Skip to content

Simplify the docs and stabilize Qwen replay output - #79

Merged
bigboateng merged 3 commits into
mainfrom
codex/plain-documentation
Oct 13, 2026
Merged

bigboateng merged 3 commits into
mainfrom
codex/plain-documentation

Conversation

@bigboateng

@bigboateng bigboateng commented Oct 13, 2026 •

Copy link
Copy Markdown
Contributor

Change contract

When: A developer starts using Pitot or looks up host setup and control boundaries.
Before: The README combines a long setup reference with images, and some examples overstate runtime telemetry or omit source-build pin limits. The Qwen CI fixture can select a pipe-output path that resolves before all output is collected.
After: A short, plain README links dedicated host, runtime and protocol references, prioritizes Codex, Qwen and DeepSeek, and introduces the offline supervisory-control example. The Qwen test fixture uses its supported terminal mode and rejects pipe fallback before its canary executes.

Boundaries preserved

  • All eleven documented hosts and the existing native macOS/Linux/Windows CI matrix remain covered.
  • Runtime control remains limited to supported actions; documentation explicitly states shell, trust, privacy and failure boundaries.
  • Qwen configuration changes are confined to the isolated CI fixture. Agent versions, product behavior and the full allow/deny evidence gate remain unchanged.
  • Incomplete runs expose bounded receipt counts; malformed or oversized receipts report unavailable without exposing their contents.

Evidence

Scenario or check Expected result Observed result
Actual Qwen terminal and pipe probes on macOS Terminal returns nonce-bound result; pipe is rejected before execution receipt 10 terminal passes and 10 pipe rejections
Canary, protocol and receipt regression tests Reject fallback and malformed diagnostics; preserve correlated native results Focused checks pass
Formatting, static analysis and full maintenance suite Clean generated and source checks Pass; 236 maintenance tests, 3 platform-specific skips
Native authenticated capture Complete current evidence across all three operating systems All 33 native cells passed
Final PR CI Exact-head checks and current agent/runtime report 49 checks passed; 33 agent and 3 runtime cells pass

Failure and recovery

A missing terminal or incomplete agent trajectory still fails CI. Revert fixture changes and regenerate their authenticated capture together if recovery is needed.

Remaining limits

The earlier Linux failure's exact process event ordering was not retained. A synthetic event sequence demonstrates the pipe-output loss mechanism; local native probes did not reproduce that original failure. Finite replay tests do not establish universal host behavior or live provider availability. The supervisory replay example remains documented for macOS/Linux.

@github-actions

Copy link
Copy Markdown

Pitot coding-agent E2E

These results come from this repository's CI at the commit shown below; the README links to the latest main status.

Agent Ubuntu macOS Windows Result Evidence
Claude ✅ Pass · real CLI 2.1.296 · native · binary-observed anthropic messages ✅ Pass · real CLI 2.1.296 · native · binary-observed anthropic messages ✅ Pass · real CLI 2.1.296 · native · binary-observed anthropic messages ✅ Passing All platforms are required
Cursor ✅ Pass · real CLI 2026.10.01-e373342 · native · binary-observed cursor connect proto ✅ Pass · real CLI 2026.10.01-e373342 · native · binary-observed cursor connect proto ✅ Pass · real CLI 2026.10.01-e373342 · native · binary-observed cursor connect proto ✅ Passing All platforms are required
Codex ✅ Pass · real CLI 0.162.1 · native · binary-observed openai responses ✅ Pass · real CLI 0.162.1 · native · binary-observed openai responses ✅ Pass · real CLI 0.162.1 · native · binary-observed openai responses ✅ Passing All platforms are required
Devin ✅ Pass · real CLI 3000.11.3 · native · binary-observed devin connect proto ✅ Pass · real CLI 3000.11.3 · native · binary-observed devin connect proto ✅ Pass · real CLI 3000.11.3 · native · binary-observed devin connect proto ✅ Passing All platforms are required
DeepSeek Harness ✅ Pass · real CLI 0.2.0-rc.2 · native · binary-observed openai chat ✅ Pass · real CLI 0.2.0-rc.2 · native · binary-observed openai chat ✅ Pass · real CLI 0.2.0-rc.2 · native · binary-observed openai chat ✅ Passing All platforms are required
GitHub Copilot CLI ✅ Pass · real CLI 1.0.95 · native · binary-observed openai chat ✅ Pass · real CLI 1.0.95 · native · binary-observed openai chat ✅ Pass · real CLI 1.0.95 · native · binary-observed openai chat ✅ Passing All platforms are required
Gemini ✅ Pass · real CLI 0.63.0 · native · binary-observed gemini generate content ✅ Pass · real CLI 0.63.0 · native · binary-observed gemini generate content ✅ Pass · real CLI 0.63.0 · native · binary-observed gemini generate content ✅ Passing All platforms are required
Kimi Code ✅ Pass · real CLI 2.1.1 · native · binary-observed openai chat ✅ Pass · real CLI 2.1.1 · native · binary-observed openai chat ✅ Pass · real CLI 2.1.1 · native · binary-observed openai chat ✅ Passing All platforms are required
OpenCode ✅ Pass · real CLI 2.0.27 · native · binary-observed openai responses ✅ Pass · real CLI 2.0.27 · native · binary-observed openai responses ✅ Pass · real CLI 2.0.27 · native · binary-observed openai responses ✅ Passing All platforms are required
Pi ✅ Pass · real CLI 1.1.0 · native · binary-observed openai chat ✅ Pass · real CLI 1.1.0 · native · binary-observed openai chat ✅ Pass · real CLI 1.1.0 · native · binary-observed openai chat ✅ Passing All platforms are required
Qwen Code ✅ Pass · real CLI 0.25.1 · native · binary-observed openai chat ✅ Pass · real CLI 0.25.1 · native · binary-observed openai chat ✅ Pass · real CLI 0.25.1 · native · binary-observed openai chat ✅ Passing All platforms are required

Runtime capabilities

Capability Ubuntu macOS Windows Result
pitot request ✅ Pass · real runtime allow/deny ✅ Pass · real runtime allow/deny ✅ Pass · real runtime allow/deny ✅ Passing

Source commit: 1852eef555ee

@bigboateng
bigboateng merged commit cb08fb0 into main Oct 13, 2026
49 checks passed
@bigboateng
bigboateng deleted the codex/plain-documentation branch October 13, 2026 17:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant