mirror of
https://github.com/codewhale-hq/Codewhale.git
synced 2026-11-13 13:41:28 -10:00
CodeWhale Bot
574dc76e26
Remove model-selected child caps, default child wall/depth ceilings, early wrap-up guidance, report-only requests and report reserves. Preserve explicit owner settings, cancellation, permission checks and deterministic partial-work receipts. Continue independent workflow steps, keep dependent skips truthful, remove cumulative child/code-call and recursive-round cutoffs, and retain unknown usage as unknown. Preserve mode history and idle active-goal resume. Upgrade untouched bundled delegate guidance by exact shipped-body hash while preserving customized and deleted skills. Update existing checks and both changelogs; no new test functions were added. Erase the shared Engine event-loop future at run_owned without adding another loop. Two successive warm local lib-test builds took 29m31s then 2m24s with Rust 1.99.0 and the same cache, profile, features and target selection. Three existing assertions also changed; this is an observation, not a cold-build or cross-platform guarantee. Record the method in both build-performance docs. Verification: 753 distinct existing checks passed across frozen passes. Repair6 ran 750 passed / 3 stale assertions; those assertions were corrected, and repair7 passed 58 relevant Engine/child/recovery/goal and corrected checks. Reuse unchanged Workflow 237, JS library 12, VM 82 and configuration evidence. Both builds and test passes retained 2,172 frozen inputs. After tests only release-note text and build-performance docs changed; runtime code stayed unchanged. git diff --check passed. Darwin linker reports oversized compact unwind metadata. Final artifact/package, CI, RC and provider/Boat qualification remain separate. Further request-wall-time and retry-window work remains open.
50 lines
1.5 KiB
JavaScript
50 lines
1.5 KiB
JavaScript
export default workflow({
|
|
"id": "issue-audit-js",
|
|
"goal": "Audit an issue fix with parallel specialist agents, then synthesize a release note",
|
|
"description": "Declarative JavaScript authoring example lowered to typed Workflow IR without executing JS.",
|
|
"nodes": [
|
|
{
|
|
"branch": {
|
|
"id": "parallel-audit",
|
|
"parallel": true,
|
|
"children": [
|
|
{
|
|
"agent": {
|
|
"id": "code-audit",
|
|
"prompt": "Inspect the implementation for correctness and regression risk.",
|
|
"agent_type": "review",
|
|
"mode": "read_only",
|
|
"file_scope": ["crates"]
|
|
}
|
|
},
|
|
{
|
|
"agent": {
|
|
"id": "test-audit",
|
|
"prompt": "Inspect targeted tests and identify missing verification.",
|
|
"agent_type": "verifier",
|
|
"mode": "read_only",
|
|
"file_scope": ["crates", "tests"]
|
|
}
|
|
},
|
|
{
|
|
"agent": {
|
|
"id": "docs-audit",
|
|
"prompt": "Check whether docs or release notes should mention the change.",
|
|
"agent_type": "review",
|
|
"mode": "read_only",
|
|
"file_scope": ["docs"]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"reduce": {
|
|
"id": "synthesize-release-risk",
|
|
"inputs": ["code-audit", "test-audit", "docs-audit"],
|
|
"prompt": "Combine specialist findings into a release-ready risk summary."
|
|
}
|
|
}
|
|
]
|
|
});
|