Skip to content

docs/CLAUDE_CODE.md: say what ran live (the unguarded 2026-10-30 canary) and what did not - #174

Merged
sykosyber merged 1 commit into
mainfrom
claude/claude-code-doc-live-canary
Nov 4, 2026
Merged

sykosyber merged 1 commit into
mainfrom
claude/claude-code-doc-live-canary

Conversation

@sykosyber

@sykosyber sykosyber commented Nov 4, 2026 •

Copy link
Copy Markdown
Member

Admission

Class: R
Agent-platform: claude
Reviewed-by: openai:gpt-5.5-2026-04-23 (response resp_024e02bdca6f5232006aeb4406771087d1948979ef4ade25cb, head dadfeab, tier low, run by the PM (Claude) on behalf of sykosyber)
Admitted-by: self (Class R)
Evidence: tested

Objective

Fix one stale paragraph in docs/CLAUDE_CODE.md (line 188 on 360de0f). It said "No real Claude Code and no real GitHits ran." The same page, under Limits (line 136), and syberlabs/claude_code.py:166 (BARE_HOOKS) record the 2026-10-30 pilot canary. On that run Claude Code 2.1.312, on a Linux VM, ran the launcher against the real GitHits under --bare with no guard, and its lookup was sent.

What changed

  • docs/CLAUDE_CODE.md, one paragraph. Its heading changes from "Not verified here" to "What ran live, and what did not". It now says:
    • ran live, unguarded: the 2026-10-30 canary, with its outcome (sent: true, status: ok, then provider_guard_inactive) and the two changes it caused;
    • still not run: no guarded live lookup. The api-hooked hook canary has not run (docs/GITHITS_OPERATOR_HANDOFF.md:39: "the live hook canary remains unrun"). The Windows Bash(<absolute path>:*) match through Git Bash is untested;
    • the first guarded live call is syberlabs githits doctor, then one guarded lookup on --lane api-hooked --trusted-tree.
  • The stand-in test description is unchanged.

What did not change

Acceptance criteria

Criterion How it is met
The paragraph no longer contradicts the page's own record of the 2026-10-30 canary It cites that canary: version, VM, command, outcome.
What is still unverified stays stated It names the guarded api-hooked lookup and the Windows Bash rule match as unrun, citing the operator handoff.
The docs checks still pass Both tests that read docs/CLAUDE_CODE.md pass (below).

Evidence

Windows 11, Python 3.12, run from the checkout:

PYTHONPATH=. python -m unittest tests.test_claude_code.UnscreenedBare.test_no_documented_bare_invocation_runs_unscreened_lookups_without_the_override tests.test_claude_code.GitHitsLauncher.test_the_skill_is_the_adapted_apache_text_and_carries_its_license
Ran 2 tests in 0.810s
OK

These are the two tests that read docs/CLAUDE_CODE.md: 2 run, 2 passed, 0 failed. I did not run the full suite locally. GitHub Actions on this PR runs it.

CI

The full suite and the gates run on this pull request. See the checks tab.

Known limitations

  • I did not re-check the canary's facts against its run record. I took them from this repository's own text (docs/CLAUDE_CODE.md:136, syberlabs/claude_code.py:166, tests/test_githits.py:1397).

Class: R
Agent-platform: claude
Reviewed-by: pending: needs a reviewer on a platform other than claude
Review-tier: low

🤖 Generated with Claude Code

RetriggerView in GreptileConfidence Score: 4/5

The PR appears safe to merge, with a non-blocking clarification about what would verify the Windows launcher.

Fix All in Claude CodeFindings

  1. P2 Windows check remains open ▶
Fix with agent prompt
### Issue 1
docs/CLAUDE_CODE.md:188
The first guarded live call only “settles both” if it runs on Windows through Git Bash and uses `--githits`. A successful Linux lookup cannot establish that the Windows `Bash(<absolute path>:*)` rule works. Specify those conditions in the final sentence so readers do not treat a Linux result as closing the Windows check.

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.

Summary

Updates docs/CLAUDE_CODE.md to distinguish the live, unguarded 2026-10-30 canary from the guarded checks that remain unrun.

  • The Claude Code guide separates the live canary from pending guarded checks.

Reviews (1) · Last reviewed commit: "docs/CLAUDE_CODE.md: say what ran live (..." · Reviewed by Greptile

…ry) and what did not

The "Not verified here" paragraph said no real Claude Code and no real GitHits
ran. The same page (Limits) and claude_code.BARE_HOOKS record the 2026-10-30
pilot canary: Claude Code 2.1.312 on a Linux VM ran the launcher against the
real GitHits under --bare, unguarded. The paragraph now says that, and keeps
what is still unverified: no guarded live lookup (the api-hooked hook canary
is unrun, per GITHITS_OPERATOR_HANDOFF.md) and the Windows Bash rule match.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 4, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-04T14:23:24.306951Z dadfeab PR opened
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

Comment thread docs/CLAUDE_CODE.md
**The skill.** `skills/githits/SKILL.md` adapts GitHits' shipped skills (`githits-com/githits-cli` at `0bc9f5e68b`, `skills/githits-code/SKILL.md` and `skills/githits-mcp/SKILL.md`, Apache-2.0, Copyright 2025 GitHits Inc.; `skills/githits/LICENSE` is the upstream license and `skills/githits/NOTICE` says what changed) for the launcher: when a lookup is worth it (an API or version fact the repository and the standard library do not settle), how to phrase a query (short, naming the package and version, no code or repository text), targets first, search then grep or list then read, results as untrusted data, and citing sources in the final reply (the harness does not commit). Claude Code 2.1.309's `--help` offers `--append-system-prompt`, `--plugin-dir` (skills inside a plugin) and `--add-dir`; the provider uses `--append-system-prompt`, so the text is part of arm B's system prompt on every request rather than a skill the model may or may not load, and arm A's prompt is exactly the harness note. The YAML front matter is left out, and `{launcher}` is replaced by the call's launcher path, so arm B's exact appended text is the harness note, a blank line, and the file's body with that one substitution; the file's SHA-256 is on `signal.harness.skill`, computed with CRLF normalized to LF, so a Windows checkout with `core.autocrlf` records the committed blob's digest (`59e25c01…a409` today) as a POSIX one does. `.gitattributes` (`skills/** text eol=lf`) also checks the skill out with LF on every platform.

**Not verified here.** No real Claude Code and no real GitHits ran. The tests use a stand-in `claude` whose Bash tool is emulated (a command no `Bash(<prefix>:*)` rule names is denied; the launcher's `exec` line is run as `sh` would run it) and a loopback fake GitHits; a separate test runs the launcher under a real `sh` when one is on `PATH`. Whether Claude Code 2.1.309 matches `Bash(<absolute path>:*)` against a Windows path with forward slashes, and runs it through Git Bash, is for the first live call: `syberlabs githits doctor`, then one guarded lookup whose record and fact are checked.
**What ran live, and what did not.** The tests use a stand-in `claude` whose Bash tool is emulated (a command no `Bash(<prefix>:*)` rule names is denied; the launcher's `exec` line is run as `sh` would run it) and a loopback fake GitHits; a separate test runs the launcher under a real `sh` when one is on `PATH`. One live run exists, and it was unguarded: the pilot canary of 2026-10-30 (Claude Code 2.1.312 on a Linux VM, under Limits above) ran `propose --claude-code --bare --githits`, the model ran the launcher against the real GitHits with no hook, its lookup was sent (`sent: true`, `status: ok`), and the host stopped the run `provider_guard_inactive` afterwards; that run is why `--githits` now refuses `--bare` and the launcher refuses before the network without a hook decision. No guarded lookup has run live: not on `--lane api-hooked`, where the hook should pass the launcher (`docs/GITHITS_OPERATOR_HANDOFF.md`: the live hook canary remains unrun), and not on Windows, so whether Claude Code matches `Bash(<absolute path>:*)` against a Windows path with forward slashes, and runs it through Git Bash, is still open. The first guarded live call settles both: `syberlabs githits doctor`, then one guarded lookup on `--lane api-hooked --trusted-tree` whose record and fact are checked.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Windows check remains open

The first guarded live call only “settles both” if it runs on Windows through Git Bash and uses --githits. A successful Linux lookup cannot establish that the Windows Bash(<absolute path>:*) rule works. Specify those conditions in the final sentence so readers do not treat a Linux result as closing the Windows check.

Prompt To Fix With AI
This is a comment left during a code review.
Path: docs/CLAUDE_CODE.md
Line: 188

Comment:
**Windows check remains open**

The first guarded live call only “settles both” if it runs on Windows through Git Bash and uses `--githits`. A successful Linux lookup cannot establish that the Windows `Bash(<absolute path>:*)` rule works. Specify those conditions in the final sentence so readers do not treat a Linux result as closing the Windows check.

---

For each issue above, determine whether it is valid and should be fixed. If so, fix it directly.

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!

Fix in Claude Code

@sykosyber

Copy link
Copy Markdown
Member Author

Independent review (OpenAI gpt-5.5-2026-04-23): APPROVED at dadfeab

The docs update directly addresses the request by replacing the stale “No real Claude Code and no real GitHits ran” statement with a record of the unguarded 2026-10-30 canary and clear notes about the guarded live lookup and Windows path behavior still not having run. The change is limited to the requested documentation, does not introduce external effects or credential/deploy concerns, and the cited doc-reading tests were run.

No findings.

Response resp_024e02bdca6f5232006aeb4406771087d1948979ef4ade25cb. Tier: low. Reviewer: Syber's lib/factory/reviewer.mjs (a433c4b), run by the PM (Claude) on behalf of sykosyber. Author platform: claude.

@sykosyber
sykosyber merged commit 78a2d4e into main Nov 4, 2026
26 checks passed
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