taskchef 5.1.1 → 5.3.0

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "taskchef",
-  "version": "5.1.1",
+  "version": "5.3.0",
   "description": "Dispatch work from a data-only workspace to visible Codex project tasks.",
   "author": {
     "name": "Favo Yang",

package/README.md

@@ -241,6 +241,17 @@ loads and validates configured projects, and returns a generated task UUID,
 preparation timestamp, and exact correlation marker. `task record` accepts one
 JSON value only from closed, non-interactive standard input.
 
+For repeatable live delegation measurements, run
+`npm run benchmark:e2e -- write`. It reads one non-interactive JSON value,
+validates a stable schema, derives durations and summary totals, and writes a
+timestamped result under the supplied output directory (default:
+`reports/e2e-benchmarks`). Use `validate <file>` to verify a saved result and
+`clean [directory]` to remove only prior TaskChef end-to-end result JSON files.
+Start from `assets/e2e-benchmark-example.json`; the writer accepts strict
+schema fields only and supports stopped workflows after preparation, creation,
+or recording failures. The writer stamps `taskchefVersion` from its own package;
+saved files retain that version for historical validation.
+
 ### One-time upgrade from an older workspace
 
 TaskChef 5 does not include a general migration command. For a one-time upgrade,
@@ -345,17 +356,21 @@ taskchef task show t1
 taskchef task list
 taskchef task list --project payments
 taskchef task list --ascending
+taskchef task list --full-id
 taskchef task summary
 ```
 
-Human-readable task listings put the scannable fields first and the durable ID
-last. Values are kept in full and aligned in columns. Tasks are newest-first by
-default; pass `--ascending` to list them from oldest to newest. The same order
-applies to the `tasks` array in `--json` output.
+Human-readable task listings include both the task ID and Codex thread ID.
+UUID-shaped IDs use their first eight-character section by default; pass
+`--full-id` to show both IDs in full. Null thread IDs appear as `-`, consistent
+with other empty table cells. Tasks are newest-first by default; pass
+`--ascending` to list them from oldest to newest. ID formatting does not alter
+the complete values in `--json` output, and the selected order applies to its
+`tasks` array.
 
 ```text
-TITLE           PROJECT   CREATED                   ID
-Add retry logs  payments  2026-08-12T10:00:00.000Z  c0f010ff-84f2-4838-a69d-0ff1f5d721d7
+TITLE           PROJECT   CREATED                   ID        THREAD ID
+Add retry logs  payments  2026-08-12T10:00:00.000Z  c0f010ff  019f9d46
 ```
 
 The complete data contract is in [SPEC.md](SPEC.md). Deferred ideas are in

package/SPEC.md

@@ -228,6 +228,51 @@ helpers with injected thread-tool callbacks, while the skill owns the actual
 desktop-tool calls and the CLI remains responsible only for validated data
 operations.
 
+### End-to-end benchmark results
+
+An explicitly requested live benchmark writes one ignored, timestamped JSON
+artifact through `scripts/e2e-benchmark.js`. Schema version 1 contains:
+
+- benchmark name, TaskChef version, run ID, and wall-clock start/end
+- project, title, and exact unmarked workload prompt
+- TaskChef task ID, nullable durable/client IDs, recording state, resolution,
+  and attempt count
+- ISO start/end, derived duration, and outcome for preparation/project listing,
+  task creation, recording, and optional provisional resolution
+- boolean record, marker, executor-output, and candidate-filter-effectiveness
+  validation results
+- derived total wall time, measured stage time, orchestration overhead,
+  resolution state, and attempt count
+
+Stage outcomes are `success|failed` for preparation,
+`durable|provisional|failed` for creation, `recorded|failed` for recording, and
+`native|discovered|unresolved|failed` for provisional resolution. `failed`
+distinguishes a terminal resolver error from a completed no-match checkpoint,
+which must proceed to the second fallback attempt. Task resolution is
+`immediate|native|discovered|unresolved`. Preparation failure has only the
+preparation stage and a null task ID; creation failure stops after creation;
+recording failure stops before provisional resolution. The committed example
+shows the durable success shape, while these transition rules define the
+shorter failure and longer provisional shapes.
+The writer derives `taskchefVersion` from the running package instead of
+trusting template input. Raw executor output and transcripts are never stored;
+`outputVerified` records only whether the requested output was verified.
+
+The writer rejects missing required stages, duplicate or unknown stages,
+invalid timestamps, contradictory workflow outcomes, overlapping stages,
+unknown fields, and overwriting an existing run. Later stages are omitted when
+preparation or creation fails, and provisional resolution is omitted when task
+recording fails. Fallback snapshot observations include the complete recent
+task count plus the filtered candidate and exact-match counts, from which
+candidate-filter effectiveness is checked. Each snapshot records
+`resolveWriteOutcome` as `not-attempted`, `succeeded`, or `failed`, so a unique
+match followed by an atomic write failure remains an honest unresolved result.
+A compact valid starting document is committed as
+`assets/e2e-benchmark-example.json`. Filenames use
+`<startedAt-with-colons-replaced>-taskchef-delegate-e2e.json`. Its cleanup
+operation removes only files matching the full generated filename grammar in
+the selected results directory.
+
 `task record` rejects an interactive TTY before reading because its protocol is
 exactly one JSON value followed by EOF. Workspace-lock contention is retried for
 up to seven seconds, while permanent permission failures such as `EPERM` or
@@ -245,7 +290,10 @@ The CLI reads persisted history without contacting Codex:
 - `task show <id>` returns one entry.
 - `task list` returns entries newest-first by creation time, optionally filtered
   by historical project name or exact path. `--ascending` returns oldest-first.
-  The selected order applies to both human rows and the JSON `tasks` array.
+  Human rows include task and thread ID columns, abbreviating UUID-shaped IDs
+  to their first eight-character section unless `--full-id` is passed. Null
+  thread IDs display as `-`. ID formatting does not alter JSON values, and the
+  selected order applies to both human rows and the JSON `tasks` array.
 - `task summary` returns the total and per-project counts.
 - `task resolve <id> --thread-id <thread-id>` atomically fills one nullable
   thread ID after Codex verifies the exact structured marker match.

package/assets/e2e-benchmark-example.json

@@ -0,0 +1,46 @@
+{
+  "schemaVersion": 1,
+  "benchmark": "taskchef-delegate-e2e",
+  "runId": "replace-with-run-id",
+  "startedAt": "2026-08-13T06:30:00.000Z",
+  "completedAt": "2026-08-13T06:30:05.000Z",
+  "workload": {
+    "project": "example-project",
+    "title": "Example workload",
+    "prompt": "Return the requested example output."
+  },
+  "task": {
+    "taskId": "00000000-0000-4000-8000-000000000000",
+    "threadId": "00000000-0000-7000-8000-000000000000",
+    "clientThreadId": null,
+    "recorded": true,
+    "resolution": "immediate",
+    "resolutionAttempts": 0
+  },
+  "stages": [
+    {
+      "name": "prepare-and-list-projects",
+      "startedAt": "2026-08-13T06:30:00.000Z",
+      "completedAt": "2026-08-13T06:30:00.200Z",
+      "outcome": "success"
+    },
+    {
+      "name": "create-thread",
+      "startedAt": "2026-08-13T06:30:01.000Z",
+      "completedAt": "2026-08-13T06:30:01.100Z",
+      "outcome": "durable"
+    },
+    {
+      "name": "record-task",
+      "startedAt": "2026-08-13T06:30:02.000Z",
+      "completedAt": "2026-08-13T06:30:04.000Z",
+      "outcome": "recorded"
+    }
+  ],
+  "validation": {
+    "recordVerified": true,
+    "markerVerified": true,
+    "outputVerified": false,
+    "candidateFilterEffective": false
+  }
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "taskchef",
-  "version": "5.1.1",
+  "version": "5.3.0",
   "description": "A non-blocking interactive dispatcher for visible Codex tasks.",
   "license": "MIT",
   "author": "Favo Yang",
@@ -25,6 +25,7 @@
     "index.js",
     "SPEC.md",
     "scripts/benchmark-dispatch-prepare.js",
+    "scripts/e2e-benchmark.js",
     "src",
     "skills/taskchef-bootstrap",
     "skills/taskchef-delegate",
@@ -39,6 +40,7 @@
   },
   "scripts": {
     "benchmark:dispatch": "node scripts/benchmark-dispatch-prepare.js",
+    "benchmark:e2e": "node scripts/e2e-benchmark.js",
     "test": "node --test tests/taskchef.test.js"
   },
   "dependencies": {

package/scripts/e2e-benchmark.js

@@ -0,0 +1,517 @@
+#!/usr/bin/env node
+
+import { mkdir, readFile, readdir, unlink, writeFile } from "node:fs/promises";
+import path from "node:path";
+import { fileURLToPath } from "node:url";
+
+const BENCHMARK_NAME = "taskchef-delegate-e2e";
+const STAGE_NAMES = [
+  "prepare-and-list-projects",
+  "create-thread",
+  "record-task",
+  "resolve-provisional",
+];
+const STAGE_OUTCOMES = Object.freeze({
+  "prepare-and-list-projects": new Set(["success", "failed"]),
+  "create-thread": new Set(["durable", "provisional", "failed"]),
+  "record-task": new Set(["recorded", "failed"]),
+  "resolve-provisional": new Set(["native", "discovered", "unresolved", "failed"]),
+});
+const RESOLUTIONS = new Set(["immediate", "native", "discovered", "unresolved"]);
+const RESULT_FILENAME_PATTERN = /^\d{4}-\d{2}-\d{2}T\d{2}-\d{2}-\d{2}\.\d{3}Z-taskchef-delegate-e2e\.json$/;
+const UUID_PATTERN = /^[0-9a-f]{8}-[0-9a-f]{4}-[1-8][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$/;
+const SEMVER_PATTERN = /^(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)(?:-((?:0|[1-9]\d*|\d*[A-Za-z-][0-9A-Za-z-]*)(?:\.(?:0|[1-9]\d*|\d*[A-Za-z-][0-9A-Za-z-]*))*))?(?:\+([0-9A-Za-z-]+(?:\.[0-9A-Za-z-]+)*))?$/;
+
+function requireExactKeys(value, allowed, name) {
+  const unknown = Object.keys(value).filter((key) => !allowed.includes(key));
+  if (unknown.length > 0) throw new Error(`${name} has unknown field ${unknown[0]}`);
+}
+
+function requireObject(value, name) {
+  if (!value || typeof value !== "object" || Array.isArray(value)) {
+    throw new Error(`${name} must be an object`);
+  }
+  return value;
+}
+
+function requireString(value, name) {
+  if (typeof value !== "string" || value.trim().length === 0) {
+    throw new Error(`${name} must be a non-empty string`);
+  }
+  return value;
+}
+
+function timestamp(value, name) {
+  requireString(value, name);
+  if (!/^\d{4}-\d{2}-\d{2}T/.test(value)) {
+    throw new Error(`${name} must use a four-digit UTC year`);
+  }
+  const milliseconds = Date.parse(value);
+  if (!Number.isFinite(milliseconds) || new Date(milliseconds).toISOString() !== value) {
+    throw new Error(`${name} must be a canonical UTC ISO timestamp`);
+  }
+  return milliseconds;
+}
+
+function nullableString(value, name) {
+  if (value === null) return null;
+  return requireString(value, name);
+}
+
+function managedResultFilename(name) {
+  if (!RESULT_FILENAME_PATTERN.test(name)) return false;
+  const timestampPart = name.slice(0, -`-${BENCHMARK_NAME}.json`.length);
+  const iso = `${timestampPart.slice(0, 13)}:${timestampPart.slice(14, 16)}:${timestampPart.slice(17)}`;
+  try {
+    timestamp(iso, "result filename timestamp");
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+function requireNonnegativeNumber(value, name) {
+  if (typeof value !== "number" || !Number.isFinite(value) || value < 0) {
+    throw new Error(`${name} must be a nonnegative number`);
+  }
+  return value;
+}
+
+function normalizeObservations(
+  input,
+  startedMs,
+  completedMs,
+  preparationStage,
+  creationStage,
+  recordingStage,
+  resolutionStage,
+  resolutionAttempts,
+) {
+  if (input === undefined) return undefined;
+  const observations = requireObject(input, "observations");
+  requireExactKeys(observations, [
+    "preparation",
+    "resolutionSnapshots",
+    "validationDurationMs",
+    "candidateMetadata",
+  ], "observations");
+  const result = {};
+  if (observations.preparation !== undefined) {
+    const preparation = requireObject(observations.preparation, "observations.preparation");
+    requireExactKeys(preparation, ["dispatchPrepareMs", "nativeProjectListMs"], "observations.preparation");
+    result.preparation = {
+      dispatchPrepareMs: requireNonnegativeNumber(preparation.dispatchPrepareMs, "observations.preparation.dispatchPrepareMs"),
+      nativeProjectListMs: requireNonnegativeNumber(preparation.nativeProjectListMs, "observations.preparation.nativeProjectListMs"),
+    };
+    const preparationDurationMs = timestamp(preparationStage.completedAt, "prepare-and-list-projects.completedAt") -
+      timestamp(preparationStage.startedAt, "prepare-and-list-projects.startedAt");
+    if (Object.values(result.preparation).some((durationMs) => durationMs > preparationDurationMs)) {
+      throw new Error("observations.preparation durations must fit within the preparation stage");
+    }
+  }
+  if (observations.resolutionSnapshots !== undefined) {
+    if (!Array.isArray(observations.resolutionSnapshots)) {
+      throw new Error("observations.resolutionSnapshots must be an array");
+    }
+    let previousSnapshotStartedMs = null;
+    let previousSnapshotCompletedMs = null;
+    result.resolutionSnapshots = observations.resolutionSnapshots.map((snapshot, index) => {
+      requireObject(snapshot, `observations.resolutionSnapshots[${index}]`);
+      requireExactKeys(snapshot, [
+        "attempt", "startedAt", "completedAt", "recentTaskCount", "candidateCount", "exactMatchCount",
+        "resolveWriteMs", "resolveWriteOutcome",
+      ], `observations.resolutionSnapshots[${index}]`);
+      if (!Number.isInteger(snapshot.attempt) || snapshot.attempt !== index + 1 || snapshot.attempt > resolutionAttempts) {
+        throw new Error(`observations.resolutionSnapshots[${index}].attempt must be sequential and within resolutionAttempts`);
+      }
+      const snapshotStartedMs = timestamp(snapshot.startedAt, `observations.resolutionSnapshots[${index}].startedAt`);
+      const snapshotCompletedMs = timestamp(snapshot.completedAt, `observations.resolutionSnapshots[${index}].completedAt`);
+      const resolutionStartedMs = resolutionStage ? timestamp(resolutionStage.startedAt, "resolve-provisional.startedAt") : null;
+      const resolutionCompletedMs = resolutionStage ? timestamp(resolutionStage.completedAt, "resolve-provisional.completedAt") : null;
+      if (
+        resolutionStartedMs === null || snapshotStartedMs < resolutionStartedMs ||
+        snapshotCompletedMs < snapshotStartedMs || snapshotCompletedMs > resolutionCompletedMs ||
+        snapshotStartedMs < startedMs || snapshotCompletedMs > completedMs
+      ) {
+        throw new Error(`observations.resolutionSnapshots[${index}] must fall within the resolution stage`);
+      }
+      const firstCheckpointMs = Math.max(
+        timestamp(creationStage.completedAt, "create-thread.completedAt") + 10_000,
+        timestamp(recordingStage.completedAt, "record-task.completedAt"),
+      );
+      if (index === 0 && snapshotStartedMs < firstCheckpointMs) {
+        throw new Error("the first resolution snapshot must respect the 10-second catch-up checkpoint");
+      }
+      if (previousSnapshotCompletedMs !== null && snapshotStartedMs < previousSnapshotCompletedMs) {
+        throw new Error("resolutionSnapshots must be ordered and non-overlapping");
+      }
+      if (previousSnapshotStartedMs !== null && snapshotStartedMs - previousSnapshotStartedMs < 20_000) {
+        throw new Error("resolutionSnapshots must start at least 20 seconds apart");
+      }
+      for (const name of ["recentTaskCount", "candidateCount", "exactMatchCount", "resolveWriteMs"]) {
+        requireNonnegativeNumber(snapshot[name], `observations.resolutionSnapshots[${index}].${name}`);
+      }
+      if (!["not-attempted", "succeeded", "failed"].includes(snapshot.resolveWriteOutcome)) {
+        throw new Error(`observations.resolutionSnapshots[${index}].resolveWriteOutcome is invalid`);
+      }
+      if ((snapshot.exactMatchCount === 1) !== (snapshot.resolveWriteOutcome !== "not-attempted")) {
+        throw new Error(`observations.resolutionSnapshots[${index}] resolve write must agree with exact matches`);
+      }
+      if (snapshot.resolveWriteOutcome === "not-attempted" && snapshot.resolveWriteMs !== 0) {
+        throw new Error(`observations.resolutionSnapshots[${index}].resolveWriteMs must be zero when no write was attempted`);
+      }
+      if (!Number.isInteger(snapshot.recentTaskCount) || !Number.isInteger(snapshot.candidateCount) || !Number.isInteger(snapshot.exactMatchCount)) {
+        throw new Error(`observations.resolutionSnapshots[${index}] counts must be integers`);
+      }
+      if (snapshot.recentTaskCount > 50) {
+        throw new Error(`observations.resolutionSnapshots[${index}].recentTaskCount must not exceed 50`);
+      }
+      if (snapshot.candidateCount > snapshot.recentTaskCount || snapshot.exactMatchCount > snapshot.candidateCount) {
+        throw new Error(`observations.resolutionSnapshots[${index}] counts are inconsistent`);
+      }
+      if (snapshot.resolveWriteMs > snapshotCompletedMs - snapshotStartedMs) {
+        throw new Error(`observations.resolutionSnapshots[${index}].resolveWriteMs exceeds snapshot duration`);
+      }
+      previousSnapshotStartedMs = snapshotStartedMs;
+      previousSnapshotCompletedMs = snapshotCompletedMs;
+      return { ...snapshot };
+    });
+  }
+  if (observations.validationDurationMs !== undefined) {
+    result.validationDurationMs = requireNonnegativeNumber(observations.validationDurationMs, "observations.validationDurationMs");
+    const finalStage = resolutionStage ?? recordingStage ?? creationStage ?? preparationStage;
+    const postWorkflowMs = completedMs - timestamp(finalStage.completedAt, `${finalStage.name}.completedAt`);
+    if (result.validationDurationMs > postWorkflowMs) {
+      throw new Error("observations.validationDurationMs must fit after the workflow stages");
+    }
+  }
+  if (observations.candidateMetadata !== undefined) {
+    const metadata = requireObject(observations.candidateMetadata, "observations.candidateMetadata");
+    const names = ["targetProjectIdPresent", "targetCreatedAtPresent", "targetEnvironmentPresent", "targetCwdPresent"];
+    requireExactKeys(metadata, names, "observations.candidateMetadata");
+    for (const name of names) {
+      if (typeof metadata[name] !== "boolean") throw new Error(`observations.candidateMetadata.${name} must be boolean`);
+    }
+    result.candidateMetadata = { ...metadata };
+  }
+  return result;
+}
+
+export function normalizeBenchmarkResult(input, { requireDerived = false } = {}) {
+  const value = structuredClone(requireObject(input, "benchmark result"));
+  requireExactKeys(value, [
+    "schemaVersion", "benchmark", "taskchefVersion", "runId", "startedAt", "completedAt",
+    "workload", "task", "stages", "validation", "observations", "summary",
+  ], "benchmark result");
+  if (value.schemaVersion !== 1) throw new Error("schemaVersion must be 1");
+  if (value.benchmark !== BENCHMARK_NAME) {
+    throw new Error(`benchmark must be ${BENCHMARK_NAME}`);
+  }
+  requireString(value.taskchefVersion, "taskchefVersion");
+  if (!SEMVER_PATTERN.test(value.taskchefVersion)) throw new Error("taskchefVersion must be a semantic version");
+  requireString(value.runId, "runId");
+  const startedMs = timestamp(value.startedAt, "startedAt");
+  const completedMs = timestamp(value.completedAt, "completedAt");
+  if (completedMs < startedMs) throw new Error("completedAt must not precede startedAt");
+
+  const workload = requireObject(value.workload, "workload");
+  requireExactKeys(workload, ["project", "title", "prompt"], "workload");
+  requireString(workload.project, "workload.project");
+  requireString(workload.title, "workload.title");
+  requireString(workload.prompt, "workload.prompt");
+  if (/<!--\s*taskchef_id=/i.test(workload.prompt)) {
+    throw new Error("workload.prompt must not contain a TaskChef marker");
+  }
+
+  const task = requireObject(value.task, "task");
+  requireExactKeys(task, [
+    "taskId", "threadId", "clientThreadId", "recorded", "resolution", "resolutionAttempts",
+  ], "task");
+  task.taskId = nullableString(task.taskId, "task.taskId");
+  if (task.taskId !== null && !UUID_PATTERN.test(task.taskId)) {
+    throw new Error("task.taskId must be a lowercase UUID");
+  }
+  task.threadId = nullableString(task.threadId, "task.threadId");
+  task.clientThreadId = nullableString(task.clientThreadId, "task.clientThreadId");
+  if (task.threadId !== null && task.threadId.trim().toLowerCase().startsWith("local:")) {
+    throw new Error("task.threadId must not use the provisional local: namespace");
+  }
+  if (task.threadId !== null && task.threadId === task.clientThreadId) {
+    throw new Error("task.threadId must differ from task.clientThreadId");
+  }
+  if (typeof task.recorded !== "boolean") throw new Error("task.recorded must be boolean");
+  requireString(task.resolution, "task.resolution");
+  if (!RESOLUTIONS.has(task.resolution)) throw new Error("task.resolution is invalid");
+  if (!Number.isInteger(task.resolutionAttempts) || task.resolutionAttempts < 0) {
+    throw new Error("task.resolutionAttempts must be a nonnegative integer");
+  }
+  if (task.resolutionAttempts > 2) throw new Error("task.resolutionAttempts must not exceed 2");
+
+  if (!Array.isArray(value.stages)) throw new Error("stages must be an array");
+  const stagesByName = new Map();
+  let previousCompletedMs = startedMs;
+  for (const [index, stage] of value.stages.entries()) {
+    requireObject(stage, `stages[${index}]`);
+    requireExactKeys(stage, ["name", "startedAt", "completedAt", "outcome", "durationMs"], `stages[${index}]`);
+    requireString(stage.name, `stages[${index}].name`);
+    if (!STAGE_NAMES.includes(stage.name)) throw new Error(`unknown stage ${stage.name}`);
+    if (stagesByName.has(stage.name)) throw new Error(`duplicate stage ${stage.name}`);
+    const stageStartedMs = timestamp(stage.startedAt, `${stage.name}.startedAt`);
+    const stageCompletedMs = timestamp(stage.completedAt, `${stage.name}.completedAt`);
+    if (stageCompletedMs < stageStartedMs) {
+      throw new Error(`${stage.name}.completedAt must not precede startedAt`);
+    }
+    if (stageStartedMs < startedMs || stageCompletedMs > completedMs) {
+      throw new Error(`${stage.name} must fall within the benchmark run`);
+    }
+    if (stageStartedMs < previousCompletedMs) throw new Error("stages must be ordered and non-overlapping");
+    requireString(stage.outcome, `${stage.name}.outcome`);
+    if (!STAGE_OUTCOMES[stage.name].has(stage.outcome)) {
+      throw new Error(`${stage.name}.outcome is invalid`);
+    }
+    const durationMs = stageCompletedMs - stageStartedMs;
+    if (requireDerived && stage.durationMs === undefined) {
+      throw new Error(`${stage.name}.durationMs is required in a saved result`);
+    }
+    if (stage.durationMs !== undefined && stage.durationMs !== durationMs) {
+      throw new Error(`${stage.name}.durationMs does not match its timestamps`);
+    }
+    stage.durationMs = durationMs;
+    stagesByName.set(stage.name, stage);
+    previousCompletedMs = stageCompletedMs;
+  }
+  if (!stagesByName.has(STAGE_NAMES[0])) throw new Error(`missing required stage ${STAGE_NAMES[0]}`);
+  const resolutionStagePresent = stagesByName.has("resolve-provisional");
+  if (task.resolutionAttempts > 0 && !resolutionStagePresent) {
+    throw new Error("resolutionAttempts must agree with the resolve-provisional stage");
+  }
+  if (task.resolutionAttempts === 0 && resolutionStagePresent) {
+    throw new Error("zero resolutionAttempts must omit the resolve-provisional stage");
+  }
+
+  if (!value.stages.every((stage, index) => stage.name === STAGE_NAMES[index])) {
+    throw new Error("stages must use the documented workflow order");
+  }
+
+  const preparationOutcome = stagesByName.get("prepare-and-list-projects").outcome;
+  const creationOutcome = stagesByName.get("create-thread")?.outcome;
+  const recordingOutcome = stagesByName.get("record-task")?.outcome;
+  const resolutionOutcome = stagesByName.get("resolve-provisional")?.outcome;
+  if (preparationOutcome === "failed") {
+    if (
+      value.stages.length !== 1 || task.taskId !== null || task.threadId !== null || task.clientThreadId !== null ||
+      task.recorded || task.resolution !== "unresolved" || task.resolutionAttempts !== 0
+    ) throw new Error("failed preparation must stop the workflow unresolved");
+  } else if (task.taskId === null || creationOutcome === undefined) {
+    throw new Error("successful preparation requires a task ID and creation stage");
+  }
+  if (creationOutcome !== undefined && creationOutcome !== "failed" && recordingOutcome === undefined) {
+    throw new Error("successful creation requires a record-task stage");
+  }
+  if (recordingOutcome !== undefined && (recordingOutcome === "recorded") !== task.recorded) {
+    throw new Error("record-task outcome must agree with task.recorded");
+  }
+  if (creationOutcome === "durable") {
+    if (task.resolution !== "immediate" || task.threadId === null || resolutionStagePresent) {
+      throw new Error("durable creation must be an immediate durable resolution");
+    }
+  } else if (creationOutcome === "provisional") {
+    if (task.clientThreadId === null) throw new Error("provisional creation requires a clientThreadId");
+    if (task.recorded) {
+      if (task.resolutionAttempts === 0) {
+        if (resolutionStagePresent || task.resolution !== "unresolved" || task.threadId !== null) {
+          throw new Error("zero-attempt provisional creation must remain unresolved");
+        }
+      } else if (
+        !resolutionStagePresent ||
+        (resolutionOutcome !== task.resolution && !(task.resolution === "unresolved" && resolutionOutcome === "failed"))
+      ) {
+        throw new Error("recorded provisional creation must agree with its resolution stage");
+      }
+      if ((task.resolution === "unresolved") !== (task.threadId === null)) {
+        throw new Error("provisional resolution must agree with task.threadId");
+      }
+    } else if (
+      resolutionStagePresent || task.resolution !== "unresolved" || task.threadId !== null || task.resolutionAttempts !== 0
+    ) {
+      throw new Error("unrecorded provisional creation must remain unresolved");
+    }
+  } else if (
+    creationOutcome === "failed" && (
+      value.stages.length !== 2 || task.resolution !== "unresolved" || task.threadId !== null ||
+      task.clientThreadId !== null || task.recorded || resolutionStagePresent
+    )
+  ) {
+    throw new Error("failed creation must remain unrecorded and unresolved");
+  }
+
+  const validation = requireObject(value.validation, "validation");
+  const validationNames = [
+    "recordVerified",
+    "markerVerified",
+    "outputVerified",
+    "candidateFilterEffective",
+  ];
+  requireExactKeys(validation, validationNames, "validation");
+  for (const name of validationNames) {
+    if (typeof validation[name] !== "boolean") throw new Error(`validation.${name} must be boolean`);
+  }
+  if (validation.recordVerified && !task.recorded) throw new Error("recordVerified requires a recorded task");
+  if (validation.markerVerified && task.threadId === null) throw new Error("markerVerified requires a durable threadId");
+  if (validation.outputVerified && task.threadId === null) throw new Error("outputVerified requires a durable threadId");
+
+  value.observations = normalizeObservations(
+    value.observations,
+    startedMs,
+    completedMs,
+    stagesByName.get("prepare-and-list-projects"),
+    stagesByName.get("create-thread"),
+    stagesByName.get("record-task"),
+    stagesByName.get("resolve-provisional"),
+    task.resolutionAttempts,
+  );
+  if (value.observations === undefined) delete value.observations;
+  const snapshots = value.observations?.resolutionSnapshots ?? [];
+  if (
+    snapshots.length > 0 && snapshots.length !== task.resolutionAttempts &&
+    !(resolutionOutcome === "failed" && snapshots.length === task.resolutionAttempts - 1)
+  ) {
+    throw new Error("resolutionSnapshots must account for every fallback attempt");
+  }
+  if (
+    task.resolutionAttempts === 2 && snapshots.length !== 2 &&
+    !(resolutionOutcome === "failed" && snapshots.length === 1)
+  ) {
+    throw new Error("two resolution attempts require two fallback snapshots");
+  }
+  if (task.resolution === "native" && (task.resolutionAttempts !== 1 || snapshots.length !== 0)) {
+    throw new Error("native resolution requires exactly one non-snapshot attempt");
+  }
+  if (task.resolution === "discovered") {
+    if (
+      snapshots.length === 0 || snapshots.at(-1).exactMatchCount !== 1 ||
+      snapshots.at(-1).resolveWriteOutcome !== "succeeded"
+    ) {
+      throw new Error("discovered resolution requires one successfully persisted final snapshot match");
+    }
+  }
+  if (snapshots.some(
+    (snapshot) => snapshot.attempt < task.resolutionAttempts && snapshot.exactMatchCount > 0,
+  )) {
+    throw new Error("any nonzero snapshot match count must terminate fallback resolution");
+  }
+  if (
+    task.resolution === "unresolved" && snapshots.some(
+      (snapshot) => snapshot.resolveWriteOutcome === "succeeded",
+    )
+  ) {
+    throw new Error("unresolved resolution cannot have a successful resolve write");
+  }
+  if (
+    snapshots.some((snapshot) => snapshot.resolveWriteOutcome === "failed") &&
+    resolutionOutcome !== "failed"
+  ) {
+    throw new Error("a failed resolve write requires a failed resolution stage");
+  }
+  if (
+    resolutionStagePresent && snapshots.length === 0 &&
+    !["native", "unresolved"].includes(task.resolution)
+  ) {
+    throw new Error("non-snapshot resolution must be native or unresolved");
+  }
+  if (snapshots.length === 1 && snapshots[0].exactMatchCount === 0 && task.resolutionAttempts !== 2) {
+    throw new Error("a completed first snapshot with zero matches requires the second fallback attempt");
+  }
+  const filterEffective = snapshots.length > 0 && snapshots.every(
+    (snapshot) => snapshot.candidateCount < snapshot.recentTaskCount,
+  );
+  if (validation.candidateFilterEffective !== filterEffective) {
+    throw new Error("candidateFilterEffective must match resolution snapshot counts");
+  }
+
+  const measuredStageMs = value.stages.reduce((total, stage) => total + stage.durationMs, 0);
+  const totalWallMs = completedMs - startedMs;
+  const summary = {
+    totalWallMs,
+    measuredStageMs,
+    orchestrationOverheadMs: totalWallMs - measuredStageMs,
+    resolved: task.threadId !== null,
+    resolutionAttempts: task.resolutionAttempts,
+  };
+  if (requireDerived && value.summary === undefined) {
+    throw new Error("summary is required in a saved result");
+  }
+  if (value.summary !== undefined) {
+    const suppliedSummary = requireObject(value.summary, "summary");
+    requireExactKeys(suppliedSummary, Object.keys(summary), "summary");
+    if (Object.entries(summary).some(([name, expected]) => suppliedSummary[name] !== expected)) {
+      throw new Error("summary does not match the derived benchmark summary");
+    }
+  }
+  value.summary = summary;
+  return value;
+}
+
+function timestampFilename(iso) {
+  return iso.replaceAll(":", "-");
+}
+
+export async function writeBenchmarkResult(input, outputDirectory) {
+  const packageJson = JSON.parse(await readFile(new URL("../package.json", import.meta.url), "utf8"));
+  const result = normalizeBenchmarkResult({ ...input, taskchefVersion: packageJson.version });
+  await mkdir(outputDirectory, { recursive: true });
+  const filename = `${timestampFilename(result.startedAt)}-${BENCHMARK_NAME}.json`;
+  const outputPath = path.join(outputDirectory, filename);
+  await writeFile(outputPath, `${JSON.stringify(result, null, 2)}\n`, { flag: "wx" });
+  return { outputPath, result };
+}
+
+export async function cleanBenchmarkResults(outputDirectory) {
+  const entries = await readdir(outputDirectory, { withFileTypes: true }).catch((error) => {
+    if (error.code === "ENOENT") return [];
+    throw error;
+  });
+  const removed = [];
+  for (const entry of entries) {
+    if (!entry.isFile() || !managedResultFilename(entry.name)) continue;
+    await unlink(path.join(outputDirectory, entry.name));
+    removed.push(entry.name);
+  }
+  return removed.sort();
+}
+
+async function readJsonStdin() {
+  if (process.stdin.isTTY) throw new Error("write requires non-interactive JSON on stdin");
+  let input = "";
+  process.stdin.setEncoding("utf8");
+  for await (const chunk of process.stdin) input += chunk;
+  if (input.trim().length === 0) throw new Error("expected benchmark JSON on stdin");
+  return JSON.parse(input);
+}
+
+async function main(args) {
+  const command = args[0];
+  const target = path.resolve(args[1] ?? "reports/e2e-benchmarks");
+  if (command === "write") {
+    const { outputPath, result } = await writeBenchmarkResult(await readJsonStdin(), target);
+    process.stdout.write(`${JSON.stringify({ outputPath, summary: result.summary })}\n`);
+    return;
+  }
+  if (command === "validate") {
+    const result = normalizeBenchmarkResult(JSON.parse(await readFile(target, "utf8")), { requireDerived: true });
+    process.stdout.write(`${JSON.stringify({ inputPath: target, summary: result.summary })}\n`);
+    return;
+  }
+  if (command === "clean") {
+    process.stdout.write(`${JSON.stringify({ outputDirectory: target, removed: await cleanBenchmarkResults(target) })}\n`);
+    return;
+  }
+  throw new Error("usage: e2e-benchmark.js <write|validate|clean> [path]");
+}
+
+if (process.argv[1] && path.resolve(process.argv[1]) === fileURLToPath(import.meta.url)) {
+  main(process.argv.slice(2)).catch((error) => {
+    process.stderr.write(`${error.message}\n`);
+    process.exitCode = 1;
+  });
+}

package/skills/taskchef-delegate/SKILL.md

@@ -139,3 +139,28 @@ delegated input contains an unresolved task's exact marker, run
 `<plugin-root>/bin/taskchef.js task resolve <task-id> --thread-id <thread-id> --json`.
 Never edit `tasks.jsonl` directly. The CLI permits only an idempotent one-way
 transition from `threadId: null` to one unique durable thread ID.
+
+## End-to-end evaluation
+
+When explicitly asked to benchmark delegation, measure one real task without
+waiting for executor completion. Start from
+`<plugin-root>/assets/e2e-benchmark-example.json`. Capture one ISO start/end
+interval for the parallel preparation/project-list operation, followed by
+sequential non-overlapping creation, recording, and optional provisional
+resolution stages. Follow the complete schema and workflow transitions in
+`<plugin-root>/SPEC.md`; the example is the durable-success starting shape.
+Omit later stages when an earlier operation stops the workflow.
+Fallback snapshot observations additionally require `recentTaskCount`,
+`candidateCount`, `exactMatchCount`, and `resolveWriteMs`. For each snapshot,
+also record `resolveWriteOutcome` as `not-attempted`, `succeeded`, or `failed`;
+a unique match whose atomic write fails remains unresolved. After the bounded
+workflow ends, verify the canonical task record once and, when resolved, read
+the task once to verify the requested output. A failed verification remains a
+false validation flag even when the corresponding operation succeeded. Feed
+one exact JSON value to
+`node <plugin-root>/scripts/e2e-benchmark.js write <output-directory>` on closed,
+non-interactive stdin. Keep timestamped results in the TaskChef source
+repository's ignored `reports/e2e-benchmarks/` directory. Never include hidden
+reasoning or transcripts. Use the script's `clean` command before establishing
+a replacement baseline. Mark candidate filtering effective only when the
+fallback snapshot narrows reads below the complete recent-task window.

package/src/cli.js

@@ -154,6 +154,12 @@ function sortTasksByCreatedAt(tasks, ascending) {
     .map(({ task }) => task);
 }
 
+function displayId(value, fullId) {
+  if (fullId || value === null || value === undefined) return value;
+  const uuidSection = String(value).match(/^[0-9a-fA-F]{8}(?=-)/);
+  return uuidSection ? uuidSection[0] : value;
+}
+
 async function initialize(args) {
   validateCommandArgs(args, 2, {
     values: ["--workspace", "--codex-cli"],
@@ -315,20 +321,22 @@ async function taskShow(args) {
 async function taskList(args) {
   validateCommandArgs(args, 2, {
     values: ["--workspace", "--project"],
-    switches: ["--ascending", "--json"],
+    switches: ["--ascending", "--full-id", "--json"],
   });
   const filtered = await filterTasks(workspaceRoot(args), {
     project: option(args, "--project", null),
   });
   const dispatches = sortTasksByCreatedAt(filtered, args.includes("--ascending"));
   const result = { taskCount: dispatches.length, tasks: dispatches };
+  const fullId = args.includes("--full-id");
   print(result, args, (value) => table(
-    ["TITLE", "PROJECT", "CREATED", "ID"],
+    ["TITLE", "PROJECT", "CREATED", "ID", "THREAD ID"],
     value.tasks.map((dispatch) => [
       dispatch.title,
       dispatch.project?.name,
       dispatch.createdAt,
-      dispatch.id,
+      displayId(dispatch.id, fullId),
+      displayId(dispatch.threadId, fullId),
     ]),
   ));
   return 0;
@@ -360,7 +368,7 @@ Usage:
   taskchef task record [--json] [--workspace <path>]
   taskchef task resolve <task-id> --thread-id <thread-id> [--json] [--workspace <path>]
   taskchef task show <task-id> [--json] [--workspace <path>]
-  taskchef task list [--project <name-or-path>] [--ascending] [--json] [--workspace <path>]
+  taskchef task list [--project <name-or-path>] [--ascending] [--full-id] [--json] [--workspace <path>]
   taskchef task summary [--json] [--workspace <path>]
 
 Task record reads one JSON value from closed, non-interactive standard input.