Commit History

  1. fix: add missing uuid id generation for new Google OAuth users Running

    2b144e1
  2. fix: correct avatar_url field name in Google OAuth callback; add pool_pre_ping for Neon connection stability

    dda0d24
  3. fix: add pool_pre_ping and pool_recycle to prevent stale Neon connection errors

    4b9badf
  4. chore: clean up diagnostic print statements from main.py

    7a3fa9f
  5. debug: add print checks for prometheus.yml contents

    6eaeadc
  6. debug: add GRAFANA_API_KEY diagnostic prints

    071242a
  7. fix: use request.url.hostname in proto middleware to resolve AttributeError

    14c91e1

  1. fix(observability): create prometheus multiproc dir automatically on startup

    8ae944d
  2. fix(auth): add fallback profile fetch from Google userinfo API

    dc27da6
  3. debug: add startup diagnostics for Google OAuth credentials

    0705a4f
  4. fix(auth): implement manual state restoration fallback for OAuth callback

    75f0c2f
  5. fix(auth): enable same_site none and https_only for cross-domain OAuth cookies

    8143708
  6. fix(auth): trust reverse proxy headers and force HTTPS scheme in production

    e6ff8f6

  1. fix(agent): handle non-dict LLM response gracefully and delay setting task to FAILED during Celery retries

    6ae9355
  2. feat(api): filter cases by authenticated user and protect endpoints

    1ba28b2
  3. feat(api): add endpoint to list past cases

    0e149eb
  4. feat(auth): implement Google OAuth and Email/Password authentication

    5d3cd52

  1. clean up celery_worker.py by removing rate-limit delays and logs for paid Gemini key

    b841b71
  2. revert LLMService back to official Google GenAI SDK

    db48c8b

  1. optimize search result limit to 2 and sleep delay to 12s for OpenRouter free tier stability

    1bc3290
  2. add 4-second rate-limiting delay between hypothesis evaluations to respect free tier limits

    957c1df
  3. refactor LLMService to route Gemini requests through OpenRouter

    f496440
  4. integrate ResearchAgent loop and update_hypothesis database updates in Celery worker

    a5f8d50

  1. implement ResearchAgent with search formulation and synthesis loops

    179446d
  2. replace duckduckgo-search with ddgs package and implement search tool

    0b191da
  3. add duckduckgo search tool utility for agent web research

    50b9615
  4. feat: installed the duckduckgo-search via uv

    820dc96

  1. fix: enforce PROMETHEUS_MULTIPROC_DIR at metrics layer top of file to fix multiprocess isolation

    c281923
  2. feat: configure prometheus multiprocess metrics collection for celery and fastapi

    3deefdf
  3. feat: add prometheus metric tracking for token counts, agent latency, and failure rates

    76340c7
  4. feat: mount prometheus metrics app on /metrics endpoint in fastapi gateway

    62344a7

  1. feat: setup prometheus and grafana docker services and initialize core observability metrics

    7972f6e
  2. chore: upgrade default gemini model to 2.5-flash and remove hardcoded models

    d1e4ef4
  3. feat: migrate decompose route to enqueue async celery jobs with 202 accepted response

    a5b0080
  4. feat: setup celery app initialization and async run_case_manager_task task

    418ffb4

  1. feat: complete FastAPI gateway routes and entry point integration

    3ab2751
  2. feat: implement CaseManagerAgent and BaseAgent harness execution pipeline

    2724990

  1. feat: implement google gemini llm helper service with structured json configuration

    8419ecc
  2. feat: implement shared context manager for Postgres mapping and context state updates

    b27ea06

  1. fix: resolve db sslmode string space and foreign key table naming

    1826316
  2. feat: created neon db connection using sqlalchemy

    2c7c156

  1. feat: define shared context data contracts and configure uv project metadata

    c6f5784

  1. feat: added files and folders

    b1b23df