taskchef 5.2.0 → 5.4.0

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "taskchef",
-  "version": "5.2.0",
+  "version": "5.4.0",
   "description": "Dispatch work from a data-only workspace to visible Codex project tasks.",
   "author": {
     "name": "Favo Yang",

package/README.md

@@ -356,17 +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

@@ -179,9 +179,11 @@ cases.
 For each assignment, `$taskchef-delegate`:
 
 1. runs `dispatch prepare` and native Codex project discovery concurrently;
-   the preparation command resolves the canonical workspace, loads and
-   validates configured projects, and generates the full UUID, preparation
-   timestamp, and exact marker in one process
+   only when neither a native provisional-ID resolver nor programmatic tool
+   orchestration is available, it also takes one recent-thread baseline
+   snapshot in that parallel group. The preparation command resolves the
+   canonical workspace, loads and validates configured projects, and generates
+   the full UUID, preparation timestamp, and exact marker in one process
 2. selects one unambiguous configured target and matches its exact path against
    the already-loaded native projects
 3. prefixes the instruction with the prepared exact
@@ -195,22 +197,27 @@ For each assignment, `$taskchef-delegate`:
 6. when creation returns only a provisional client ID, immediately appends the
    marked entry with `threadId: null`, then prefers one native client-ID wait or
    resolution call with a 30-second timeout when Codex exposes one
-7. when no native operation is available, takes at most two recent-thread
+7. when no native operation is available, excludes durable Codex IDs from the
+   successful pre-creation baseline, then takes at most two recent-thread
    snapshots on a nominal 10- and 30-second schedule after the provisional
    result; a late first checkpoint runs immediately, and the second starts at
    least 20 seconds after the first actually started. It filters candidates by
    available host/project/time/worktree metadata, uses title only as an advisory
-   ordering hint, and accepts only one thread whose structured delegated input
-   starts with the exact marker
+   ordering hint, batches independent reads programmatically when supported,
+   and accepts only one thread whose structured delegated input starts with the
+   exact marker
 8. atomically fills the nullable thread ID after an exact match
 9. returns after recording or after reporting that bounded resolution was
    unresolved, without waiting for executor work completion.
 
-The exact random marker makes a pre-creation thread snapshot unnecessary.
-Creation-time filtering allows five seconds of clock skew. Candidate reads run
-concurrently where the host permits and inspect only structured
-`codexDelegation.input`, never untrusted title, summary, preview, or plain-text
-marker echoes. A native resolver result is verified against the same structured
+The exact random marker remains the sole correlation proof. A successful
+pre-creation snapshot is only a candidate-elimination baseline; its failure
+does not block creation or weaken the marker check. Creation-time filtering
+allows five seconds of clock skew. Candidate reads run concurrently where the
+host permits, use one programmatic batch when available, and inspect only
+structured `codexDelegation.input`, never untrusted title, summary, preview, or
+plain-text marker echoes. A native resolver result is verified against the same
+structured
 marker before persistence. Zero exact matches remain unresolved; multiple exact
 matches are ambiguous. Snapshot, candidate-read, native-resolution, or
 task-resolution errors leave the already-recorded nullable entry intact. The
@@ -290,7 +297,10 @@ 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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "taskchef",
-  "version": "5.2.0",
+  "version": "5.4.0",
   "description": "A non-blocking interactive dispatcher for visible Codex tasks.",
   "license": "MIT",
   "author": "Favo Yang",

package/skills/taskchef-delegate/SKILL.md

@@ -27,15 +27,21 @@ for all deterministic workspace and task-record operations.
 
 ## Dispatch
 
-1. In parallel, run `<plugin-root>/bin/taskchef.js dispatch prepare --json`
-   and list the native Codex projects once. The prepare command resolves the
+1. In parallel, run `<plugin-root>/bin/taskchef.js dispatch prepare --json`,
+   list the native Codex projects once, and, only when neither a dedicated
+   provisional-ID resolver nor programmatic tool orchestration is available,
+   take one pre-creation `list_threads` snapshot with limit 50. Do not add this
+   snapshot when candidate reads can be issued in one programmatic batch. The
+   prepare command resolves the
    canonical workspace, loads and validates the configured routing targets,
    generates the lowercase full UUID task ID, and returns `preparedAt` plus the
    exact first-line marker. Use
    `$taskchef-bootstrap` if the workspace is missing or unhealthy.
    The CLI resolves `--workspace`, then `TASKCHEF_WORKSPACE`, then
    `~/.agents/taskchef`; do not substitute the current project. Reject the
-   dispatcher workspace itself as a target.
+   dispatcher workspace itself as a target. From the pre-creation snapshot,
+   retain only durable Codex thread IDs as a candidate-elimination baseline.
+   Snapshot failure must not block creation; continue without a baseline.
 2. Split the request into the smallest independently useful outcomes. Include
    constraints, expected testing, and reporting in every instruction.
 3. Classify against configured `name`, every URL in the `githubRepos` list, and
@@ -54,9 +60,9 @@ for all deterministic workspace and task-record operations.
    Prefix the complete executor instruction with
    exactly `<!-- taskchef_id=<full UUID> -->` as the first line, followed by a
    blank line and the instruction body. Preserve this
-   marked instruction for recording, and note the creation time.
-   Do not take a pre-creation thread snapshot; the exact random marker is the
-   correlation key.
+   marked instruction for recording, and note the creation time. The exact
+   random marker remains the sole correlation proof; the pre-creation IDs only
+   eliminate threads that already existed.
 6. Create one real Codex task using the exact configured project, a local
    environment on its executor host, the marked instruction, and a short title.
 7. When `create_thread` returns a durable `threadId`, immediately run
@@ -81,8 +87,10 @@ for all deterministic workspace and task-record operations.
      accepts the provisional ID and waits for or resolves its durable thread
      ID, call it exactly once with a timeout of at most 30 seconds. Do not invent
      an operation or pass the provisional ID to tools that require `threadId`.
-   - When no native operation is available, take at most two `list_threads`
-     snapshots with limit 50. The nominal schedule is 10 and 30 seconds after
+   - When no native operation is available, take at most two post-creation
+     `list_threads` snapshots with limit 50. Exclude every durable Codex ID from
+     the successful pre-creation baseline before reading candidates. The
+     nominal schedule is 10 and 30 seconds after
      the provisional result. Treat the first checkpoint as due, not expired: if
      nullable recording or other required work finishes after 10 seconds, take
      the first snapshot immediately. Start the second snapshot no sooner than
@@ -96,7 +104,9 @@ for all deterministic workspace and task-record operations.
      may normalize it, so never exclude a candidate because its title differs.
    - Read every remaining candidate with `read_thread`, requesting one turn and
      no command output. Read candidates concurrently when the tool surface
-     permits. Inspect only the structured
+     permits; when programmatic tool orchestration is available, issue the
+     independent reads together in one programmatic batch. Inspect only the
+     structured
      `userMessage.content[].codexDelegation.input`; do not trust titles,
      summaries, previews, plain-text echoes, or assistant output as proof.
    - Accept a candidate only when the structured input's first line is exactly

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.

package/src/delegation.js

@@ -250,6 +250,7 @@ export async function createAndRecordDelegation({
   recordTask,
   resolveRecordedTask = null,
   resolveProvisionalThread = null,
+  baselineThreadIds = new Set(),
   taskId = randomUUID(),
   checkpointsMs = THREAD_RESOLUTION_CHECKPOINTS_MS,
   timeoutMs = THREAD_RESOLUTION_TIMEOUT_MS,
@@ -274,6 +275,9 @@ export async function createAndRecordDelegation({
   if (resolveRecordedTask !== null && typeof resolveRecordedTask !== "function") {
     throw new Error("resolveRecordedTask must be a function or null");
   }
+  if (!(baselineThreadIds instanceof Set)) {
+    throw new Error("baselineThreadIds must be a Set");
+  }
   validateResolutionSchedule(checkpointsMs, timeoutMs);
 
   const prepared = prepareDelegation(instruction, { taskId });
@@ -507,6 +511,7 @@ export async function createAndRecordDelegation({
     try {
       const snapshot = await listThreads({ limit: recentLimit });
       candidates = filterThreadCandidates(snapshot, {
+        baselineThreadIds,
         excludedThreadIds: provisionalIds,
         hostId: expected.hostId ?? null,
         projectId: expected.projectId ?? target.projectId ?? null,