mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-15 21:07:20 +01:00
Merge remote-tracking branch 'origin/main' into capy/agent-ready-errors
This commit is contained in:
commit
e6924276e2
145 files changed
+8254
-714
No files matched your search
@@ -16,7 +16,7 @@
|
||||
"scripts/lib/published-text.ts": {"blob":"3f2e4d616b5dd0204035710c66b64d49055c5714","since":4},
|
||||
"scripts/lib/shard-engine.ts": {"blob":"3cd0b1aaa84018b00bf9ea0ce48093f3c8492f66","since":4},
|
||||
"scripts/test-paid-shards.ts": {"blob":"8ddee5f11ed7856876135520dd8025ab989e2db9","since":4},
|
||||
"scripts/test-pr-profile.ts": {"blob":"d95cffbf216a49d412824e2f518efc34cae015b4","since":4,"nonBehavioral":"PR-lane selection only: free-only files (the vendored Capy skill) skip the paid prompt-coverage rule; no case's verdict or inputs change"},
|
||||
"scripts/test-pr-profile.ts": {"blob":"ddc1e5991636c8c94722cd32472edce26489b26d","since":4,"nonBehavioral":"adds the free-only windows-pregate-e2e.yml workflow to FREE_ONLY_PR_FILES; no paid case reads it, so no verdict can change"},
|
||||
"scripts/test-strict-output.ts": {"blob":"01185d20dc9761b04b9b2f751ec98664fe0eaf93","since":4},
|
||||
"test/helpers/agent-sdk-runner.ts": {"blob":"210bba92d241a90df578b2c7fc943ac5755d0025","since":4},
|
||||
"test/helpers/auq-substance-panel.ts": {"blob":"4881260ef793668e4963a062db6d06a5e1f7a40f","since":4},
|
||||
|
||||
@@ -439,16 +439,15 @@ Other preflight failures retain their printed diagnosis, including harness misma
|
||||
These failures do not block the review; they use the bounded fallback below.
|
||||
|
||||
Enter only when **Outcome routing** selects fallback; do not restart the outside
|
||||
invocation after its failure. A native result never counts as outside coverage.
|
||||
invocation after its failure.
|
||||
Immediately before dispatch, recheck whether reviews are enabled. If the mode is
|
||||
\`CODEX_MODE: disabled\`, return to **Record the disabled outcome** without
|
||||
dispatching. Otherwise continue with the same prepared prompt.
|
||||
` : ctx.skillName === 'plan-eng-review' ? `**Native fallback — provider unavailable or execution failed, with reviews enabled:**
|
||||
|
||||
Use this fallback only after the routing row says to use it. Immediately before
|
||||
dispatch, check the preflight result again: disabled means no replacement;
|
||||
Immediately before dispatch, check the preflight result again: disabled means no replacement;
|
||||
record disabled coverage and do not dispatch. If still enabled, run the bounded
|
||||
native attempt below. A native result never supplies outside coverage.` : `**Error handling:** All errors are non-blocking — the outside voice is informational.
|
||||
native attempt below.` : `**Error handling:** All errors are non-blocking — the outside voice is informational.
|
||||
${outsideVoiceFailurePolicy(ctx, { timeoutMinutes: 5, onTimeout: 'fallback', stderrOnEmpty: false, fallback: 'native', escape: 1 })}
|
||||
|
||||
**Native fallback — provider unavailable or execution failed, with reviews enabled:**
|
||||
@@ -464,50 +463,48 @@ A native result never supplies outside coverage.`}`}`;
|
||||
}
|
||||
|
||||
function codexPlanBoundedWait(ctx: TemplateContext, ceo: boolean, needsApprovalReadiness: boolean): string {
|
||||
return `**Bounded outside-voice wait — one five-minute wait plus dispatch/cancellation overhead:**
|
||||
return `**Bounded outside-voice wait — one five-minute host timer:**
|
||||
|
||||
${['plan-ceo-review', 'plan-eng-review'].includes(ctx.skillName) ? `Before dispatch, verify TaskOutput and TaskStop in this session's tool definitions,
|
||||
and Plan in Agent's declared subagent types. Do not launch a task to test availability.
|
||||
If any capability is missing or undeclared, take the unavailable path below.` : `Before dispatch, verify the host offers the built-in Plan agent type, TaskOutput and
|
||||
TaskStop. If any is unavailable, take the unavailable path below without launching.`}
|
||||
Before dispatch, check this session's tools for TaskStop, Bash's \`run_in_background\`
|
||||
and Plan among Agent's subagent types. Do not launch a task to test availability;
|
||||
if any is missing, take the unavailable path without launching.
|
||||
Use Plan, which denies native Edit, Write and NotebookEdit tools. Do not set a model
|
||||
override; keep the inherited model. This is not a filesystem sandbox: the review-only
|
||||
prompt also forbids mutations through other tools. The subagent has fresh context
|
||||
but is the same harness; model identity stays unknown unless the runtime reports it.
|
||||
A native result never supplies outside coverage.
|
||||
prompt also forbids mutations through other tools. A native result never supplies
|
||||
outside coverage. This is the one exception to foreground dispatch here.
|
||||
Execute the four steps once:
|
||||
|
||||
This is the single bounded-wait exception to foreground dispatch for this outside
|
||||
voice. Execute the four steps once:
|
||||
|
||||
1. Dispatch via the Agent tool with \`subagent_type: "Plan"\` and
|
||||
\`run_in_background: true\`. Subagent prompt: same plan review prompt as above.
|
||||
Keep the returned \`agentId\`; do not guess an ID or launch a second task.
|
||||
If dispatch fails without an ID, take the unavailable path without guessing one.
|
||||
2. Immediately call TaskOutput with that exact ID as \`task_id\`, \`block: true\`,
|
||||
and \`timeout: 300000\`. Make one wait only; do not poll or renew the budget.
|
||||
3. Check TaskOutput's outer fields: \`<retrieval_status>\` must be \`success\`,
|
||||
\`<task_id>\` must match, \`<task_type>\` must be \`local_agent\`, \`<status>\`
|
||||
must be \`completed\`, \`<output>\` must be nonempty, and there must be no outer
|
||||
\`<error>\`. Accept findings only if that output is an identifiable complete
|
||||
1. Start the timer: Bash \`command: "sleep 300"\`, \`run_in_background: true\`,
|
||||
\`timeout: 300000\`. Dispatch via the Agent tool with \`subagent_type: "Plan"\`
|
||||
and \`run_in_background: true\` where offered, with the same plan review prompt.
|
||||
Keep the returned agent ID; do not guess an ID or launch a second task.
|
||||
2. End your turn and wait for task notifications. Make one wait only: do not poll,
|
||||
sleep, Read either output file or renew the timer.
|
||||
3. Only the agent's \`<task-notification>\` arriving before the timer's counts:
|
||||
\`<task-id>\` must match the agent ID, \`<status>\` must be \`completed\`, \`<summary>\`
|
||||
must say it finished ("is waiting on its own background work": keep waiting; a
|
||||
turn limit: partial) and \`<result>\` must be nonempty; a "[Subagent hand-back]"
|
||||
header only frames it. Accept findings only if it is an identifiable complete
|
||||
final reviewer report. Reject raw or in-progress transcripts; do not extract
|
||||
finding fragments from them. Terminal status or warning markers alone do not
|
||||
establish report completeness. If any check fails or the report cannot be identified, follow step 4. Otherwise present it under an \`OUTSIDE VOICE (${outsideVoiceFor(ctx).nativeLabel} subagent):\`
|
||||
establish report completeness. If any check fails or the report cannot be identified, follow step 4. Otherwise call TaskStop with the timer's ID, present it under an \`OUTSIDE VOICE (${outsideVoiceFor(ctx).nativeLabel} subagent):\`
|
||||
header, then continue to ${ceo ? '**Integrate reviewer findings**' : 'Cross-model tension'}.
|
||||
4. On any noncompletion (timeout, error, missing/mismatched result, failed/killed
|
||||
status, raw transcript or empty report), call TaskStop with the same ID as
|
||||
\`task_id\`. TaskOutput timeout does not stop the agent. Record the stop result;
|
||||
if cancellation fails, say cancellation is unconfirmed. If TaskStop reports the
|
||||
task already completed after the timeout, still give no late-result credit.
|
||||
4. Otherwise (timer first, no ID, failed or stopped status, partial or empty result,
|
||||
or Agent returns a report directly: no enforced deadline, so no credit), call
|
||||
TaskStop with the same ID as the agent, and call TaskStop with the timer's ID if it runs.
|
||||
Record each stop result; if one fails, cancellation is unconfirmed.
|
||||
For a completion after the timer or TaskStop, still give no late-result credit.
|
||||
|
||||
**Unavailable path:** "Outside voice unavailable. Continuing to ${needsApprovalReadiness ? 'planning decisions and Approval readiness' : 'outputs'}."
|
||||
**Unavailable path:** "Outside voice unavailable: <cause>. Fix: <fix>. Continuing to ${needsApprovalReadiness ? 'planning decisions and Approval readiness' : 'outputs'}. (OUTSIDE_VOICE_UNAVAILABLE)"
|
||||
The cause adds to the provider's diagnosis: Plan agent type not offered, TaskStop not offered,
|
||||
background tasks unavailable${ctx.host === 'claude' ? ' (fix: Claude Code 2.1.277+, background tasks on)' : ''}, no complete report within five minutes, or a failed status.
|
||||
Do not retry with a general-purpose agent. Report missing outside-voice coverage.
|
||||
Ignore partial or late results for critique, agreement, clean status or coverage.
|
||||
${ceo ? 'Skip Integrate reviewer findings and Cross-model tension.' : 'Skip Cross-model tension.'} Persist an unavailable result using the command below
|
||||
with STATUS = "unavailable", SOURCE = "none", OUTSIDE_STATUS = "unavailable";
|
||||
then continue directly to ${needsApprovalReadiness ? 'the remaining planning decisions and Approval readiness' : 'outputs'}. The storage policy still applies.
|
||||
Do not record a clean review when no reviewer completed within the accepted wait.
|
||||
|
||||
${ceo ? '' : '(On `CODEX_MODE: disabled` you already skipped this section per the preflight — do not reach here.)'}`;
|
||||
with STATUS = "unavailable", SOURCE = "none", OUTSIDE_STATUS = "unavailable", adding \`"unavailable_reason":"<cause>"\`;
|
||||
then continue directly to ${needsApprovalReadiness ? 'the remaining planning decisions and Approval readiness' : 'outputs'}.
|
||||
Do not record a clean review when no reviewer completed.
|
||||
`;
|
||||
}
|
||||
|
||||
function codexPlanCrossModelTension(ctx: TemplateContext): string {
|
||||
|
||||
@@ -185,7 +185,7 @@ pass/fail/blocked/not run/inconclusive/not applicable (reason).
|
||||
| Contract | Observe |
|
||||
|---|---|
|
||||
| Successful execution | Expected return/output and final business effect, not just launch/acceptance |
|
||||
| Invalid/missing input | Declared rejection, correct status and no forbidden state change |
|
||||
| Invalid/missing input | One probe per documented input rule (allowed characters, format, sign, range, arity): declared rejection, correct status and no forbidden state change |
|
||||
| Authentication/authorization | Valid identity, missing/invalid identity, wrong owner/role and durable no-effect boundary |
|
||||
| CLI process contract | Exact exit code, stdout and stderr separately; resulting file/state changes |
|
||||
| State transitions | Initial, intermediate and completed/failed states and their permitted transitions |
|
||||
|
||||
@@ -247,6 +247,7 @@ export const FREE_ONLY_PR_FILES = [
|
||||
'scripts/ship-measure-sweep.ts', // The weekly sweep CLI; it launches paid cases, never runs inside one.
|
||||
'.github/workflows/version-gate.yml',
|
||||
'.github/workflows/windows-free-tests.yml',
|
||||
'.github/workflows/windows-pregate-e2e.yml',
|
||||
'.github/workflows/windows-setup-e2e.yml',
|
||||
] as const;
|
||||
|
||||
|
||||
Reference in new issue
Block a user