can1357 f74c6d892a feat(coding-agent-eval): renamed the eval helper API from llm() to completion() ...

- Renamed eval oneshot helper from llm() to completion() across JS/Python APIs.
- Remapped eval bridge internals to completion semantics (__completion__, runEvalCompletion, completion status op).
- Updated docs, prompts, and timeout guidance to describe completion() usage and behavior.
- Adjusted completion defaults for active-session model preference, fallback parsing, and slow-tier effort handling.

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

..

__tests__

fix(eval/py): corrected read() positional offset/limit support and tests

2026-06-08 02:04:59 +02:00

display.ts

feat(coding-agent/eval): added local python-runner subprocess execution

2026-05-12 09:09:24 +02:00

executor.ts

fix(eval): resolved JS/Python resets by awaiting in-flight operations

2026-06-08 02:04:59 +02:00

index.ts

feat(eval): added per-cell inactivity timeout budgets in eval executors

2026-05-31 10:11:59 +02:00

kernel.ts

fix(eval): probed Win32 console directly instead of inferring from stdio

2026-06-06 01:04:13 +00:00

prelude.py

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

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

prelude.ts

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

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

runner.py

refactor(coding-agent): removed args global from eval runtimes

2026-05-31 07:54:52 +02:00

runtime.ts

fix(coding-agent): probed all Python runtimes to bypass broken managed env

2026-05-31 02:00:18 +02:00

spawn-options.ts

fix(eval): probed Win32 console directly instead of inferring from stdio

2026-06-06 01:04:13 +00:00

tool-bridge.ts

fix(eval): kept Python kernel alive when parallel() cell interrupted

2026-06-05 20:42:29 +02:00