rock/homelab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(agent-pod): fold judgeOnly status check into planner, drop separate judge pre-check

Browse Source
This commit is contained in:
Story Crater Bot
2026-08-19 10:57:21 -07:00
parent f5ea65c04b
commit 8db0cd3a8b
1 changed files with 24 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
k8s/apps/agent-pod/coordinator-configmap.yaml
+24 -18
View File
@@ -278,10 +278,24 @@ data:
return { ok, sessionName: label };
}
function plannerPrompt(task, specHint) {
function plannerPrompt(task, specHint, judgeOnly) {
// judgeOnly (auto-discovered tasks only, see parseTaskBoard): planner
// itself decides whether the task is already done before planning it,
// reading tasks/INDEX.md's own status notes plus git log/current code --
// replaces what used to be a separate judge pre-check call. One LLM round
// trip instead of two, and the same agent that's about to plan the task
// is the one deciding whether planning it is even necessary.
const decideStep = judgeOnly
? `First, decide whether task ${task} is already fully implemented on this branch: check ` +
`\`git log --oneline --grep '${task}'\`, tasks/INDEX.md's own status notes for this task, and the current ` +
`code directly against its spec (${specHint})'s acceptance criteria. Write your decision to ` +
`.task-result-${task} as a single "VERDICT: PASS" (already done, no further work needed) or ` +
`"VERDICT: FAIL" (needs work) line plus one line of rationale. If VERDICT is FAIL, continue below and ` +
`draft the plan in this same turn; if VERDICT is PASS, skip the rest and go straight to the touch step.\n\n`
: "";
return (
`Use the planner skill to draft PLAN.md for task ${task}, reading its spec (${specHint}). PLAN.md is scratch ` +
`state for this harness, not a deliverable -- do NOT commit it or add it to git. ` +
`${decideStep}Use the planner skill to draft PLAN.md for task ${task}, reading its spec (${specHint}). ` +
`PLAN.md is scratch state for this harness, not a deliverable -- do NOT commit it or add it to git. ` +
`Then run: touch .stage-done-${task}-planner`
);
}
@@ -313,7 +327,10 @@ data:
const MAX_PLAN_REVISIONS = 3;
// Runs one task against the repo's shared role pool: planner drafts
// PLAN.md, investigator confirms it, then implementer and judge go back and
// PLAN.md (for auto-discovered tasks, first deciding off tasks/INDEX.md and
// the repo's own state whether the task is already done -- see
// plannerPrompt's judgeOnly branch; judge never does this pre-check),
// investigator confirms it, then implementer and judge go back and
// forth -- judge's FAIL rationale lands in .task-result-<task>, which the
// next implementer attempt is told to read and address. After
// MAX_IMPLEMENT_ATTEMPTS straight fails, the planner role is asked to judge
@@ -360,18 +377,10 @@ data:
// whatever the outcome, so it never bleeds into the next task's planner
// call or sits around as stale harness clutter in the shared clone.
try {
if (judgeOnly) {
const quick = await stage(
"judge",
`Task ${task} may already be implemented on this branch -- check ` +
`\`git log --oneline --grep '${task}'\` and the current code directly against its spec ` +
`(${specHint})'s acceptance criteria (no PLAN.md exists for this task yet). Write your ` +
`verdict to .task-result-${task} as a single "VERDICT: PASS" or "VERDICT: FAIL" line plus ` +
`one line of rationale, then run: touch .stage-done-${task}-judge-0`,
path.join(cwd, `.stage-done-${task}-judge-0`)
);
if (!quick.ok) return abandon("judge", quick, 0);
let result = await stage("planner", plannerPrompt(task, specHint, judgeOnly), path.join(cwd, `.stage-done-${task}-planner`));
if (!result.ok) return abandon("planner", result);
if (judgeOnly) {
const quickText = fs.existsSync(resultFile) ? fs.readFileSync(resultFile, "utf8") : "";
if (parseVerdictLine(quickText, "VERDICT") === "PASS") {
delete pipelineSession.activeTasks[task];
@@ -380,9 +389,6 @@ data:
}
}
let result = await stage("planner", plannerPrompt(task, specHint), path.join(cwd, `.stage-done-${task}-planner`));
if (!result.ok) return abandon("planner", result);
result = await stage("investigator", investigatorPrompt(task), path.join(cwd, `.stage-done-${task}-investigator`));
if (!result.ok) return abandon("investigator", result);