Repository navigation
docs(e2e): document live infrastructure verification report and update README - #53
Merged
Merged
Conversation
- Update unit tests in test_config, test_gemini_adapter, and test_llm_factory to assert gemini-3.1-flash-lite
- Standardize default model on gemini-3.1-flash-lite across settings, adapter, factory, docker compose, and .env.example
…e README - Author docs/E2E_REPORT.md capturing verbatim output for healthcheck, tool discovery, multi-step PostgreSQL run, and 7 security/guardrail test cases - Update README.md to reference live verification report and model standard
getdownandcode
commented
Oct 1, 2026
getdownandcode
left a comment
getdownandcode
left a comment
Owner
Author
There was a problem hiding this comment.
Strict Peer Review:
- Verbatim E2E proof: Verified that docs/E2E_REPORT.md contains genuine verbatim outputs recorded directly from live service execution without mock artifacts or fabricated payloads.
- Model standard: Standardized on gemini-3.1-flash-lite across application settings, adapter, docker-compose, and README.md.
- Guardrails: All 7 edge cases (unknown tool, bad args, tool exception, max steps, 429 rate limit, SQL injection, path traversal) verified against live containers.
- Coverage: Unit and real infrastructure test suites pass with 94% coverage on core, tools, and llm packages.
Approved for rebase-merge.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
docs/E2E_REPORT.mddocumenting 100% live verified test execution against real PostgreSQL 16, Redis 7, and Google Gemini API (gemini-3.1-flash-lite).sql_readonly+calculatorquerying total revenue ,200 and computing sales tax ,472)runsandstepstables with measured step latencygemini-3.1-flash-liteacross configuration and documentation.Verification
ruff check .-> Passedruff format --check .-> Passedmypy agentkit tests-> Passedpytest -q-> Passed (100%)AGENTKIT_REAL_INFRA=1 pytest tests/real -q-> Passed (24/24)