chore(prompt-budget): ratchet limits after the session-todo cut

[senamakel]

Why

#6436 merged with the last measured prompt/tool sizes not yet written back to scripts/prompt-budget.limits: dropping the todo board tools shrank the orchestrator's tool column (20,946 → 20,434 B) and the shortened tasks pack summary brought use_skill back under its line. Without this the budget lane reports "IMPROVED but was not ratcheted" and the saving can grow back.

What changed

• scripts/prompt-budget.limits: orchestrator:9169:20434, use_skill re-measured. Generated by scripts/check-prompt-budget.sh --write; scripts/check-prompt-budget.sh is green.

Verification

scripts/check-prompt-budget.sh → [prompt-budget] OK — every agent is within its limit.

Summary by CodeRabbit

• Chores
  • Updated prompt-budget validation thresholds for the orchestrator and use_skill tool schemas.
  • The revised limits enforce tighter prompt-size budgets.

[tinysweeper]

Tiny Sweeper review

Tiny Sweeper reviewed this change across 6 lane(s) and found 0 active actionable finding(s). Detailed lane evidence and any incomplete work are listed below.

State: Reviewing pending checks
Priority: low
Reviewed head: 9f32510c7353
Updated: 1790068594 (Unix time)

Review snapshot

Change surface	Files	Review signal	Count
Production	1	Active findings	0
Tests	0	Noted findings	0
Documentation	0	Resolved findings	0
Configuration	0	Pending checks/questions	5

Completeness: Complete
Test assessment: No supported feature-to-test mapping was available; this does not mean tests are absent or passed.

What changed

The review could not produce a supported behavioral summary; inspect the cited changed surface and lane details below.

Features

None identified with supported citations.

Tests

No supported feature-to-test mapping was produced. Test execution is not inferred.

Findings

No active actionable findings.

Pending checks: Rust E2E (mock backend), Build Playwright E2E Artifact, E2E (Playwright / web lane), Desktop E2E (full suite, 3 OS), Rust Feature-Gate Smoke (gates off)

Before merge

• Wait for Rust E2E (mock backend), Build Playwright E2E Artifact, E2E (Playwright / web lane), Desktop E2E (full suite, 3 OS), Rust Feature-Gate Smoke (gates off).

Agent review details

critique

• Conclusion: Success
• Scope reviewed: all assigned evidence
• Lane summary: The limits are tightened to the newly measured orchestrator and use_skill sizes, preserving the ratchet while allowing the configured slack. The change looks safe to merge. _The code index is behind this pull request (indexed at `6d5a6a2b3df7`), so retrieved context may be out of date._ _4 memory call(s) failed (model: cortex: v1/recall: timed out after 10s), so this review saw part of what the engine holds._

security

• Conclusion: Success
• Scope reviewed: all assigned evidence
• Lane summary: The prompt budget limits are tightened for the orchestrator and use_skill entries without widening any guardrails. The change looks safe to merge. _The code index is behind this pull request (indexed at `6d5a6a2b3df7`), so retrieved context may be out of date._ _4 memory call(s) failed (model: cortex: v1/recall: timed out after 10s), so this review saw part of what the engine holds._

tests

• Conclusion: Success
• Scope reviewed: all assigned evidence
• Lane summary: Lowers two prompt-budget limits to match measured values, tightening the ratchet. No behavioural change; the checker script enforces the new ceilings. Safe to merge. No findings.}, _The code index is behind this pull request (indexed at `6d5a6a2b3df7`), so retrieved context may be out of date._ _4 memory call(s) failed (model: cortex: v1/recall: timed out after 10s), so this review saw part of what the engine holds._

commits

• Conclusion: Neutral
• Scope reviewed: all assigned evidence
• Lane summary: Nothing sensitive found in what this pull request commits.

description

• Conclusion: Success
• Scope reviewed: all assigned evidence
• Lane summary: Ratchet-only decrease of the orchestrator tool column (20455 → 20434) and the use_skill schema ceiling (1732 → 1711), consistent with the stated removal of todo-board tools. The limits move in the allowed direction only; no violations of the down-only ratchet policy. _The code index is behind this pull request (indexed at `6d5a6a2b3df7`), so retrieved context may be out of date._ _4 memory call(s) failed (model: cortex: v1/recall: timed out after 10s), so this review saw part of what the engine holds._

e2e

• Conclusion: Neutral
• Scope reviewed: all assigned evidence
• Lane summary: The diff updates two recorded prompt-budget baselines to lower values (orchestrator tool-schema bytes 20455→20434, tool:use_skill 1732→1711). This is a metadata-only change with no external surface — no route, command, flag, screen, persisted format, or queue message is added or altered. No end-to-end test drives this change, and none is needed. Waiting on end-to-end jobs: `Rust E2E (mock backend)`, `Build Playwright E2E Artifact`, `E2E (Playwright / web lane)`, `Desktop E2E (full suite, 3 OS)`, `Rust Feature-Gate Smoke (gates off)`.
• Unresolved questions/checks: Rust E2E (mock backend), Build Playwright E2E Artifact, E2E (Playwright / web lane), Desktop E2E (full suite, 3 OS), Rust Feature-Gate Smoke (gates off)

Evidence and run details

• Models: ladder/vectors, gpt-5.6-luna, deepseek/deepseek-v4-flash
• Spend: $0.007546
• Tokens: 88766 input · 4844 output · 3310 cached · 56 embedding

Head	State	Pass summary
9f32510c7353	pending	0 active finding(s), 0 resolved finding(s) (at 1790068594)

[coderabbitai]

Navigate logical layers of code changes, visualize relationships, and explore their blast radius.

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Advanced

Run ID: 57c65613-f615-4694-9ba5-ea68e3de8ab1

📥 Commits

Reviewing files that changed from the base of the PR and between a63c2b8 and 9f32510.

📒 Files selected for processing (1)

• scripts/prompt-budget.limits

Included review availability: Your plan provides up to 10 included reviews per hour; 8 remain after this review.

---

📝 Walkthrough

Walkthrough

The change lowers two prompt-budget ceilings in scripts/prompt-budget.limits: the orchestrator tool-schema ceiling and the use_skill per-tool schema ceiling.

Changes

Prompt budget limits

Layer / File(s)	Summary
Lower schema ceilings scripts/prompt-budget.limits	The orchestrator ceiling changes from 20,455 to 20,434 bytes. The use_skill ceiling changes from 1,732 to 1,711 bytes.

Priority: ⬇️ Low

Estimated code review effort: 1 (Trivial) | ~2 minutes

Change: Other

Suggested reviewers: m3ga-mind

Merge Risk: ⚪ Minimal · up to 9f325

This narrowly scoped change updates prompt-budget ceilings to match the intended reductions, with no identified production impact or merge blocker.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly describes the prompt-budget limit ratchet caused by the session-todo change. It is concise and matches the main change.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0…
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

---

_{A rabbit checks the budget line,
Two ceilings shrink by bytes just fine.
The tools now fit a narrower gate,
use_skill trims its schema weight.
Hop, hop—the limits ratchet straight!}

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

✨ Finishing Touches 💡 1

🛠️ Fix failing CI checks 💡

• Commit to this branch
• Create a new PR

[tinysweeper]

tinysweeper found nothing blocking. Approving.

             $0.0075 · 88,766 in / 4,844 out · 3,310 cached (4%)  · ladder/vectors, gpt-5.6-luna, deepseek/deepseek-v4-flash · 56 embedded
critique:    $0.0021 · 33,174 in / 515 out   · 3,310 cached (10%) · gpt-5.6-luna
security:    $0.0010 · 14,676 in / 163 out   · 0 cached (0%)      · gpt-5.6-luna
tests:       $0.0015 · 15,604 in / 460 out   · 0 cached (0%)      · deepseek/deepseek-v4-flash
description: $0.0007 · 6,913 in  / 496 out   · 0 cached (0%)      · deepseek/deepseek-v4-flash
e2e:         $0.0017 · 16,559 in / 1,138 out · 0 cached (0%)      · deepseek/deepseek-v4-flash