Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .claude-plugin/marketplace.json
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
"name": "t3-pstack",
"source": "./plugins/pstack",
"description": "pstack for T3 Code: rigorous agent workflows whose panels and fan-outs run across model families through T3. Original pstack by Lauren Tan (poteto).",
"version": "2.2.6"
"version": "2.2.7"
}
]
}
13 changes: 13 additions & 0 deletions CHANGES.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,19 @@

This file is the release changelog, with one `## <version> - <title>` entry per release, newest first. The Cursor-to-T3 rewrite rules live in [`tools/substitutions.json`](tools/substitutions.json), and the [sync boundary](CONTRIBUTING.md#the-sync-boundary) in `CONTRIBUTING.md` defines how a change to upstream's skill content is declared.

## 2.2.7 - An Autopilot-full owner's brief says it is not a leaf, so the owner starts its own reviewers

2.2.6 made each Autopilot-full PR owner a `delegate_task` child, and it made every `delegate_task` child a leaf, which does the work itself and starts no subagent unless its brief names one. Step 2 said only that the owner's brief "lets the owner delegate as the playbooks say", which names no subagent. In a run of 2.2.6 on this Mac's T3, the root read the leaf rule and wrote "You are a leaf. Do all the work yourself and start no subagents." into the owner's brief. The owner then ran `/no-comments` in its own thread where that skill starts Comment Sicko, and skipped show-me-your-work's cross-model review of its trail. Both times its reason was that it starts no subagents.

Step 2 now says that the owner's brief tells it that it is not a leaf and starts the subagents its playbooks name, such as `/no-comments`'s Comment Sicko and show-me-your-work's cross-model review of the trail, because Dispatch on T3 makes a child a leaf unless its brief names its subagents. Autopilot-stack runs Autopilot-full's step 2, so it gets the same brief. Orchestrate starts two kinds of child that start children of their own. An owner's kickoff now says what Autopilot-full's owner brief says, and a sub-coordinator's kickoff says that it is not a leaf and starts its area's workers with `delegate_task`. All three are substitutions in `tools/substitutions.json`. The leaf rule in Dispatch on T3 and in the session-start routing text does not change, and neither hooks file changes.

These runs used T3 0.1.8-nightly.20261106 on macOS. Each root thread ran on `claudeAgent/claude-opus-5-5` at `effort=xhigh` and read poteto-mode and its playbooks from this release's tree in place of the installed 2.2.6. The repositories and threads are deleted since.

- The Autopilot-full run repeated 2.2.6's, with a queue of one in a throwaway repository whose origin is a local bare repository with no forge and whose trunk had moved one commit past the local `main`. The operator allowed step 2 only. The root's owner brief said "You are not a leaf. Start the subagents your playbooks name, such as the /no-comments Comment Sicko and the show-me-your-work cross-model review of your trail." The owner built the change and pushed its branch. It then called `delegate_task` for Comment Sicko on `claudeAgent/claude-opus-5-5` and for the trail review on `codex/gpt-6-astra`, a different family from its own, and its report carried the reviewer's Attention section. Each of those two briefs said "You are a leaf: start no subagent", and neither started a child.
- The leaf check repeated 2.2.6's. A root gave one `delegate_task` child on the `how explorer` entry a brief to investigate thoroughly why `slugify` produces bad slugs and to find every class of failure. The child read the `how` skill, which fans out explorers, ran six shell commands, and started no subagent.

This release syncs nothing from Lauren's pstack, so all three components stay pinned at cursor/plugins `c742dd6`. At that pin each component's dry run reports no undeclared fork and no substitution that matches nothing. This is a patch release, and no setting or workflow has to change. On Codex, run `npx -y github:chhoumann/t3-pstack update` after it, as after every release.

## 2.2.6 - Writing delegates get T3's worktree isolation, PR owners are child tasks, and a child is a leaf

**A writing child gets T3's worktree isolation ([#50](https://github.com/chhoumann/t3-pstack/issues/50)).** poteto-mode's Dispatch on T3 told the parent to make each writing child's worktree itself, with `git worktree add` from `HEAD`, and to remove it and its branch after the result. No T3 thread is bound to such a worktree. As #50 reports, T3's cleanup therefore never reaches it, and a run that stops early leaves it behind. The child's commits also stayed on a branch no thread owned, so the PR came from that branch while the thread's own branch stayed empty. A writer now gets `delegate_task`'s `isolation: "worktree"`, and T3 makes its worktree and branch from the thread checkout's `HEAD` commit. One writer may instead stay in the parent's checkout while the parent writes nothing. The brief asks the child to end its reply with its branch and commit, because T3 can rename that branch during the run and `task_status` does not report it. The parent then brings the commits onto its own branch with `git merge`, and a PR opens only from a T3 thread's branch. `delegate_task` refuses the worktree with `Unable to resolve the parent checkout commit` when the thread's project is not a git checkout or has no commit yet. So the rule says to commit first in a repo with no commit. It keeps `git worktree add` for a thread whose project is not a git checkout, for work that lives in a checkout other than the thread's own, and for a child whose worktree gets uncommitted changes copied in, as interrogate's adversaries do, because isolation leaves those changes out. Isolation always starts at the parent's `HEAD`. So a child that must start from another commit, such as a PR head or fresh trunk, gets its own worktree even when it only reads, and its first step is `git fetch` and `git reset --hard` of its own branch to that commit. That covers a Shipping verifier, which also names the commit in its verdict, an Autopilot-full owner, and a swarm worker on another branch, and none of them moves the parent's checkout. A child sent into a worktree it does not own, such as a finished Orchestrate worker's, runs shared with that path as the only place it writes and runs its commands. A child ends its reply with its path, branch, and commit, which is how an arena candidate in an isolated worktree reports its output location, since the parent cannot name it at spawn. swarm, arena, Orchestrate, Shipping, Feature step 4, and Opening a PR point at the same rule.
Expand Down
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -14,9 +14,9 @@ npx -y github:chhoumann/t3-pstack update
npx -y github:chhoumann/t3-pstack doctor
```

`npx -y github:chhoumann/t3-pstack` runs the installer from the latest commit on `main`. Each Claude Code home's marketplace auto-updates from `main` too, and each Codex home's marketplace stays on the release tag the installer pinned. To run one release's installer, name its tag, as in `npx -y github:chhoumann/t3-pstack#v2.2.6 doctor`.
`npx -y github:chhoumann/t3-pstack` runs the installer from the latest commit on `main`. Each Claude Code home's marketplace auto-updates from `main` too, and each Codex home's marketplace stays on the release tag the installer pinned. To run one release's installer, name its tag, as in `npx -y github:chhoumann/t3-pstack#v2.2.7 doctor`.

`install` and `update` are the same command, and a second run changes nothing. With Node 20 or later, it installs or updates the `t3-pstack@t3-pstack` plugin in every Claude Code and Codex config home T3 can run: `~/.claude` and `~/.codex`, `$CLAUDE_CONFIG_DIR` and `$CODEX_HOME`, and the home of each `claudeAgent` and `codex` instance in T3's settings, disabled ones included. Name any other home with `--claude-home <dir>` or `--codex-home <dir>`. Each home's `t3-pstack` marketplace must come from `chhoumann/t3-pstack`, or from `--source <owner/repo|git URL|dir>` on the same run, and a home whose marketplace has another source is left as it is. A run never switches a home's source, so a home already on `chhoumann/t3-pstack` stays on it under another `--source`, and `doctor` warns and prints the commands that move it. A local directory needs a path such as `./t3-pstack`, since `owner/repo` always means GitHub. On Codex it also trusts t3-pstack's session-start hook, once its hooks file is the one this release pins. Codex runs a plugin's hook only once it is trusted, and T3's Codex sessions never ask, so without this step the hook never runs. Codex 0.164 and later tie that trust to every file in the installed plugin, so each release turns the hook off until the installer trusts it again. So the installer pins each Codex home's `t3-pstack` marketplace to the release's tag, such as `v2.2.6`, and Codex's own auto-upgrade leaves that tag where it is. A release reaches a Codex home only when `update` runs, and that run trusts the hook again. A local directory has no tag, so a marketplace from one stays unpinned. Run `update` after each release.
`install` and `update` are the same command, and a second run changes nothing. With Node 20 or later, it installs or updates the `t3-pstack@t3-pstack` plugin in every Claude Code and Codex config home T3 can run: `~/.claude` and `~/.codex`, `$CLAUDE_CONFIG_DIR` and `$CODEX_HOME`, and the home of each `claudeAgent` and `codex` instance in T3's settings, disabled ones included. Name any other home with `--claude-home <dir>` or `--codex-home <dir>`. Each home's `t3-pstack` marketplace must come from `chhoumann/t3-pstack`, or from `--source <owner/repo|git URL|dir>` on the same run, and a home whose marketplace has another source is left as it is. A run never switches a home's source, so a home already on `chhoumann/t3-pstack` stays on it under another `--source`, and `doctor` warns and prints the commands that move it. A local directory needs a path such as `./t3-pstack`, since `owner/repo` always means GitHub. On Codex it also trusts t3-pstack's session-start hook, once its hooks file is the one this release pins. Codex runs a plugin's hook only once it is trusted, and T3's Codex sessions never ask, so without this step the hook never runs. Codex 0.164 and later tie that trust to every file in the installed plugin, so each release turns the hook off until the installer trusts it again. So the installer pins each Codex home's `t3-pstack` marketplace to the release's tag, such as `v2.2.7`, and Codex's own auto-upgrade leaves that tag where it is. A release reaches a Codex home only when `update` runs, and that run trusts the hook again. A local directory has no tag, so a marketplace from one stays unpinned. Run `update` after each release.

`doctor` reports on the same homes and changes nothing itself: each marketplace's source, each Codex marketplace's pin, the installed version, whether its files are all there, whether it is enabled, the Codex hook's trust, Claude Code records that pin an old version, plain copies of the plugin's skills, and the model sheet. It exits 1 on any problem and prints a fix for each.

Expand Down
2 changes: 1 addition & 1 deletion VERSION
Original file line number Diff line number Diff line change
@@ -1 +1 @@
2.2.6
2.2.7
2 changes: 1 addition & 1 deletion package.json
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"name": "t3-pstack",
"private": true,
"version": "2.2.6",
"version": "2.2.7",
"description": "The installer and development tooling for t3-pstack, Lauren Tan's pstack rewritten in place for T3 Code. The plugin itself lives in plugins/pstack.",
"author": {
"name": "Christian Bager Bach Houmann",
Expand Down
2 changes: 1 addition & 1 deletion plugins/pstack/.claude-plugin/plugin.json
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"name": "t3-pstack",
"displayName": "t3-pstack (pstack for T3 Code)",
"version": "2.2.6",
"version": "2.2.7",
"description": "pstack for T3 Code: Lauren Tan's pstack with its Cursor mechanics rewritten in place for T3, so subagents, panels, schedules, and PR watches dispatch through T3's orchestration and panels mix Claude, GPT, and Grok.",
"author": {
"name": "Christian Bager Bach Houmann",
Expand Down
2 changes: 1 addition & 1 deletion plugins/pstack/.codex-plugin/plugin.json
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
{
"name": "t3-pstack",
"version": "2.2.6",
"version": "2.2.7",
"description": "pstack for T3 Code on a Codex host: Lauren Tan's pstack with its Cursor mechanics rewritten in place for T3, so subagents, panels, schedules, and PR watches dispatch through T3's orchestration.",
"author": {
"name": "Christian Bager Bach Houmann",
Expand Down
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
### Autopilot-full

**You own the verdicts, never the PRs. One owner carries each PR from build to merge, and nothing merges until your swarm, which never wrote the code, has proven the code that lands.**
Expand All @@ -5,7 +5,7 @@
A verdict covers one patch and green CI covers one head. Step 4 runs a full swarm once, and again only for a major change. The patch-id rule in `playbooks/shipping.md` can carry a lane's result, and every new head needs its own green CI.

1. **The operator's gates come first.** The grant covers only the queue's items, so items the operator names as theirs and PRs outside the queue stop at merge-ready. A request to state the plan is not a go.
2. **Spawn one owner per PR, and keep its work where a replacement can find it.** Resolve the forge once for the program. GitHub CLI (`gh`) is the default. If `command -v origin` succeeds and Origin can resolve the repository, use `origin pr` for every PR operation. Otherwise stay on `gh` and record the fallback. Never require Graphite (`gt`). Each owner is a `delegate_task` child with `mode: "async"` and `isolation: "worktree"` that starts from fresh trunk, per poteto-mode's Dispatch on T3. Its brief names this playbook and this thread's ID, so the owner reports back with `t3_thread_send`, and lets the owner delegate as the playbooks say. T3 gives a child no `watch_pull_request`, so the owner babysits in `drive` mode and reports a wait for a person to this thread, which watches that PR. It builds, opens its PR per `playbooks/opening-a-pr.md`, proves the change on the real artifact, babysits to green per `playbooks/babysit.md`, and merges once steps 4 and 5 clear it.
2. **Spawn one owner per PR, and keep its work where a replacement can find it.** Resolve the forge once for the program. GitHub CLI (`gh`) is the default. If `command -v origin` succeeds and Origin can resolve the repository, use `origin pr` for every PR operation. Otherwise stay on `gh` and record the fallback. Never require Graphite (`gt`). Each owner is a `delegate_task` child with `mode: "async"` and `isolation: "worktree"` that starts from fresh trunk, per poteto-mode's Dispatch on T3. Its brief names this playbook and this thread's ID, so the owner reports back with `t3_thread_send`. It also tells the owner that it is not a leaf and starts the subagents its playbooks name, such as `/no-comments`'s Comment Sicko and show-me-your-work's cross-model review of the trail, because Dispatch on T3 makes a child a leaf unless its brief names its subagents. T3 gives a child no `watch_pull_request`, so the owner babysits in `drive` mode and reports a wait for a person to this thread, which watches that PR. It builds, opens its PR per `playbooks/opening-a-pr.md`, proves the change on the real artifact, babysits to green per `playbooks/babysit.md`, and merges once steps 4 and 5 clear it.

Open the PR early so CI and bots run alongside the work. The code is ready only after the slop-strip (the **deslop** skill, `/deslop`) and the `/no-comments` pass, so the full swarm runs on finished code. Then rebase onto current trunk and report the code-ready head before self-proof, so verification runs on the base the patch lands on. Report every later head, and merge-ready once self-proof, CI, and babysit are done. Fix rounds stay on that base unless trunk conflicts, breaks CI, or lands a known concurrent change to the same files, because each rebase restarts CI. Run the repo's checks for the touched paths on the committed head before the code-ready push and before a later push that needs a verifier.

Expand Down
4 changes: 2 additions & 2 deletions plugins/pstack/skills/poteto-mode/playbooks/orchestrate.md
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
### Orchestrate

**You run the program, never the code. Decide which agent does each piece of work, then check what each one produces.** For a standing project handed to one coordinator chat: multi-day, many stacked PRs, dozens to hundreds of subagents, few human turns. One task driven to a predicate is Autonomous run. One ambitious run that needs a bespoke workflow is figure-it-out. Work that one agent could finish inside the session's budget is not a program.
Expand All @@ -6,9 +6,9 @@

#### Topology

- **One owner per PR.** The owner is the only writer of its branch and carries the PR from build to merge. Only the owner pushes, rebases, or retargets it. Closing or retargeting a base PR orphans every PR above it, so the owner does that only on your call. You never author or edit code. Conflicted merges, chain rebases, and fixes go to owners.
- **One owner per PR.** The owner is the only writer of its branch and carries the PR from build to merge. Only the owner pushes, rebases, or retargets it. Closing or retargeting a base PR orphans every PR above it, so the owner does that only on your call. You never author or edit code. Conflicted merges, chain rebases, and fixes go to owners. An owner's kickoff tells it that it is not a leaf and starts the subagents its playbooks name, such as `/no-comments`'s Comment Sicko, because Dispatch on T3 makes a child a leaf unless its brief names its subagents.
- **A fresh worker for each independent task.** Its kickoff carries everything it needs, including each upstream report it depends on, pasted in full. Workers can't see their siblings. Every worker runs on this machine, and one that writes gets `isolation: "worktree"`, per poteto-mode's Dispatch on T3. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section.
- **A sub-coordinator only when one area has many parallel workers.** It owns that area's workers and kickoffs and sends you one rollup, never raw worker reports. Stop at three levels: you, sub-coordinators, and workers. Keep about ten workers in flight per coordinator, and start the next one as each finishes instead of waiting on a whole batch.
- **A sub-coordinator only when one area has many parallel workers.** It owns that area's workers and kickoffs and sends you one rollup, never raw worker reports. Its kickoff tells it that it is not a leaf and starts that area's workers with `delegate_task`, because Dispatch on T3 makes a child a leaf unless its brief names its subagents. Stop at three levels: you, sub-coordinators, and workers. Keep about ten workers in flight per coordinator, and start the next one as each finishes instead of waiting on a whole batch.
- **Reuse a worker's worktree when new work needs its built state,** such as its checkout, uncommitted changes, or a running process. Once that worker is done, start a fresh one there instead of removing the worktree, as poteto-mode's Dispatch on T3 says for a child sent into a worktree it does not own. Message a worker, with `t3_thread_send` to its `childThreadId`, only for a follow-up on the same work. Never message one to check on it, because a message restarts an idle agent.
- **Each PR gets a verifier that isn't its author,** on a different model family. The owner merges only on that verifier's pass at the current head.
- **Start with one unit.** Take it through kickoff, owner, verifier, and merge before you fan out, so a flaw in the kickoff costs one agent instead of fifty. On near-identical cheap units, the first unit is that test.
Expand Down
Loading
Loading