docs(diagrams): refresh strategy and PITWALL diagrams - #1258
Conversation
Update routing, agent outputs, retrieval fallbacks, and PITWALL polling details. Refresh three 16:9 HTML/SVG pairs and record the fidelity ledger. Checks: 20 diagram-surface tests passed. Six changed Draw.io sources parse without dangling edges. Chromium rendered the HTML and standalone SVG exports at 1280x720 with no console errors or text overflow.
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Advanced Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 881df7fe92
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".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| <p class="eyebrow">F1 StratLab · decision pipeline</p> | ||
| <svg viewBox="0 0 1280 720" xmlns="http://www.w3.org/2000/svg" role="img" aria-labelledby="orchestration-title orchestration-desc"> | ||
| <title id="orchestration-title">N31 orchestrator flow</title> | ||
| <desc id="orchestration-desc">N25 to N28 distributions feed Monte Carlo, while N29 radio reasoning and N30 regulation evidence inform rich synthesis.</desc> |
There was a problem hiding this comment.
Show all agent inputs to rich synthesis
The rich pipeline does not split inputs this way: _build_orchestrator_prompt serializes the N25 pace, N26 tyre, N27 situation, and N28 pit blocks—including their reasoning—directly into SUB-AGENT OUTPUTS, in addition to supplying the Monte Carlo scores. This new description and the matching flow imply that N25–N28 affect synthesis only through Monte Carlo, which is particularly misleading for N25 because its sampled pace is currently unused by the scorer. Add a direct N25–N28 input to synthesis or revise the description and corresponding diagram/export.
Useful? React with 👍 / 👎.
What
scripts/for dead or low-value measurement files. No safe deletions were identified.Why
The previous diagrams described stale data contracts, scoring semantics, and PITWALL transport behavior. This refresh preserves the full engineering detail while correcting those contracts.
Scripts audit
measure_*.pyscripts.Validation
uv run pytest -q tests/surfaces/test_diagrams_no_retired_surface.py: 20 passed.a-n29-ris routed around N27 and enters the router from the side. The orchestrator HTML render also confirms the fallback fits its card.11ea8aa.git diff --check: clean.Related: #1253