can1357 8715ed207c feat(coding-agent-eval): added oneshot llm helper and __llm__ bridge ...

- Added one-shot `llm(prompt, opts)` helpers in JS and Python eval runtimes.
- Added `__llm__` eval bridge wiring for synthetic LLM tool dispatch and status/event output.
- Added `runEvalLlm` with tier-to-model resolution, effort handling, and oneshot completion execution.
- Added structured schema output handling via `respond` tool and JSON fallback parsing.
- Documented new llm behavior in eval docs/changelog and added tests for tier mapping and error cases.

2026-05-30 00:27:04 +02:00

..

display.ts

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

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

executor.ts

feat: overhauled stream timeout and eval session management

2026-05-26 16:49:11 +02:00

index.ts

fix(coding-agent): shared Python kernels between eval and user shortcut

2026-05-27 22:16:23 -04:00

kernel.ts

feat(eval/py): added runtime environment and working directory support to Python kernel execution

2026-05-26 15:26:29 +02:00

prelude.py

feat(coding-agent-eval): added oneshot llm helper and __llm__ bridge

2026-05-30 00:27:04 +02:00

prelude.ts

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

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

runner.py

feat(eval/py): added runtime environment and working directory support to Python kernel execution

2026-05-26 15:26:29 +02:00

runtime.ts

fix(coding-agent): add CONDA_PREFIX for python venv

2026-05-15 07:57:59 +00:00

tool-bridge.ts

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

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