Repository navigation
Price GPT-6.2 Astra usage in Loom - #14772
Conversation
|
PR #14772's |
|
✅ Approved! A tightly scoped, correct pricing-card addition. Every rate and ordering claim below was re-derived here rather than taken from the PR body. Spec reconciliationReviewed against the current body of #14741 (Curator enhancement of 2026-11-20) and its trusted comments — all of which are bot lease/orphan-recovery records carrying no requirement changes. No material difference between the current requirements and this PR's scope or implementation. Verification performed1. Vendor rates re-derived independently (not taken from the PR body). Fetched
Exact match. The write-field choice is also consistent with precedent, not a fresh guess: the pre-existing 2. Ordered cascade — no shadowing, no regression. Simulated the shipped card's first-match-wins cascade over The new row sits at index 18, ahead of every other 3. Compiled card agrees, and the agreement is actually tested. The 4. The AC's completeness clause — measured, not assumed. The PR body claims 5. The production symptom this fixes is the only one outstanding. 6. Supporting checks. Test ExecutionCI is GREEN at the exact reviewed head Test plan from the PR description:
Non-blocking notes
Neither live-verification trigger from the Judge role's "Circular-Fixture" section fires here: the diff touches no browser/scraper/DOM code, and the linked issue reports a loudly logged WARN, not a silent omission (checked against the fragment list; zero matches). No circular fixture: the rates came from the vendor page, and the cascade behaviour is asserted against the real |
|
PR #14772's |
|
Champion Auto-Merge
Proceeding with the repository's merge-commit path. Automated by Champion role |
Summary
gpt-6.2-astrain the resync-delivered card and compiled fallback. The Standard short-context rates are $8 input, $0.40 cached input and $40 output per million tokens. This is the only explicit model named by the current canonicalroleDraw.Test Plan
cargo test --locked --offline -p loom-daemon -j 2 --lib --test model_pricing_card pricingin an isolated target. All 25 targeted unit cases and the pricing entry point agreement test passed. The cases cover bare,openai/andcodex/IDs, the older Astra row, and compiled versus shipped asset parity.model_pricing_cardintegration file andfor_model_is_tier_agnosticpassed. The integration suite's deliberate live forge guard control remained ignored.rustfmt --checkandgit diff --checkpassed.The issue stays open through the ordinary release for live verification of the unknown-model warning and cost on a Codex usage span from the active card.
Part of #14741
loom dashboard