Skip to content

fix(deliberation): stop passing --markdown/--limit to graph probe commands - #470

Merged
solomonneas merged 1 commit into
mainfrom
fix/issue-442-deliberation-probe-flags
Jul 24, 2026
Merged

fix(deliberation): stop passing --markdown/--limit to graph probe commands#470
solomonneas merged 1 commit into
mainfrom
fix/issue-442-deliberation-probe-flags

Conversation

@solomonneas

Copy link
Copy Markdown
Collaborator

What

The deliberation scope planner appended --markdown --limit 8 to every graphtrail call, but only context accepts those flags. callers, callees, and impact reject them and exit non-zero, so the planner always derived a single evidence scope and rejected every --deliberate plan before dispatch.

This is the direct cause of route C's 0/10 in the #442 experiment: 8/8 cases failed pre-dispatch with deliberation could not assemble enough grounded GraphTrail evidence scopes and route C never made a model call.

Change

  • _graphtrail_markdown is now _graphtrail_scope_text and only passes --markdown --limit 8 on the context probe.
  • Regression test with a fake graphtrail binary that mirrors the installed CLI's flag surface (rejects --markdown/--limit on the three probe commands). The existing tests mocked derive_evidence_scopes wholesale, which is why this was never caught.

Verify

./scripts/verify passed locally (Brigade verify run 20260724-010851-work-verify-e2ec06, exit 0). The new test fails on main and passes here.

Notes for review

This fixes the mode's entry path; it takes no position on whether the flag stays. That call is tracked in #442 and the experiment scoring there was produced with the mode broken, so route C remains unmeasured until a rerun.

Refs #442

…mands

The scope planner appended --markdown --limit 8 to every graphtrail call,
but only 'context' accepts those flags. callers, callees, and impact
reject them and exit non-zero, so the planner always derived a single
evidence scope and rejected every deliberation plan before dispatch
(issue #442 experiment, route C: 8/8 pre-dispatch failures).

Pass the markdown flags only on the context probe and add a regression
test with a fake graphtrail binary that mirrors the real CLI's flag
surface.

Co-authored-by: Claude <noreply@anthropic.com>
@coderabbitai

coderabbitai Bot commented Jul 24, 2026

Copy link
Copy Markdown

Important

Review skipped

Auto reviews are limited based on label configuration.

🏷️ Required labels (at least one) (1)
  • coderabbit-review

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Repository: escoffier-labs/coderabbit/.coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: b8fb1dea-d9d6-4889-b1b2-bb8b0bda57e4

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • 🔍 Trigger review
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch fix/issue-442-deliberation-probe-flags

Comment @coderabbitai help to get the list of available commands.

@solomonneas solomonneas self-assigned this Jul 24, 2026
@solomonneas
solomonneas merged commit cdeaff1 into main Jul 24, 2026
28 checks passed
@solomonneas
solomonneas deleted the fix/issue-442-deliberation-probe-flags branch July 26, 2026 20:38
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