@tea-agent/loop-agent 0.12.0 → 0.13.0-beta.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/AGENTS.md +155 -153
- package/CHANGELOG.md +338 -265
- package/README.md +345 -298
- package/bin/agent-worker.js +22 -22
- package/bin/loop-agent.js +21 -21
- package/dist/application/dag/generate-task-dag.js +28 -28
- package/dist/application/evaluation/candidate-hash.js +75 -0
- package/dist/application/evaluation/candidate.js +52 -0
- package/dist/application/evaluation/replay.js +289 -0
- package/dist/application/evaluation/types.js +130 -0
- package/dist/cli/command-definitions.js +27 -7
- package/dist/cli/program.js +8 -4
- package/dist/commands/cursor-prompt.js +6 -6
- package/dist/commands/eval.js +235 -0
- package/dist/commands/init.js +544 -506
- package/dist/commands/knowledge.js +129 -31
- package/dist/commands/loop-benchmark.js +11 -11
- package/dist/commands/pi-reuse-benchmark.js +16 -16
- package/dist/executors/pi-sdk-executor.js +38 -24
- package/dist/executors/shell-executor.js +34 -2
- package/dist/executors/shell-presets.js +20 -0
- package/dist/executors/shell-verification.js +7 -0
- package/dist/governance/manifest-types.js +4 -0
- package/dist/infrastructure/evaluation/candidate-store.js +435 -0
- package/dist/infrastructure/evaluation/store.js +40 -0
- package/dist/sidecars/cursor-prompt/executor.js +1 -1
- package/dist/task/config-types.js +28 -1
- package/dist/task/runtime.js +27 -27
- package/dist/worker/cli.js +96 -1
- package/dist/worker/delivery/package.js +3 -3
- package/dist/worker/feature/decision-loader.js +37 -6
- package/dist/worker/feature/next-action.js +10 -2
- package/dist/worker/feature/ready-plan-projection.js +81 -0
- package/dist/worker/feature/reducer.js +2 -1
- package/dist/worker/feature/review.js +19 -2
- package/dist/worker/feature/run.js +27 -2
- package/dist/worker/follow-up/approve.js +5 -2
- package/dist/worker/follow-up/factory.js +1 -1
- package/dist/worker/observability/read-model.js +246 -41
- package/dist/worker/observe/routes.js +173 -15
- package/dist/worker/observe/spec-evidence.js +281 -0
- package/dist/worker/observe/static/api.js +46 -27
- package/dist/worker/observe/static/app.js +150 -150
- package/dist/worker/observe/static/constants.js +148 -148
- package/dist/worker/observe/static/copy.js +67 -67
- package/dist/worker/observe/static/dag-helpers.js +172 -172
- package/dist/worker/observe/static/dag-layout.d.ts +31 -31
- package/dist/worker/observe/static/dag-layout.js +83 -83
- package/dist/worker/observe/static/dag-model.js +72 -72
- package/dist/worker/observe/static/dom.js +61 -61
- package/dist/worker/observe/static/format-pool.js +67 -67
- package/dist/worker/observe/static/format.js +292 -292
- package/dist/worker/observe/static/index.html +308 -308
- package/dist/worker/observe/static/kpi.js +94 -94
- package/dist/worker/observe/static/relations.js +133 -128
- package/dist/worker/observe/static/router.js +93 -85
- package/dist/worker/observe/static/run-processing.js +148 -148
- package/dist/worker/observe/static/shell-chrome.js +68 -68
- package/dist/worker/observe/static/state.js +253 -253
- package/dist/worker/observe/static/styles.css +1902 -1890
- package/dist/worker/observe/static/views/batch.js +227 -226
- package/dist/worker/observe/static/views/dag-graph.js +172 -172
- package/dist/worker/observe/static/views/dag-inspector.js +607 -477
- package/dist/worker/observe/static/views/dag.js +362 -362
- package/dist/worker/observe/static/views/dashboard.js +445 -442
- package/dist/worker/observe/static/views/failures.js +143 -143
- package/dist/worker/observe/static/views/feature.js +492 -453
- package/dist/worker/observe/static/views/pool.js +350 -347
- package/dist/worker/observe/static/views/run.js +453 -453
- package/dist/worker/observe/static/views/session-timeline.js +205 -205
- package/dist/worker/observe/static/views/shell.js +7 -7
- package/dist/worker/observe/static/views/task.js +314 -260
- package/dist/worker/observe/static/views/timeline.js +163 -163
- package/dist/worker/pool/doctor.js +165 -0
- package/dist/worker/pool/migrate-state.js +303 -0
- package/dist/worker/pool/run-store.js +205 -17
- package/dist/worker/pool/types.js +17 -1
- package/dist/worker/pool/validation.js +100 -15
- package/dist/worker/report/morning-report.js +12 -2
- package/dist/worker/runner/run-ready.js +41 -26
- package/dist/worker/task-graph/ready-planner.js +136 -0
- package/dist/workflows/dag/backend-test-analysis-contract.js +120 -0
- package/dist/workflows/dag/canvas-observer.js +275 -275
- package/dist/workflows/dag/convergence/controller.js +16 -8
- package/dist/workflows/dag/dynamic-runtime/map.js +90 -2
- package/dist/workflows/dag/failure-routing.js +12 -1
- package/dist/workflows/dag/init-hybrid.js +2404 -360
- package/dist/workflows/dag/node-execution.js +9 -0
- package/dist/workflows/dag/prompt.js +9 -0
- package/dist/workflows/dag/report.js +35 -1
- package/dist/workflows/dag/runner.js +28 -2
- package/dist/workflows/dag/task-demand-routing.js +383 -0
- package/dist/workflows/dag/types.js +51 -13
- package/dist/workflows/dag/upstream-artifacts.js +1 -0
- package/dist/workflows/dag/validate.js +59 -1
- package/docs/README.md +106 -104
- package/docs/agent-dag-recovery-playbook.md +195 -184
- package/docs/agent-dag-runner.md +67 -67
- package/docs/architecture/README.md +26 -26
- package/docs/architecture/dag-execution.md +140 -140
- package/docs/architecture/evolution.md +54 -53
- package/docs/architecture/facts-and-state.md +71 -58
- package/docs/architecture/runtime-boundaries.md +191 -191
- package/docs/architecture/system-overview.md +93 -93
- package/docs/architecture/worker-and-feature.md +85 -81
- package/docs/cursor-prompt-sidecar.md +36 -36
- package/docs/decisions/README.md +18 -15
- package/docs/design/README.md +167 -77
- package/docs/development-principles.md +73 -73
- package/docs/exec-plans/README.md +6 -6
- package/docs/exec-plans/active/README.md +15 -9
- package/docs/exec-plans/completed/README.md +85 -73
- package/docs/feature-workflow.md +389 -261
- package/docs/harness-methodology-debugging.md +153 -153
- package/docs/harness-methodology-tdd.md +130 -130
- package/docs/harness-methodology-verification.md +27 -27
- package/docs/init-surface.manifest.json +289 -280
- package/docs/loop-agent-harness.md +142 -130
- package/docs/production-readiness.md +96 -96
- package/docs/progress/README.md +64 -54
- package/docs/reports/README.md +117 -94
- package/docs/skills/README.md +7 -7
- package/docs/skills/vetted-skill-registry.md +29 -27
- package/docs/templates/adr.md +60 -60
- package/docs/templates/agent-dag-authority-surface-audit.prompt.md +94 -94
- package/docs/templates/agent-dag-decision-envelope.schema.json +213 -213
- package/docs/templates/agent-dag-decision-gate-dogfood-report.md +117 -117
- package/docs/templates/agent-dag-decision-gate.prompt.md +246 -246
- package/docs/templates/agent-dag-process-supervisor.prompt.md +98 -98
- package/docs/templates/agent-dag-report.schema.json +473 -473
- package/docs/templates/agent-dag-review-verdict.prompt.md +68 -68
- package/docs/templates/agent-dag.base.json +190 -190
- package/docs/templates/agent-dag.final-verification.json +185 -185
- package/docs/templates/agent-dag.schema.json +411 -383
- package/docs/templates/agent-dag.supervised-implementation.json +501 -501
- package/docs/templates/backend-test-analysis.schema.json +44 -0
- package/docs/templates/backend-test-dag.generate-pytest.prompt.md +202 -139
- package/docs/templates/backend-test-dag.json +311 -276
- package/docs/templates/backend-test-dag.retrospect.prompt.md +125 -125
- package/docs/templates/backend-test-dag.review-cases.prompt.md +81 -81
- package/docs/templates/exec-plan.md +64 -64
- package/docs/templates/feature-spec.md +53 -53
- package/docs/templates/frontend-design-contract.md +42 -33
- package/docs/templates/frontend-task-constraints.md +35 -25
- package/docs/templates/frontend-task-requirement.md +70 -61
- package/docs/templates/frontend-test-dag.generate-cases.prompt.md +5 -0
- package/docs/templates/frontend-test-dag.json +23 -0
- package/docs/templates/frontend-test-dag.retrieve-context.prompt.md +3 -0
- package/docs/templates/frontend-test-dag.retrospect.prompt.md +3 -0
- package/docs/templates/frontend-test-dag.review-cases.prompt.md +3 -0
- package/docs/templates/frontend-test-dag.review-execution.prompt.md +3 -0
- package/docs/templates/harness.schema.json +221 -221
- package/docs/templates/hybrid-dag.json +188 -188
- package/docs/templates/init-evolution-review.md +35 -35
- package/docs/templates/interactive-ui-round2-experiment.md +66 -66
- package/docs/templates/knowledge-graph-bootstrap-dag.json +118 -0
- package/docs/templates/knowledge-sync-dag.json +178 -0
- package/docs/templates/knowledge-sync-draft.schema.json +71 -0
- package/docs/templates/product-line/AGENTS.md +8 -8
- package/docs/templates/product-line/README.md +9 -9
- package/docs/templates/product-line/acceptance.yaml +14 -14
- package/docs/templates/product-line/closeout.yaml +9 -9
- package/docs/templates/product-line/design.md +13 -13
- package/docs/templates/product-line/links.md +10 -10
- package/docs/templates/product-line/requirement.md +17 -17
- package/docs/templates/product-line/task-graph.yaml +15 -15
- package/docs/templates/product-line/task.yaml +64 -64
- package/docs/templates/product-line/test-plan.md +7 -7
- package/docs/templates/production-readiness-checklist.md +57 -57
- package/docs/templates/progress-log.md +17 -17
- package/docs/templates/project-start-checklist.md +9 -9
- package/docs/templates/qa-report.md +48 -48
- package/docs/templates/sprint-contract.md +29 -29
- package/docs/templates/worker-dogfood-evidence.md +80 -80
- package/docs/templates/worker-dogfood-setup.md +68 -68
- package/docs/verification-matrix.md +70 -66
- package/examples/decision-gate-agent-dag.json +177 -177
- package/examples/example-dag.json +46 -46
- package/examples/hybrid-loop-agent-dag.json +189 -189
- package/harness.json +66 -66
- package/package.json +88 -46
- package/scripts/check-product-line-docs.sh +29 -29
- package/scripts/check-task-pool-root.sh +32 -32
- package/scripts/kb-bootstrap-init-skeleton.sh +240 -0
- package/scripts/kb-graph-incremental-prepare.mjs +386 -0
- package/scripts/kb-graph-incremental-prepare.sh +5 -0
- package/scripts/kb-graph-materialize.mjs +105 -0
- package/scripts/kb-graph-materialize.sh +4 -0
- package/scripts/kb-graph-promote.mjs +164 -0
- package/scripts/kb-graph-promote.sh +4 -0
- package/scripts/kb-query.mjs +554 -0
- package/scripts/kb-query.sh +5 -0
- package/skills/agent-worker/SKILL.md +39 -37
- package/skills/agent-worker/references/agent-worker-operator.md +60 -43
- package/skills/ai-engineering-context/SKILL.md +48 -48
- package/skills/analyze-product-dependencies/SKILL.md +67 -0
- package/skills/analyze-product-dependencies/agents/openai.yaml +4 -0
- package/skills/analyze-product-dependencies/references/api-documentation-schema.md +30 -0
- package/skills/analyze-product-dependencies/references/dependency-analysis-schema.md +28 -0
- package/skills/analyze-product-dependencies/references/example.md +76 -0
- package/skills/analyze-product-dependencies/references/forward-test-cases.md +35 -0
- package/skills/analyze-product-dependencies/references/input-contract.md +11 -0
- package/skills/analyze-product-dependencies/references/scouting-rules.md +61 -0
- package/skills/analyze-product-dependencies/scripts/test-validators.mjs +267 -0
- package/skills/analyze-product-dependencies/scripts/validate-api-documentation.mjs +101 -0
- package/skills/analyze-product-dependencies/scripts/validate-dependency-analysis.mjs +142 -0
- package/skills/analyze-product-dependencies/scripts/validate-product-requirement-input.mjs +76 -0
- package/skills/analyze-product-dependencies/scripts/validation-helpers.mjs +146 -0
- package/skills/analyze-product-requirements/SKILL.md +90 -0
- package/skills/analyze-product-requirements/agents/openai.yaml +4 -0
- package/skills/analyze-product-requirements/references/acceptance-criteria.md +91 -0
- package/skills/analyze-product-requirements/references/clarification-and-knowledge.md +56 -0
- package/skills/analyze-product-requirements/references/example.md +86 -0
- package/skills/analyze-product-requirements/references/forward-test-cases.md +66 -0
- package/skills/analyze-product-requirements/references/product-analysis-schema.md +32 -0
- package/skills/analyze-product-requirements/references/product-requirement-schema.md +33 -0
- package/skills/analyze-product-requirements/references/requirement-clarification-schema.md +35 -0
- package/skills/analyze-product-requirements/scripts/test-validators.mjs +193 -0
- package/skills/analyze-product-requirements/scripts/validate-product-analysis.mjs +69 -0
- package/skills/analyze-product-requirements/scripts/validate-product-requirement.mjs +97 -0
- package/skills/analyze-product-requirements/scripts/validate-requirement-clarification.mjs +98 -0
- package/skills/analyze-product-requirements/scripts/validation-helpers.mjs +156 -0
- package/skills/code-review-core/SKILL.md +20 -20
- package/skills/codebase-scout/SKILL.md +19 -19
- package/skills/frontend-design-review/SKILL.md +66 -59
- package/skills/frontend-design-review/references/review-checklist.md +58 -37
- package/skills/frontend-implementation/SKILL.md +47 -51
- package/skills/frontend-implementation/references/code-standards.md +32 -34
- package/skills/frontend-implementation/references/design-spec.md +46 -46
- package/skills/frontend-implementation/references/node-contracts.md +76 -32
- package/skills/frontend-review/SKILL.md +59 -53
- package/skills/frontend-review/references/review-findings.md +47 -42
- package/skills/frontend-verification/SKILL.md +53 -40
- package/skills/frontend-verification/references/verification-checklist.md +68 -56
- package/skills/grill-me/SKILL.md +10 -10
- package/skills/grill-with-docs/SKILL.md +88 -88
- package/skills/grill-with-docs/adr-format.md +47 -47
- package/skills/grill-with-docs/context-format.md +60 -60
- package/skills/init-capability-evolution/SKILL.md +70 -70
- package/skills/loop-agent/SKILL.md +151 -151
- package/skills/loop-agent/references/README.md +67 -67
- package/skills/loop-agent/references/command-reference.md +505 -452
- package/skills/loop-agent/references/docs-converge.md +126 -126
- package/skills/loop-agent/references/harness-policy.md +263 -263
- package/skills/loop-agent/references/hybrid-dag.md +238 -233
- package/skills/loop-agent/references/learned/README.md +21 -21
- package/skills/loop-agent/references/long-running-loop.md +57 -57
- package/skills/loop-agent/references/model-routing.md +36 -36
- package/skills/loop-agent/references/multi-worktree.md +54 -54
- package/skills/loop-agent/references/one-shot-runs.md +85 -85
- package/skills/loop-agent/references/orchestrator-and-interventions.md +169 -169
- package/skills/loop-agent/references/pi-prompt.md +23 -23
- package/skills/loop-agent/references/pi-subagent-assisted-mode.md +84 -84
- package/skills/loop-agent/references/post-implementation-and-patterns.md +44 -44
- package/skills/loop-agent/references/task-workflow.md +89 -89
- package/skills/loop-agent/references/verification-and-failure-handling.md +139 -139
- package/skills/playwright-cli/SKILL.md +420 -0
- package/skills/playwright-cli/references/element-attributes.md +23 -0
- package/skills/playwright-cli/references/playwright-tests.md +39 -0
- package/skills/playwright-cli/references/request-mocking.md +87 -0
- package/skills/playwright-cli/references/running-code.md +241 -0
- package/skills/playwright-cli/references/session-management.md +225 -0
- package/skills/playwright-cli/references/storage-state.md +275 -0
- package/skills/playwright-cli/references/test-generation.md +433 -0
- package/skills/playwright-cli/references/tracing.md +139 -0
- package/skills/playwright-cli/references/video-recording.md +143 -0
- package/skills/playwright-cli-case-generator/SKILL.md +74 -0
- package/skills/requesting-code-review/SKILL.md +101 -101
- package/skills/requesting-code-review/code-reviewer.md +168 -168
- package/skills/systematic-debugging/CREATION-LOG.md +119 -119
- package/skills/systematic-debugging/SKILL.md +296 -296
- package/skills/systematic-debugging/condition-based-waiting-example.ts +158 -158
- package/skills/systematic-debugging/condition-based-waiting.md +115 -115
- package/skills/systematic-debugging/defense-in-depth.md +122 -122
- package/skills/systematic-debugging/find-polluter.sh +63 -63
- package/skills/systematic-debugging/root-cause-tracing.md +169 -169
- package/skills/systematic-debugging/test-academic.md +14 -14
- package/skills/systematic-debugging/test-pressure-1.md +58 -58
- package/skills/systematic-debugging/test-pressure-2.md +68 -68
- package/skills/systematic-debugging/test-pressure-3.md +69 -69
- package/skills/test-driven-development/SKILL.md +20 -20
- package/skills/using-git-worktrees/SKILL.md +215 -215
- package/skills/verification-before-completion/SKILL.md +154 -154
- package/skills/webapp-testing/SKILL.md +19 -19
|
@@ -19,6 +19,7 @@ export function buildExpandedChildTask(input) {
|
|
|
19
19
|
executor: child.executor,
|
|
20
20
|
role: child.role,
|
|
21
21
|
skills: child.skills,
|
|
22
|
+
toolProfile: child.toolProfile,
|
|
22
23
|
writePolicy: child.writePolicy,
|
|
23
24
|
allowedPaths: renderDynamicPatternList(child.allowedPaths, item, index, expansion.itemName) ?? [],
|
|
24
25
|
forbiddenPaths: renderDynamicPatternList(child.forbiddenPaths, item, index, expansion.itemName) ?? [],
|
|
@@ -140,10 +141,72 @@ export async function executeDynamicMapExpansion(input) {
|
|
|
140
141
|
};
|
|
141
142
|
await writeDagRunJsonArtifact(input.runDir, `expansions/${input.task.id}.expansion.json`, manifest);
|
|
142
143
|
await input.persistState();
|
|
143
|
-
|
|
144
|
+
const blockedChildren = [];
|
|
145
|
+
const tokenBudget = input.expansion.tokenBudget;
|
|
146
|
+
const isBudgetBlockedRecord = (record) => record?.status === "SKIPPED" &&
|
|
147
|
+
typeof record.stderr === "string" &&
|
|
148
|
+
record.stderr.includes("token-budget-exhausted");
|
|
149
|
+
let totalTokensUsed = 0;
|
|
150
|
+
let tokenBudgetExhausted = false;
|
|
151
|
+
// Resume-safe seed: count completed children and preserve prior budget skips.
|
|
152
|
+
if (tokenBudget !== undefined) {
|
|
153
|
+
for (const child of children) {
|
|
154
|
+
const record = input.state.nodes[child.id];
|
|
155
|
+
if (record?.status === "FINISHED") {
|
|
156
|
+
totalTokensUsed += record.tokensUsed ?? 0;
|
|
157
|
+
}
|
|
158
|
+
else if (isBudgetBlockedRecord(record)) {
|
|
159
|
+
if (!blockedChildren.some((entry) => entry.nodeId === child.id)) {
|
|
160
|
+
blockedChildren.push({
|
|
161
|
+
nodeId: child.id,
|
|
162
|
+
reason: "token-budget-exhausted",
|
|
163
|
+
});
|
|
164
|
+
}
|
|
165
|
+
}
|
|
166
|
+
}
|
|
167
|
+
if ((tokenBudget.maxTotalTokens !== undefined &&
|
|
168
|
+
totalTokensUsed >= tokenBudget.maxTotalTokens) ||
|
|
169
|
+
blockedChildren.length > 0) {
|
|
170
|
+
tokenBudgetExhausted = true;
|
|
171
|
+
}
|
|
172
|
+
}
|
|
173
|
+
for (let childIndex = 0; childIndex < children.length; childIndex += 1) {
|
|
174
|
+
const child = children[childIndex];
|
|
144
175
|
const childRecord = input.state.nodes[child.id];
|
|
176
|
+
// Never re-run completed or budget-blocked children on resume.
|
|
145
177
|
if (childRecord?.status === "FINISHED")
|
|
146
178
|
continue;
|
|
179
|
+
if (isBudgetBlockedRecord(childRecord))
|
|
180
|
+
continue;
|
|
181
|
+
if (tokenBudget !== undefined &&
|
|
182
|
+
(tokenBudgetExhausted ||
|
|
183
|
+
(tokenBudget.maxTotalTokens !== undefined &&
|
|
184
|
+
totalTokensUsed >= tokenBudget.maxTotalTokens))) {
|
|
185
|
+
for (const remaining of children.slice(childIndex)) {
|
|
186
|
+
const record = input.state.nodes[remaining.id];
|
|
187
|
+
if (!record || record.status === "FINISHED")
|
|
188
|
+
continue;
|
|
189
|
+
if (isBudgetBlockedRecord(record)) {
|
|
190
|
+
if (!blockedChildren.some((entry) => entry.nodeId === remaining.id)) {
|
|
191
|
+
blockedChildren.push({
|
|
192
|
+
nodeId: remaining.id,
|
|
193
|
+
reason: "token-budget-exhausted",
|
|
194
|
+
});
|
|
195
|
+
}
|
|
196
|
+
continue;
|
|
197
|
+
}
|
|
198
|
+
record.status = "SKIPPED";
|
|
199
|
+
record.stderr = "blocked: token-budget-exhausted";
|
|
200
|
+
if (!blockedChildren.some((entry) => entry.nodeId === remaining.id)) {
|
|
201
|
+
blockedChildren.push({
|
|
202
|
+
nodeId: remaining.id,
|
|
203
|
+
reason: "token-budget-exhausted",
|
|
204
|
+
});
|
|
205
|
+
}
|
|
206
|
+
}
|
|
207
|
+
await input.persistState();
|
|
208
|
+
break;
|
|
209
|
+
}
|
|
147
210
|
await executeDagNode({
|
|
148
211
|
nodeId: child.id,
|
|
149
212
|
tasksById: input.tasksById,
|
|
@@ -159,8 +222,25 @@ export async function executeDynamicMapExpansion(input) {
|
|
|
159
222
|
throw new Error(`dynamic child node ${child.id} requested a human pause; map_agent children do not support pause in v0`);
|
|
160
223
|
},
|
|
161
224
|
});
|
|
225
|
+
const executedTokens = input.state.nodes[child.id]?.tokensUsed ?? 0;
|
|
226
|
+
totalTokensUsed += executedTokens;
|
|
227
|
+
if (tokenBudget &&
|
|
228
|
+
((tokenBudget.maxTokensPerCase !== undefined &&
|
|
229
|
+
executedTokens >= tokenBudget.maxTokensPerCase) ||
|
|
230
|
+
(tokenBudget.maxTotalTokens !== undefined &&
|
|
231
|
+
totalTokensUsed >= tokenBudget.maxTotalTokens))) {
|
|
232
|
+
tokenBudgetExhausted = true;
|
|
233
|
+
}
|
|
162
234
|
}
|
|
163
|
-
const
|
|
235
|
+
const budgetBlockedIds = new Set(blockedChildren.map((entry) => entry.nodeId));
|
|
236
|
+
const failedChildren = childNodeIds.filter((nodeId) => {
|
|
237
|
+
const record = input.state.nodes[nodeId];
|
|
238
|
+
if (!record || record.status === "FINISHED")
|
|
239
|
+
return false;
|
|
240
|
+
if (budgetBlockedIds.has(nodeId) || isBudgetBlockedRecord(record))
|
|
241
|
+
return false;
|
|
242
|
+
return true;
|
|
243
|
+
});
|
|
164
244
|
const aggregate = {
|
|
165
245
|
workflowNodeId: input.expansion.workflowNodeId,
|
|
166
246
|
itemCount: items.length,
|
|
@@ -172,9 +252,17 @@ export async function executeDynamicMapExpansion(input) {
|
|
|
172
252
|
stdout: input.state.nodes[nodeId]?.stdout,
|
|
173
253
|
output: parseJsonFromText(input.state.nodes[nodeId]?.stdout),
|
|
174
254
|
assistantText: input.state.nodes[nodeId]?.assistantText,
|
|
255
|
+
blocked: blockedChildren.find((child) => child.nodeId === nodeId)?.reason ??
|
|
256
|
+
(isBudgetBlockedRecord(input.state.nodes[nodeId])
|
|
257
|
+
? "token-budget-exhausted"
|
|
258
|
+
: undefined),
|
|
175
259
|
})),
|
|
260
|
+
tokensUsed: totalTokensUsed,
|
|
176
261
|
};
|
|
177
262
|
return {
|
|
263
|
+
// A post-case token stop is an expected bounded outcome; downstream review
|
|
264
|
+
// must receive its aggregate rather than be skipped with the map barrier.
|
|
265
|
+
// Real child failures remain fail-closed even when later cases are budget-blocked.
|
|
178
266
|
ok: failedChildren.length === 0,
|
|
179
267
|
stdout: JSON.stringify(aggregate),
|
|
180
268
|
stderr: failedChildren.length > 0
|
|
@@ -22,6 +22,10 @@ const FOLLOW_UP_BY_PRODUCT_LINE = {
|
|
|
22
22
|
NeedsHuman: "human-review",
|
|
23
23
|
Unknown: "human triage",
|
|
24
24
|
};
|
|
25
|
+
function isFrontendDesignGateNode(nodeId) {
|
|
26
|
+
const lower = nodeId.toLowerCase();
|
|
27
|
+
return lower.includes("design-gate");
|
|
28
|
+
}
|
|
25
29
|
function routeToProductLine(input) {
|
|
26
30
|
const normalized = input.normalizedFailureCategory;
|
|
27
31
|
if (!normalized || normalized === "success")
|
|
@@ -47,6 +51,9 @@ function routeToProductLine(input) {
|
|
|
47
51
|
if (nodeId.includes("test") || raw.includes("test-bug")) {
|
|
48
52
|
return "TestBug";
|
|
49
53
|
}
|
|
54
|
+
if (isFrontendDesignGateNode(nodeId)) {
|
|
55
|
+
return "ContractMismatch";
|
|
56
|
+
}
|
|
50
57
|
return "ProductBug";
|
|
51
58
|
case "static-error":
|
|
52
59
|
return "SpecUnclear";
|
|
@@ -75,8 +82,12 @@ export function routeDagFailure(input) {
|
|
|
75
82
|
const productLineFailureCategory = routeToProductLine(input);
|
|
76
83
|
if (!productLineFailureCategory)
|
|
77
84
|
return {};
|
|
85
|
+
const recommendedFollowUp = productLineFailureCategory === "ContractMismatch" &&
|
|
86
|
+
isFrontendDesignGateNode(input.nodeId ?? "")
|
|
87
|
+
? "frontend-plan-revision-and-rerun"
|
|
88
|
+
: FOLLOW_UP_BY_PRODUCT_LINE[productLineFailureCategory];
|
|
78
89
|
return {
|
|
79
90
|
productLineFailureCategory,
|
|
80
|
-
recommendedFollowUp
|
|
91
|
+
recommendedFollowUp,
|
|
81
92
|
};
|
|
82
93
|
}
|