can1357 a25d521cab refactor(catalog): baked thinking metadata into buildModel pipeline ...

- Replaced minLevel/maxLevel range with explicit efforts array plus baked effortMap/supportsDisplay wire facts.
- Removed runtime enrichment layer and modelOmitsReasoningEffort; providers now read baked fields.
- Fixed dotted Opus 4.7/4.8 ids missing adaptive display via classifier-based predicates (#1373).
- Bumped model cache schema to v4 to invalidate pre-efforts rows.

2026-06-10 07:22:11 +02:00

..

__tests__

refactor(catalog): baked thinking metadata into buildModel pipeline

2026-06-10 07:22:11 +02:00

js

perf(coding-agent): deferred heavy imports until first feature use

2026-06-10 03:57:32 +02:00

py

fix(coding-agent): fixed eval artifact double-writes and kernel I/O capture

2026-06-10 01:27:41 +02:00

agent-bridge.ts

perf(coding-agent/eval): forced eval agent subagents to skip LSP startup

2026-06-08 12:25:53 +02:00

backend.ts

fix(coding-agent): fixed eval artifact double-writes and kernel I/O capture

2026-06-10 01:27:41 +02:00

bridge-timeout.ts

feat(coding-agent-eval): renamed the eval helper API from llm() to completion()

2026-06-08 12:22:47 +02:00

budget-bridge.ts

feat(coding-agent): added turn-budget parsing, multipliers and hard caps

2026-05-31 08:03:45 +02:00

completion-bridge.ts

refactor(catalog)!: split model catalog from pi-ai

2026-06-10 04:06:57 +02:00

concurrency-bridge.ts

feat(eval): replaced fixed concurrency cap with task.maxConcurrency bridge

2026-06-02 06:49:15 +02:00

idle-timeout.ts

fix(coding-agent): fixed eval artifact double-writes and kernel I/O capture

2026-06-10 01:27:41 +02:00

index.ts

feat(coding-agent/eval): implemented JSON cell-based eval tool inputs

2026-05-16 19:33:44 +02:00

session-id.ts

feat(eval): added shared executor inheritance for subagents with concurrent async cells

2026-05-26 14:37:56 +02:00

types.ts

feat(coding-agent): implemented eval framework and replaced python tool

2026-04-30 18:08:37 +02:00