent) - Analyzer, Critic, Editor workflow nodes - Data grounding enforcement in all LLM calls - React frontend with real-time progress 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>0c591a7