Colin McDonnell 076e5a17b5 default Claude Code effort to high ...

max effort burns roughly 2x the wall time per turn for marginal quality
gain. high is the model's tuned default ('equivalent to not setting the
parameter' per Anthropic docs). full-send can be reintroduced as an
opt-in per-run override later if needed.

2026-05-13 04:49:07 +00:00

..

claude.ts

default Claude Code effort to high

2026-05-13 04:49:07 +00:00

index.ts

rename agent key to opencode and add skill invocation coverage (#541)

2026-04-15 19:38:36 +00:00

opencode.ts

gemini-3: default thinkingLevel to medium + restrict eager prep to frozen install (#663)

2026-05-11 22:04:19 +00:00

opencodePlugin.ts

opencode: surface subagent events via injected plugin (#634)

2026-05-08 22:46:43 +00:00

postRun.test.ts

postrun: thread AgentRunContext through the retry loop instead of repackaging (#652)

2026-05-11 18:47:08 +00:00

postRun.ts

gemini-3: default thinkingLevel to medium + restrict eager prep to frozen install (#663)

2026-05-11 22:04:19 +00:00

reviewer.ts

add /anneal + pullfrog-reviewer named subagent + Build self-review polish (#550)

2026-05-04 19:13:51 +00:00

sessionLabeler.test.ts

add /anneal + pullfrog-reviewer named subagent + Build self-review polish (#550)

2026-05-04 19:13:51 +00:00

sessionLabeler.ts

add /anneal + pullfrog-reviewer named subagent + Build self-review polish (#550)

2026-05-04 19:13:51 +00:00

shared.test.ts

unify per-run token + cost accounting + persist to WorkflowRun (#547)

2026-04-20 21:27:54 +00:00

shared.ts

postrun: thread AgentRunContext through the retry loop instead of repackaging (#652)

2026-05-11 18:47:08 +00:00