Skip to content

docs(health): record day-to-day operating defaults for pyauto-brain health - #10

Merged
Jammy2211 merged 4 commits into
mainfrom
claude/health-agent-e2e-run-w5slh7
Jul 6, 2026
Merged

docs(health): record day-to-day operating defaults for pyauto-brain health#10
Jammy2211 merged 4 commits into
mainfrom
claude/health-agent-e2e-run-w5slh7

Conversation

@Jammy2211

Copy link
Copy Markdown
Contributor

What

Adds a "Day-to-day defaults (operating agreement)" section to agents/health/AGENTS.md, capturing the presentation/triage conventions converged on during the first end-to-end run of the PyAutoBrain Health Agent.

Why

The M5 unified-dashboard merge made this the first real pyauto-brain health run. The run surfaced a set of rendering/triage decisions that weren't yet written down. Recording them means future runs inherit a consistent default instead of re-deriving it each time. These are presentation/triage conventions only — the verdict is still adopted from Heart verbatim; no gating logic is added or changed.

What's in the note

  • Default surface — lead with the pyauto-heart dashboard --md mobile card, then the structured report.
  • Grouping — reasons ordered by severity, then capability.
  • Unknown-CI tiles — a repo with an unresolved required-workflow conclusion on main HEAD renders as CI in_progress (an unknown, not an active run) and doesn't enter readiness.yellow_reasons; keep such tiles visually secondary.
  • Local-checks-blind — when repo_state is present: false (repos outside PYAUTO_ROOT), the local half of Heart observes nothing; say so and downgrade confidence rather than reading silence as verified-clean. Cite the one-time PYAUTO_ROOT fix.
  • fix citations — cite pyauto-heart fix <ci|dirty|drift|timing> only when Heart's verdict names that failure class.
  • Staleness — downgrade confidence and recommend pyauto-heart tick on a stale board.
  • Expected first-run gaps vs. real problems — the standing YELLOW unknowns (no test-run report, install verification not run, no release validation) are baseline, not action items.

Scope

Single-file docs change (agents/health/AGENTS.md, +35 lines). No code, no checks, no gating behaviour touched. Observer-only boundary preserved.

🤖 Generated with Claude Code

https://claude.ai/code/session_01RLqU83iWW3R7ks33TzSyYs


Generated by Claude Code

…ealth

Capture the conventions converged on during the first end-to-end Health
Agent run: md mobile card as the default surface, severity-then-capability
reason grouping, unknown-CI tiles kept secondary, an explicit
local-checks-blind confidence downgrade when repos live outside PYAUTO_ROOT,
fix-citation discipline, staleness handling, and the expected-first-run-gap
vs real-problem separation. Presentation/triage only — the verdict is still
adopted from Heart verbatim.

Co-Authored-By: Claude <noreply@anthropic.com>
Copilot AI review requested due to automatic review settings July 3, 2026 07:11

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Pull request overview

Adds an “Day-to-day defaults (operating agreement)” section to the Health Agent documentation so routine pyauto-brain health runs follow consistent presentation/triage conventions while still adopting PyAutoHeart’s verdict verbatim.

Changes:

  • Documented default rendering order (mobile card first, then structured report).
  • Recorded triage conventions for grouping, unknown/CI tiles, local-check blindness, staleness, and baseline first-run unknowns.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread agents/faculties/health/AGENTS.md Outdated
@@ -123,6 +123,41 @@ Status: <GREEN | YELLOW | RED> (score <0-100>, snapshot <ts>)
- <red reason, mapped to its capability> (or "None")
```

## Day-to-day defaults (operating agreement)

How `pyauto-brain health` should render and reason on a routine run. These are
Comment thread agents/faculties/health/AGENTS.md Outdated
Comment on lines +149 to +151
- **`fix` citations.** Cite a `pyauto-heart fix <ci|dirty|drift|timing>` entry
point **only when Heart's verdict names that failure class**. An unknown is
not a failure — never emit a fix for it.
Comment on lines +152 to +154
- **Staleness.** If `dashboard.stale == true`, or the snapshot `ts` is older
than the watch interval, downgrade confidence and recommend
`pyauto-heart tick` rather than trusting the stale board.

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 2 comments.

Comment thread agents/health/AGENTS.md Outdated
Comment on lines +128 to +130
How `pyauto-brain health` should render and reason on a routine run. These are
presentation/triage conventions layered *on top of* the procedure above — they
never change the verdict, which is always adopted from Heart verbatim.
Comment thread agents/health/AGENTS.md Outdated
Jammy2211 pushed a commit that referenced this pull request Jul 3, 2026
Front-load the temporal clause so it no longer reads as the awkward
"reason on a routine run". Same nit Copilot raised on the operating-agreement
text in PR #10; fixed here too since the section lives in the vitals spec.

Co-Authored-By: Claude <noreply@anthropic.com>
Front-load the temporal clause so the opening no longer reads as the awkward
"reason on a routine run" Copilot flagged. Wording only.

Co-Authored-By: Claude <noreply@anthropic.com>

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 1 comment.

Comment thread agents/health/AGENTS.md Outdated
…re-review)

- `readiness.yellow_reasons` implied a nested JSON shape; readiness returns
  `yellow_reasons` at the top level. Reworded accordingly.
- `pyauto-heart fix <ci|dirty|drift|timing>` read as literal syntax and clashed
  with the Procedure section's explicit forms; now `pyauto-heart fix <topic>`
  with the topics listed as examples.

Co-Authored-By: Claude <noreply@anthropic.com>

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 2 comments.

Comment thread agents/health/AGENTS.md Outdated
Comment thread agents/health/AGENTS.md Outdated
…eview)

- The "Grouping" bullet's "blocking-first" ordering contradicted the Output
  schema's fixed section order. Clarify it applies to ranking/triage and the
  dashboard card; the structured report keeps the schema order (Warnings,
  Recommendations, Blocking Issues).
- Rewrap the Unknown-CI-tiles bullet to consistent line lengths.

Co-Authored-By: Claude <noreply@anthropic.com>
Jammy2211 pushed a commit that referenced this pull request Jul 6, 2026
…eview)

Mirror the PR #10 fixes into the vitals spec: clarify that severity-first
ordering applies to ranking/triage and the card (the structured report keeps
the Output-schema section order), and rewrap the Unknown-CI-tiles bullet.

Co-Authored-By: Claude <noreply@anthropic.com>
@Jammy2211
Jammy2211 merged commit 16d7490 into main Jul 6, 2026
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.

3 participants