pi-subagentura

Docs ownership: this repository is the source of truth for docs/. pi-docs is the separately published doc injector that can index these files; it does not manage or sync them.

Give the parent Pi agent one task and let it build the team. pi-subagentura adds reusable multi-agent workflows, lightweight background delegation, and real child Pi sessions you can watch, attach to, and continue in tmux, Zellij, or Herdr.

For routing-first delegation, start Pi with --orchestratorv2. The prompt guides the parent to route clear work to attachable interactive subagents, ask for clarification when a request is ambiguous or a narrow request has no matching child, and leave specialist repository work to those children. Compatibility workflow and in-process tools remain registered.

For reusable workflows, start Pi with the bundled orchestration guidance and describe the outcome you want. The parent can turn that request into a saved workflow, run its agents in the background, and keep their intermediate results out of the parent context.

Installation

See CHANGELOG.md for breaking changes between major versions.

Node.js 22.23.2 or newer is required.

Install globally:

pi install npm:pi-subagentura

Install for just the current project:

pi install -l npm:pi-subagentura

Try it for a single run without installing:

pi -e npm:pi-subagentura

You can also install directly from GitHub:

pi install git:github.com/lmn451/pi-subagentura

Quick start

For routing-first interactive delegation:

pi --orchestratorv2
Review the authentication layer across the API and database boundaries.

The parent routes work to attachable interactive subagents and asks for clarification when a request is ambiguous or a narrow request has no matching child. For reusable workflows, use the workflow-oriented --orchestrator mode:

pi --orchestrator
/workflow review the authentication layer
/workflows
/workflow-tree

/workflow asks the parent to create, save, and immediately run a reusable workflow. /workflows runs saved workflows, and /workflow-tree shows live phases, agents, and cancellation controls.

Reusable workflows

Workflow files are ordinary .mjs scripts with static metadata and a small set of injected orchestration primitives:

• agent() runs an isolated role with optional schema validation, persona, model, thinking level, phase label, and process/in-process isolation.
• parallel() starts independent agent thunks concurrently and waits at a barrier before continuing.
• pipeline() streams each item through a sequence of stages without waiting for every item to finish a stage first.
• phase() names progress in the TUI. Saved workflows may call another saved workflow with workflow(name, args), with one level of nesting.

Execution is async by default: the tool returns a workflow id while Pi remains usable, with status and results available through the UI, slash commands, and agent tools. Workflow agents default to separate Pi processes in tmux, Zellij, or Herdr, so they are observable and attachable; when no multiplexer is available, the runtime falls back to in-process execution. Intermediate agent results stay in workflow variables outside the parent model context. Only the workflow completion enters coordinated parent delivery; the retained final result is available through get_workflow_result.

An omitted workflow budget defaults to the finite 100_000_000_000 completed output tokens. This is a high safety ceiling with significant cost/runtime risk, not a spending recommendation; use a lower explicit budget when practical. Existing agent/item caps, concurrency, timeouts, cancellation, and errors still apply.

Workflow scripts are trusted agent-authored JavaScript. The VM improves determinism but is not a security boundary, so never run untrusted JavaScript. Background workflow jobs are scoped to the current parent session and are cancelled by reload, resume, quit, or a new session. Attachable interactive sub-agents use durable artifacts and can survive those boundaries.

See the workflow guide and bundled examples.

Why use it?

• Route work to attachable interactive specialists with --orchestratorv2
• Resume interactive artifacts, routing state, pending deliveries, and receipts within the matching parent session; delivery is bounded and at-least-once, while in-process jobs and background workflows remain session-scoped
• Watch a real child Pi session and its tool activity live in tmux, Zellij, or Herdr
• Supervise a bounded recursive tree of interactive children and grandchildren
• Focus or capture a descendant pane locally, or attach from another terminal
• Inspect bounded lifecycle, recent-event, and output previews without leaving Pi
• Continue true follow-up turns without losing the child's model context
• Inspect durable per-turn outputs and lifecycle events after detach or restart
• Run lightweight sub-agents in-process or in the background
• Compare context-aware and isolated reasoning
• Poll, collect, or cancel background jobs on demand
• Build reusable review, research, migration, and conversion workflows
• Use bundled orchestration defaults for scout/plan, oracle checks, parallel review, and review loops

User commands

These commands are intended for people at the Pi prompt.

| Command | Purpose | | ------------------- | ----------------------------------------------------------------- | | /workflow | Create, save, and run a reusable workflow from a task | | /workflows | Select and run a saved workflow | | /list-workflows | Alias for /workflows | | /workflow-status | List workflow jobs and their live or terminal status | | /workflow-tree | Open the specialized workflow progress tree | | /subagents | Supervise all async work (Ctrl+Alt+A) | | /delete-workflow | Delete a saved workflow by name or picker | | /cancel-all-flows | Cancel active jobs, workflows, and running interactive sub-agents |

Agent-facing tools

The extension registers these public tools for parent agents.

| Tool | Purpose | | --------------------------------------- | ----------------------------------------------------------------- | | workflow | Run a trusted workflow script or saved workflow | | save_workflow | Validate and save a reusable workflow | | list_workflows | List saved workflows | | delete_workflow | Delete a saved workflow | | get_workflow_status | Inspect a background workflow | | get_workflow_result | Wait for and return a workflow result | | cancel_workflow | Cancel a background workflow | | subagent_with_context | Delegate with the parent conversation | | subagent_isolated | Delegate with a fresh context | | get_subagent_status | Inspect an async in-process job | | get_subagent_result | Retrieve current or final async job output | | cancel_subagent | Cancel an async job | | prune_subagent_jobs | Remove completed and failed jobs | | list_available_models | List configured model identifiers | | get_current_pane_activity | Check whether this Pi pane is active for user attention | | list_orchestrator_agents | List bounded Orchestratorv2 routing metadata and runtime pointers | | update_orchestrator_agent_description | Update a child's confirmed routing description and aliases | | subagent_interactive | Launch an attachable Pi session in tmux, Zellij, or Herdr | | get_interactive_subagent_status | Inspect attachable child sessions | | cancel_interactive_subagent | Kill an attachable child pane | | send_interactive_subagent_message | Send a follow-up while preserving child context | | list_subagent_artifacts | List durable interactive-agent artifacts | | read_subagent_artifact | Read lifecycle events and output snapshots | | cleanup_subagent_artifacts | Remove expired artifact directories and stale registry entries |

How it compares with other Pi sub-agent extensions

There is no single best extension; the useful distinction is what kind of control you want after delegation. This table compares the most widely used Pi sub-agent extensions as of July 2026, based on their published documentation.

| Extension | Strongest fit | Pros | Cons / tradeoffs | | ---------------------------------------------------------------------------------------- | -------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | pi-subagentura | Work you may want to watch, attach to, or continue interactively | Combines lightweight in-process jobs with real child Pi sessions; recursive supervisor with focus, bounded capture, and subtree cancellation; tmux/Zellij/Herdr attach; mid-session follow-ups; durable per-turn artifacts; parent restart/reload rehydration; bounded workflow runner | Interactive mode requires tmux, Zellij, or Herdr and starts another process; in-process jobs and workflows do not survive parent-session replacement; workflow JavaScript is trusted code, not a security sandbox; smaller community than the alternatives below | | @adamjen/pi-interactive-subagents | Fully asynchronous, multiplexer-native agent workflows | Dedicated panes in cmux, tmux, Zellij, or WezTerm; live status widget; interruption and session resume; custom agents; child-to-parent help requests; bundled /plan and /iterate workflows | Child-process/multiplexer-only design with no lightweight in-process path; its help-request flow exits and later resumes the child; no documented immutable per-turn output and durable delivery-receipt protocol comparable to pi-subagentura's | | pi-subagents | Feature-rich orchestration and automated multi-step coding workflows | Large built-in agent/workflow set; foreground and background runs; chains, parallel groups, worktrees, lifecycle artifacts, fleet UI, watchdog review, supervisor messaging, and nested delegation | Much larger configuration and tool surface; more concepts to learn; does not provide an attachable terminal session—the fleet view is an inspector inside Pi | | @tintinweb/pi-subagents | Claude Code-style sub-agents inside Pi | Polished live widget and FleetView; foreground/background execution; steering and resume; custom agent definitions; worktree isolation; scheduling; model/tool/extension controls | Broad feature/configuration surface; UI and control stay inside the parent Pi experience rather than exposing a normal attachable child terminal; persistent sessions/artifacts are optional rather than the default source of truth | | @mjakl/pi-subagent | A small, predictable delegation primitive | Simple tool shape; fresh or parent-seeded context; parallel calls; named persistent sessions; depth/cycle guards; rich streaming TUI | Fewer orchestration features; no background job manager or durable event protocol; no live attachable pane; a stale persistent-session lock can require manual cleanup after a killed process |

If you want multiplexer-native async agents with broader terminal support, try @adamjen/pi-interactive-subagents. If you want the broadest orchestration toolbox, start with pi-subagents. If you want a Claude Code-like UI, try @tintinweb/pi-subagents. If you want the smallest conventional child-process implementation, try @mjakl/pi-subagent. pi-subagentura is for the narrower case where a delegated agent should remain a real session you can observe and re-enter, while still offering cheap in-process delegation for short tasks.

Adjacent coding-agent implementations

These are not Pi extensions, so the comparison is secondary. They are useful reference points for the interaction model.

| Tool | Pros | Cons / difference from pi-subagentura | | ------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Claude Code subagents | Mature built-in delegation; foreground/background execution; custom prompts, models, tools, permissions, and skills; context forking; automatic or explicit routing | Subagents are normally task workers that return results to the parent; they cannot spawn subagents; direct multi-session collaboration is a separate agent-teams feature; no tmux/Zellij/Herdr attach-and-rehydrate protocol | | Codex subagents | First-class agent threads in the app, CLI, and IDE; inspect, steer, interrupt, and switch threads; custom agent configurations; bounded nesting and concurrency controls | Part of the Codex product rather than a portable Pi extension; delegation can consume substantially more tokens; no artifact contract designed for attaching to a normal child terminal process | | OpenCode agents | Simple primary/subagent model; automatic or explicit @ invocation; custom prompts, models, tools, and permissions; built-in parent/child session navigation | Navigation stays inside OpenCode's session UI; no separate attachable mux pane or pi-subagentura-compatible durable artifact/delivery protocol |

Bundled orchestration defaults

The package also ships parent-only orchestration guidance for common multi-agent workflows in ORCHESTRATOR_SYSTEM_PROMPT.md. Enable it with the extension's --orchestrator flag:

pi --orchestrator

The guidance gives the parent agent reasonable default behavior when the user asks for things like:

• “review this codebase” — inspect first, then run fresh-context reviewers with focused angles
• “review my changes” — use read-only reviewers, synthesize findings, and only edit when authorized
• “plan this work” — scout relevant files, then produce a concrete implementation plan
• “check my approach” — run a context-aware oracle to challenge assumptions and drift
• “implement and review” — use one writer, parallel reviewers, and capped fix/review rounds

The defaults prefer async subagent_isolated for fresh scouts/reviewers, subagent_with_context for oracle checks, coordinated reference manifests instead of polling or full-output injection, and one writer at a time for implementation. Asynchronous completion defaults to completionPolicy: "each": each terminal record becomes immediately eligible, while records that finish while the parent is busy coalesce into a safe-idle continuation. Related work uses an explicit completionPolicy: "group" and caller-declared completionGroupId; relatedness is never inferred from being launched in the same turn or from task text. For cheap fan-out, the guidance suggests validating model availability before using optional model overrides.

Orchestratorv2 thin-router mode

Enable the separate prompt-directed thin router with:

pi --orchestratorv2

This flag appends ORCHESTRATOR_V2_SYSTEM_PROMPT.md; it does not select or verify the parent model and does not enforce a host-level tool allowlist. Select the intended lightweight model separately, and do not enable --orchestrator and --orchestratorv2 together. Normal workflow and in-process tools remain registered for compatibility, while the Orchestratorv2 prompt directs the parent to delegate only through attachable interactive children and use the parent session's authoritative routing ledger together with the project-local routing cache.

Extension settings

Install the optional settings panel once with:

pi install npm:@juanibiapina/pi-extension-settings

Use /extension-settings for global settings. Whether a project value can override the global one is per-setting — see the scope rules below; only max-depth is project-overridable. The optional package's /extension-settings-local command is not session-cwd-correct in the pinned @juanibiapina/[email protected]: it resolves local settings from Node's process cwd instead of Pi's command context. Do not use that command for cross-project sessions. It also still renders a hide-agent-list row, but setting it there is a no-op because that setting is global-only. For a session-local max-depth, edit <session-cwd>/.pi/settings-extensions.json manually, using the exact cwd of the Pi session. max-depth controls Orchestratorv2 lineage depth and defaults to 2; hide-agent-list defaults to false and only hides the compact per-agent activity widget rows. The running footer, list/status tools, and visual agent supervisor remain available.

Both settings can also be configured without the panel. The global file ~/.pi/agent/settings-extensions.json accepts either key:

{
  "pi-subagentura": {
    "max-depth": "4",
    "hide-agent-list": "true"
  }
}

The project-local file <project>/.pi/settings-extensions.json is read for max-depth only:

{
  "pi-subagentura": {
    "max-depth": "6"
  }
}

Scope rules:

• max-depth is read project-local first, with the global file as fallback.
• hide-agent-list is read only from the global file. A checked-out repository must not be able to hide agent activity from whoever opens it, so a project-local hide-agent-list is ignored.

An invalid persisted value never aborts a session: the extension keeps the documented default (max-depth 2, hide-agent-list false) and reports the ignored value in the TUI at the start of a root session, and to the debug log otherwise.

The extension also exposes these validated launch flags for advanced configurations:

• --subagentura-max-depth <n> — override max-depth for the current run; legacy orchestration keeps its existing depth of 8. Unlike the persisted setting, an invalid value here fails fast.
• --subagentura-hide-agent-list — force hide-agent-list on for the current run without changing the persisted global setting. It also works without the optional settings panel. The flag is on-only: it cannot override a persisted hide-agent-list of true, so to show the rows again clear the global setting.
• --subagentura-telemetry — anonymous product analytics, enabled by default. Extension booleans are presence-only; --subagentura-telemetry=false is not an opt-out.
• --no-subagentura-telemetry — presence-only opt-out for anonymous product analytics. The exact events and other opt-outs are documented in Anonymous product telemetry.

See the thin-router flow

A small real-session story: open the parent replay to see one user talking with a lightweight Orchestratorv2 parent while it fans work out to many attachable child sessions. The highlighted spawn point shows the thin router creating a second Pi session for the reusable workflow-child work.

Open the child-session replay to see that child session create two interactive specialists—a recovery-safety reviewer and a package/API reviewer—and supervise their work in its own conversation.

This is the core v2 model in miniature: you can keep talking with the orchestrator, or attach and talk directly with a child. Children can create and supervise their own descendants, while important outcomes flow back through the child and the parent’s existing artifact and notification paths. The replay annotations mark the parent-to-child handoff and the two specialist launches.

Replays generated with vibe-replay, an interactive replay and sharing tool for AI coding sessions.

The v2 prompt gives the parent a lightweight routing role: it routes clear work to attachable interactive subagents, can split broad requests across specialists, and asks for clarification when a request is ambiguous or a narrow request has no matching child. The parent is instructed to leave specialist repository work to those children; this is prompt guidance, not an enforced routing boundary.

For interactive children in the matching parent session, artifacts, routing state, pending deliveries, and receipts persist and rehydrate across same-session restart, reload, and resume paths. Delivery is bounded and at-least-once; in-process jobs and background workflows remain session-scoped.

Orchestratorv2 adds exactly two routing-metadata tools: list_orchestrator_agents and update_orchestrator_agent_description. Confirmed records include explicit provenance: user or orchestratorv2. Responsibility updates use a server-issued, single-use confirmation token bound to the exact payload, current session generation, and a later user message; a model-supplied confirmed: true is not sufficient by itself.

The parent session's current branch is the authority ledger. Every approved top-level spawn and confirmed update persists the bounded project-local record first, then appends an exact versioned parent custom entry. On reload/resume, the latest valid authority entry for each child is selected by physical branch order. Those parent entries are the sole trusted/actionable source; the project file is only untrusted cache/proposal data and may be missing, stale, malformed, or over capacity. Cache-only or mismatched rows may be shown as non-actionable diagnostics, but they never gate actionability, capacity, confirmation CAS, or repair writes. Missing cache rows do not erase valid parent authority.

When no valid parent authority exists, cache metadata remains visible only as non-actionable metadata with a closed-enum untrusted reason. Approved writes rebuild the cache from the latest parent authority plus the incoming record, so forged cache rows cannot consume the 128-record capacity or become authoritative.

The parent-entry ledger is an application-level boundary, not an OS security boundary: a same-UID process that can tamper with the parent session file can forge parent entries. This limitation is intentional and documented; the ledger does not claim to defend against arbitrary same-UID session-file tampering. Routing metadata is never a lifecycle registry or semantic resolver.

The interactive runtime launches before its initial routing metadata is persisted. If persistence fails, the child intentionally remains live and the spawn result includes an explicit warning; the extension does not cancel, roll back, replace, or respawn that child. Capacity exhaustion fails closed without evicting or deleting metadata.

Interactive children retain subagent_interactive and may autonomously create nested children without top-level approval. Nested children belong to the immediate child session and are not automatically actionable in the top-level Orchestratorv2 routing registry; their important outcomes return through that child or the existing artifact and notification paths.

Cancellation context snapshots (opt-in)

Cancellation snapshots are disabled by default. To enable bounded snapshots before parent-initiated cancellation, set:

SUBAGENT_CANCEL_SNAPSHOT=full pi

In-process sub-agents write a private atomic JSON snapshot of the canonical active branch plus bounded partial streaming state. Interactive/process sub-agents write a private manifest that points to their already-persisted Pi session JSONL and artifact files; the transcript is not duplicated. Cancellation results expose receipt paths and errors, never snapshot contents.

Optional configuration:

• SUBAGENT_CANCEL_SNAPSHOT_DIR — override the private snapshot root. The directory and files are created with 0700/0600 permissions.
• SUBAGENT_CANCEL_SNAPSHOT_MAX_BYTES — maximum raw in-process snapshot size. The default is 1048576 bytes (1 MiB); accepted values range from 4096 bytes to 16777216 bytes (16 MiB). Invalid values use the default. Oversized snapshots preserve as much context as fits and record explicit truncation/error metadata.

Snapshots use schema version 1, temp-file + rename writes, deterministic per-session/job paths, and idempotent receipts so overlapping cancellation and shutdown paths do not duplicate files. They may contain sensitive prompts, tool arguments, and model output; keep the snapshot directory private and do not commit it.

Tools

subagent_with_context

Starts a sub-agent with the current conversation history included in its prompt.

Parameters:

• task — required task for the sub-agent
• persona — optional system-style persona
• model — optional model override like anthropic/claude-sonnet-4-5
• cwd — optional working directory override
• async — run in background; returns a jobId immediately instead of blocking
• completionPolicy — async completion coordination: "each" (default) or "group"; "each" makes records independently eligible, while "group" waits for an explicit barrier
• completionGroupId — caller-declared named group ID required with completionPolicy: "group"; safe 1–128 character ID shared by related jobs (max 32 members per group, 512 groups per parent session)
• notifyOnComplete — deprecated compatibility input; any value maps to coordinated "each" delivery with no full-output injection
• triggerTurnOnComplete — deprecated compatibility input; coordinated "each" timing and human priority remain authoritative
• maxAge — optional TTL in ms for completed job retention (async only)

Deprecated compatibility fields cannot be combined with completionPolicy or completionGroupId; completionGroupId is valid only with completionPolicy: "group".

Best for:

• review tasks that depend on prior discussion
• continuing a line of reasoning in parallel
• focused implementation or research using the current context
• background side-quests that report results later

subagent_isolated

Starts a sub-agent with no inherited conversation history.

Parameters:

• task — required task for the sub-agent
• persona — optional system-style persona
• model — optional model override like anthropic/claude-sonnet-4-5
• cwd — optional working directory override
• async — run in background; returns a jobId immediately instead of blocking
• completionPolicy — async completion coordination: "each" (default) or "group"; "each" makes records independently eligible, while "group" waits for an explicit barrier
• completionGroupId — caller-declared named group ID required with completionPolicy: "group"; safe 1–128 character ID shared by related jobs (max 32 members per group, 512 groups per parent session)
• notifyOnComplete — deprecated compatibility input; any value maps to coordinated "each" delivery with no full-output injection
• triggerTurnOnComplete — deprecated compatibility input; coordinated "each" timing and human priority remain authoritative
• maxAge — optional TTL in ms for completed job retention (async only)

Deprecated compatibility fields cannot be combined with completionPolicy or completionGroupId; completionGroupId is valid only with completionPolicy: "group". Async spawn results describe the selected coordinated behavior.

Best for:

• second opinions
• clean-room summaries
• avoiding context contamination from the parent session
• background analysis without polluting the main conversation

Async Workflow Tools

When you spawn a sub-agent with async: true, it returns a jobId immediately and runs in the background. The coordinated default is completionPolicy: "each": terminal records become independently eligible immediately, and records that finish while the parent is busy coalesce into one safe-idle continuation rather than a burst of turns. A related group is formed only when the caller explicitly selects completionPolicy: "group" and supplies a shared completionGroupId; same-turn launch or task text never infers a group. The default reports compact result references rather than injecting full output, so you usually do not need to poll. Use these tools only when the user asks for status or explicit collection, when a job appears stuck, or when manual follow-up is needed:

Background jobs are scoped to the current parent session. This includes both async: true sub-agent jobs and jobs started by the workflow tool. They are cancelled on /reload, /resume, quit, and /new; their in-memory registries are not rehydrated into the next parent context. Interactive sub-agents are different: their mux panes and artifact-backed registry can survive reloads and restarts as described in Interactive Sub-agent Tools.

get_subagent_status

Poll an async subagent job by jobId. Returns a live preview of the subagent's current turn, active tool, and partial output.

Parameters:

• jobId — required job ID returned by the async spawn

get_subagent_result

Retrieve an async subagent job's current or final result and usage summary. A running job returns immediately unless explicit bounded waiting is requested. Successfully retrieving a terminal result consumes its pending coordinated delivery, so it is not sent again automatically.

Parameters:

• jobId — required job ID returned by the async spawn
• wait — optional; set to true to wait for a running job
• timeoutMs — optional wait timeout from 1 to 300,000 ms; defaults to 30,000 ms

cancel_subagent

Abort a running async subagent job by jobId.

Parameters:

• jobId — required job ID returned by the async spawn

prune_subagent_jobs

Remove all completed and failed subagent jobs from the registry. Running and cancelled jobs are preserved.

Interactive Sub-agent Tools

Observability and attachability are the primary design goals of interactive sub-agents—not debugging afterthoughts. Each child is a separate Pi process in a tmux, Zellij, or Herdr pane: watch it live, focus it from the current mux, attach from another terminal, or send follow-ups through the parent while preserving child context. If the parent is outside a mux, the child starts in a detached session and returns an attach command. The pane is the live view; durable artifacts are the source of truth.

subagent_interactive

Starts a separate interactive pi process in a tmux, Zellij, or Herdr pane and returns immediately with:

• sub-agent id
• pane id and mux backend (tmux, zellij, or herdr)
• attach command (works from outside the mux session)
• focus command (works from inside the same mux session)
• child Pi session file path
• artifact directory (events.ndjson + output.md)
• the window/tab name (in background mode) so you can find it in your mux UI

Parameters:

• task — required initial task
• name — optional display name for the pane/session
• persona — optional system prompt appended to the child session
• model — optional model override
• cwd — optional working directory
• includeContext — context mode selector: true serializes the full parent branch; false permits an explicit context; omitting both fields keeps the legacy independent mode
• context — optional explicit handoff when includeContext: false; capped at 64 KiB and never concatenated with the parent branch
• routingDescription — bounded responsibility persisted for top-level Orchestratorv2 routing; required by Orchestratorv2 policy and rejected outside that top-level mode
• routingAliases — optional bounded exact aliases for the responsibility; requires routingDescription
• mux — optional backend: "auto" (default), "tmux", "zellij", or "herdr". Auto prefers a Herdr-managed pane (HERDR_ENV=1), then the attached Zellij/tmux environment, and finally an installed tmux or Zellij detached-session backend. Explicit choice forces that backend. Herdr mode requires Pi to be running inside a Herdr pane and preserves its exact socket path for reload/rehydration.
• background — spawn in a detached named window/tab (invisible) instead of a visible horizontal split. Default true — your mux layout is undisturbed and you can attach later with the returned focus command. Pass background: false for a side-by-side split you can watch in real time.
• completionPolicy — "each" (default) or "group"; "each" makes records independently eligible, while "group" waits for a caller-declared named barrier
• completionGroupId — caller-declared named group ID required with completionPolicy: "group"; safe 1–128 character ID shared by related agents (max 32 members per group, 512 groups per parent session)
• notifyOnComplete — deprecated compatibility input; any value maps to coordinated "each" delivery with no full-output injection
• triggerTurnOnComplete — deprecated compatibility input; coordinated "each" timing and human priority remain authoritative

Deprecated compatibility fields cannot be combined with completionPolicy or completionGroupId. The spawn result describes the selected coordinated behavior.

The sub-agent's artifact contains events.ndjson lifecycle records, mutable output.md staging, and immutable protocol-v2 outputs/<eventId>.md terminal snapshots. Terminal retrieval uses the immutable snapshot by turnId; mutable output is legacy/staging fallback only. The pane is for live monitoring, and the artifact survives parent restarts.

• Interactive children also have get_current_pane_activity, which reports whether their tmux or Zellij pane is active for the user's current client. Herdr exposes server-global focus but no stable public attached-client proof, so its activity result remains neutral unknown rather than claiming user attention. Only children launched directly by a top-level Orchestratorv2 session receive protocol guidance to check this before tools or extensions that may wait for user input. Other children and parent sessions receive the neutral activity result without changing their user-attention behavior.

The interactive sub-agent registry state survives parent reloads and restarts. When spawned, a per-(cwd) state file is written to <cwd>/.pi/subagentura-state.json.

The state file and subagent panes are preserved across these actions:

| Action | State file | Panes | Rehydrated next start? | | ------------------------------------------------- | ----------- | ---------- | ---------------------------------------- | | Ctrl+D (quit) → restart with --session/-r | Kept | Preserved | ✅ Same session, parentSessionId matches | | Ctrl+D → fresh pi (no session) | Kept | Preserved | ❌ Different session, no match | | /reload | Kept | Preserved | ✅ Same session | | /resume (switch to another session) | Kept | Preserved | ✅ If parentSessionId matches | | /new | Deleted | Killed | ❌ Clean slate | | /fork | Deleted | Killed | ❌ Clean slate |

Note: /new deletes the state file. If you do /new and then /resume back to the session where subagents were spawned, they will not reappear — the state file was already deleted. Only /reload or a restart with the same session (--session/-r) preserves the registry.

On /reload and /resume, the session_start handler rehydrates the in-memory registry, filtering by parentSessionId so only subagents created in the current session are restored. Protocol-v2 byte cursors, pending delivery intents, receipts, coordinated policy, and group membership are restored. Recovered groups are sealed before polling begins. Parent-session completion and consumption entries reconcile notices and manifests so reload does not unconditionally replay already-delivered work.

Implementation details for crash-safe ordering and delivery recovery are in the state-file invariants in the source repository.

Unified async supervisor and recursive children

Run /subagents or press Ctrl+Alt+A to open the portable async supervisor. It combines standalone async in-process jobs, workflow jobs and their agent records, and the persisted lineage of interactive children and grandchildren. /workflow-tree remains available as a specialized workflow-only view. The supervisor uses a subtle theme-colored dither texture to simulate a dimmed backdrop behind its modal controls; terminal cells do not support true blur.

Standalone jobs are owner-scoped to the current parent session. Expanding a workflow shows its recent agent attempts, phases, usage, and bounded omission counts. Agent records are observational; cancelling the workflow signals its in-flight agents. Interactive lineage can include descendants created from different working directories. Interactive children receive a minimal child runtime that can launch more interactive children, but does not register in-process or workflow orchestration tools. Recursion is bounded by default to depth 8 and 256 live lineage nodes; the manifests of exited agents are pruned so a long-lived session's all-time spawn total never exhausts the budget. The supervisor shows active, actionable work only. Cancelled, completed, malformed, orphaned, cyclic, and stale entries remain available through retained artifacts but are hidden from the overlay. A footer line reports how many nodes were hidden and why, whether the view is truncated, and whether lineage refresh is failing, so hiding is never silent. Subtree cancellation walks the raw lineage manifests rather than the displayed tree, so a descendant past the depth or node cap is still cancelled and reported.

The overlay supports these controls:

| Key | Action | | ---------------------- | ------------------------------------------------------------------------------------------------------------------ | | ↑/↓, j/k | Select an async job, workflow, or interactive lineage node | | Enter/→ | Expand type-specific activity, usage, agent records, or bounded artifact details | | x | Cancel the selected running item; workflow and in-process cancellation propagates to owned agents | | v | For interactive agents, capture a bounded terminal snapshot through tmux/Zellij/Herdr | | n | For interactive agents, open the optional native tmux popup or Zellij floating viewer; Herdr has no native overlay | | f | For interactive agents, focus the persisted pane/window; Herdr uses native pane.focus | | a | For interactive agents, show the terminal-scoped attach command; Herdr uses herdr terminal attach <terminal-id> | | X | For interactive agents, confirm and cancel an actionable subtree deepest-first | | r | Refresh registries, lineage, and pane liveness | | q/Esc/Ctrl+Alt+A | Close the overlay without stopping agents |

Known Herdr limitation: the supervisor's optional n action cannot open arbitrary content in a Herdr-native overlay. Herdr currently exposes overlay and popup panes through installed plugin entrypoints rather than a generic public viewer API, so pi-subagentura does not add a hidden plugin dependency. Bounded capture (v), native pane focus (f), terminal attach commands, messaging, status, and cancellation continue to work normally. Herdr's returned focus and attach commands use the stable terminal ID rather than a transient pane ID.

Interactive row prefixes identify whether the item came from the live [registry] or persisted [lineage]. Expanding a row shows its owner, root and parent IDs, cwd, artifact directory, and Pi session file. A cancelled row disappears immediately.

Before pressing f, expand the selected interactive row to see its native return hint. With default keymaps, tmux uses prefix + ; for a split pane or prefix + l for a detached window. Zellij uses Ctrl+p, then p for a split pane or Ctrl+t, then Tab for a named tab. Herdr's supervisor f uses the native pane.focus API; its returned focus/attach command is the truthful herdr terminal attach <terminal-id> command.

Terminal capture is bounded by both bytes and lines. Expanded interactive artifact details read only regular files and bound lifecycle-event reads to 8 KiB, output reads to 4 KiB, and displayed previews to 512 characters. Direct interactive children remain in the root registry, while descendant completion delivery remains owned by the Pi session that spawned that descendant. Cancelling a descendant therefore does not inject its completion into the root session, and cancellation preserves its artifact directory for later inspection.

Sub-agent completion protocol

Every interactive child runs protocol-only Pi lifecycle hooks and therefore requires Pi SDK >=0.80.6. before_agent_start creates a provisional turn, the first turn_start binds it to the persisted Pi user-entry id, tool hooks record activity, and agent_settled records the authoritative completion after retries, compaction, and queued continuations. When Pi accepts Enter while streaming, it treats the message as steering inside the current agent run and does not emit another before_agent_start. The child protocol therefore detects the newly persisted steering user entry before its provider request and starts a distinct artifact turn for it. The explicit CLI remains supported:

$ARTIFACT_DIR/cli.mjs done 0       # success — parent reads the literal output.md path baked into the child prompt
$ARTIFACT_DIR/cli.mjs error "msg"  # unrecoverable failure
# 'cancelled' is only set by the parent via cancel_interactive_subagent

The explicit completion command is mandatory for every initial and follow-up turn. The child must complete these steps in order: write the final result to output.md, run cli.mjs done 0, wait until exactly one completion event is recorded successfully, then send its final assistant response. The command must be the final tool call of the turn. If it fails to execute, the child must not finalize; it fixes the failure and retries until completion is recorded. The child lifecycle hook at agent_settled is a crash-safety fallback, not a substitute for the explicit command. The system prompt, initial task footer, and every injected follow-up prompt repeat this requirement so the command remains the model's most recent instruction.

At each child turn start, mutable output.md is atomically reset without touching earlier snapshots. Before each completion event, the current staging file (including an empty file when the turn wrote nothing) is copied atomically to outputs/<eventId>.md with byte count and SHA-256 metadata. Events are consumed in physical NDJSON byte order; timestamps are display-only. Mixed v1/v2 logs and legacy output-N.md snapshots remain readable. New legacy completions are pointer-only because mutable output.md cannot be safely attributed to a turn.

Immutable snapshots are limited to 1 MiB. The parent and generated child CLI check the staging file size before reading it. If output.md exceeds the limit, the completion is still recorded with outputError.code = "output_too_large" and its observed byte count, but no immutable snapshot is created. The coordinated manifest therefore has no snapshot reference, and legacy injection cannot load the oversized output. The staging file remains available for manual inspection in the artifact directory.

Coordinated completion delivery

Coordinated delivery is the default for asynchronous in-process jobs, interactive agents, and background workflows. It separates the human channel from the parent-model channel:

1. Every parent-visible standalone done, error, or cancelled completion, plus every background workflow aggregate completion, appends one deterministic subagentura-completion entry rendered in the TUI. This entry is excluded from LLM context, and event replay does not append it again. Workflow-owned child turns remain visible through workflow progress but do not publish directly.
2. The parent model receives one bounded, hidden subagent-manifest containing statuses and references—not child output. Interactive records point to the immutable outputs/<eventId>.md snapshot when available plus events.ndjson; legacy artifacts may fall back to mutable output.md. In-process and workflow records point to get_subagent_result and get_workflow_result.
3. A ready manifest attaches to a pending human-initiated turn when possible. Otherwise Pi receives one triggered follow-up after the parent is safely idle. Human prompts and steering always take priority.

completionPolicy controls readiness:

• "each" (default) makes every independent result eligible immediately. Results that finish while the parent is busy are coalesced into one manifest at the next safe-idle dispatch; this is the default independent-delivery behavior.
• "group" requires the caller to provide one shared, explicit completionGroupId. Same-turn launch and task text do not infer relatedness. Register all members in the intended group before the spawning parent turn settles; settlement seals the group, rejects late members, and blocks model delivery until every registered member is done, error, or cancelled. Per-member TUI notices still appear immediately, and an entirely consumed group does not trigger an empty turn.

A named group is advanced cross-call control. A group supports at most 32 distinct source:sourceId members, with at most 512 groups per parent session. completionGroupId is 1–128 characters and must match [A-Za-z0-9][A-Za-z0-9._:-]*. A source can satisfy a group only once; later turns from the same source/group are delivered independently as each.

The completion coordinator owns readiness, group barriers, TUI notice persistence, and compact manifest construction. When an idle manifest is ready, it passes through sendCompletionTurn with the actual parent streaming state. Non-v2 modes fall through to Pi's native sendMessage; idle Orchestratorv2 uses the lower-level transport to persist a wake request, publish the manifest with its wake identity, and send a synthetic user follow-up so before_agent_start installs the thin-router prompt. A streaming parent keeps Pi's native follow-up behavior.

Wake state is process-global because Pi can load delivery and lifecycle extension graphs as separate module instances. The exact synthetic prompt is marked in before_agent_start, and only that marked run's agent_settled acknowledges the wake; unrelated turns cannot consume it. A missing run start receives at most three wake attempts separated by a 30-second watchdog, while durable acknowledgement writes retry at most three times with a one-second delay. Session replacement and shutdown clear both timers; reload/resume recover only delivered, unacknowledged wakes from the active parent branch.

Successful terminal retrieval through get_subagent_result, get_workflow_result, or read_subagent_artifact with output consumes the matching pending record before returning it. Automatic and manual delivery share the same receipts, so a consumed record is suppressed from normal subsequent dispatch. This is not an exactly-once delivery guarantee: a crash around parent dispatch can still replay a manifest as described below. Workflow-owned process or in-process children never publish directly; only the background workflow aggregate completion participates in coordinated delivery.

The deprecated notifyOnComplete and triggerTurnOnComplete fields remain accepted for compatibility. Either legacy value maps deterministically to coordinated "each": the notice is TUI-only, the parent receives only compact references, and policy plus human-priority rules control timing. Combining either field with completionPolicy or completionGroupId is rejected. Persisted pre-coordinator intents may still drain through the bounded legacy broker during upgrade recovery, but new API calls cannot select full-output injection.

Interactive coordinated policy, group membership, and intents survive same-session startup/reload/resume through .pi/subagentura-state.json and parent session entries. Consumption receipts prefer those entries and use the private fallback ledger when needed. In-process jobs and background workflows remain parent-session scoped and are retired on session replacement. new and fork do not import prior completion work.

Parent delivery fails closed behind durable notice storage. If appendEntry fails, the notice remains pending and the manifest is withheld; later coordinator activity retries without a tight loop. If the entry was written before an exception, session-entry reconciliation prevents a duplicate. Deterministic identities prevent routine replay, but Pi's synchronous sendMessage proves dispatch rather than durable commit, so a crash in that separate window can still replay a manifest.

Consumption-receipt fallback

Parent session entries are the preferred durable location for consumption receipts. If the parent cannot append an entry because appendEntry is unavailable or fails, the coordinator appends the receipt beneath the parent Pi session directory, outside the project working tree. The path is keyed by the parent session identity and is not shared across sessions. A partial manager without a session directory uses a random process-private temporary root and does not claim restart durability.

Readers take a fixed snapshot and enforce total byte, record-count, line, identifier, and selector bounds. An over-budget or truncated snapshot is ignored and advances to its end; this deliberately risks a duplicate manifest instead of letting unchecked file data consume or retire trusted completions. Turn-scoped receipts require the exact turnId, so source-only receipts cannot suppress later interactive turns. Reconciliation resumes from the bounded high-water mark for receipts appended afterward.

Session shutdown clears live coordinator state and records lifecycle retirements: non-interactive session-scoped work is retired, while interactive state and receipts remain eligible for same-session reload, resume, or restart. /new and /fork also retire interactive work and do not import prior completion work. Cleanup does not truncate or delete protected fallback ledgers, so old private files can remain after a replacement session starts.

get_interactive_subagent_status

Lists tracked interactive sub-agents, attach/select commands, and session paths. It intentionally does not capture pane output to avoid consuming model context.

Parameters:

• jobId — optional interactive sub-agent id; omit it to list all tracked sessions

cancel_interactive_subagent

Kills the mux pane for an interactive sub-agent by id. Writes a cancelled event and immutable output snapshot before killing the pane, so artifacts remain self-describing. The tool result acknowledges the cancellation to the parent. Under coordinated delivery, cancellation also creates one TUI-only terminal entry and satisfies an all-terminal group barrier; any later manifest contains only the bounded cancellation reference. Upgrade-recovered legacy intents retain their existing delivery receipt suppression.

Parameters:

• jobId — required interactive sub-agent id returned by subagent_interactive

send_interactive_subagent_message

Sends a follow-up prompt to a running or idle interactive sub-agent by id. The message is delivered into the child's existing REPL via the sub-agent's mux backend (tmux send-keys or zellij write-chars + write 13), so the child's model context is preserved — this is a true follow-up turn, not a fresh spawn.

Every persisted user entry produces a distinct artifact turn and immutable completion snapshot. An idle follow-up resets future delivery to independent each. A source can satisfy a completion group only once, so later turns from that source/group are also delivered independently as each, even when steering retained the active turn's persisted group metadata.

Workflow-owned children reject follow-ups until the workflow has consumed the current result and the pane is idle. The first successful follow-up then promotes the pane to standalone. The child calls cli.mjs done 0 again when finished.

The tool refuses to send if the sub-agent is not registered, is neither running nor idle, remains workflow-owned, or the mux rejects the send call. Each failure returns a structured isError: true result.

Parameters:

• id — required sub-agent id
• message — required follow-up prompt text

list_subagent_artifacts

Lists all known interactive sub-agents: id, name, status, artifact directory, and last-update timestamp. Use this to discover sub-agents that finished while the parent was away.

read_subagent_artifact

Reads a sub-agent's artifact by id. Returns the lifecycle event log (pass since to fetch only new events) and, by default, the latest terminal immutable protocol-v2 snapshot. Mutable output.md is used only when no protocol-v2 terminal snapshot applies, including legacy or still-running artifacts. This avoids misattributing active follow-up staging bytes to an earlier terminal turn. A successful read that returns a terminal snapshot consumes that turn's pending coordinated delivery; an events-only read does not.

Protocol-v2 completions map each Pi-derived turnId to an immutable outputs/<eventId>.md snapshot. Pass turnId to read that output; the response's details.outputHistory lists the available turnId/eventId mappings. Legacy output-N.md history remains available through numeric turn and details.availableTurns.

Parameters:

• id — required sub-agent id
• since — optional unix-ms timestamp; only return events with ts >= since
• includeOutput — include the output (default true); historical selectors imply output
• turn — optional turn number; read output-N.md for that specific turn instead of the latest output.md
• turnId — optional protocol-v2 Pi turn id, up to 256 characters; read its immutable outputs/<eventId>.md snapshot

list_available_models

List all available AI models with auth status. Use this to validate model identifiers before passing them to subagent tools — prevents silent fallback to the parent session model.

Parameters:

• filter — optional substring filter for provider or model name
• authOnly — if true (default), only return models with configured auth

Example prompts

• “Use a sub-agent to review this change and list risks.”
• “Use an isolated sub-agent to propose a README outline for this repo.”
• “Spawn a context-aware sub-agent to continue debugging while we keep planning here.”
• “Run a sub-agent in the background to run the test suite, then notify me when done.”
• “Spawn two isolated async sub-agents to review this code from different angles, then collect both results.”
• “Start an interactive sub-agent in tmux for investigating the auth bug; give me the attach command.”
• “Open an interactive sub-agent in a visible zellij pane so I can watch its tool calls live.”
• “Attach to the existing interactive sub-agent and send it a follow-up without losing context.”

Anonymous product telemetry

Anonymous product telemetry is enabled by default. The extension sends best-effort lifecycle events directly to PostHog's public capture endpoint so the maintainers can understand which execution modes are useful and where sub-agent completion or collection breaks down.

Each logical root Pi session/tree receives one random UUID. It is not derived from Pi's session id and is never a stable installation, machine, user, repository, or project identity. The UUID and closed mode are stored only in the existing active-session .pi/subagentura-state.json file so live starts and later completions remain correlated across reload, resume, and matching startup recovery after quit. Fresh new and fork sessions replace or clear it. Bounded active-turn progress (closed dimensions, turn timestamps, and message counts) may be stored there for the same recovery purpose; prompt and output content is never included. Recursive interactive children receive correlation only through the existing mode-0600, one-use lineage bootstrap—not through ambient identity environment variables—and never read or write the root state file's telemetry metadata. A child without that explicit context starts an unrelated anonymous correlation rather than reconstructing identity.

The payload schema is versioned and contains these events:

| Event | Properties | | -------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | session_started | package version; straight, orchestrator, or orchestrator_v2 mode | | agent_created | once per accepted in-process agent or launched interactive pane; execution kind, closed mux (none, tmux, zellij, or herdr), closed invocation source, public/sanitized model, async, exact bounded depth plus bucket, and completion policy | | task_started | once per accepted in-process job or authoritative interactive turn; repeats the closed execution and mux dimensions and adds job or turn | | interactive_message_sent | explicit parent-to-child steering/follow-up direction and bounded count only | | task_completed | repeated closed execution and mux dimensions; success, error, or cancelled; rounded numeric duration plus bucket, both reported as unknown when the measured span is implausible; bounded child-conversation message count when observable | | completion_delivered | manifest or compatibility notification kind and bounded record count | | result_consumed | in-process, interactive, or workflow result kind |

All events include the closed root mode and set $process_person_profile: false, $geoip_disable: true, and $ip: "0.0.0.0". Terminal task events repeat the closed invocation source and completion policy so completion rates need no identifier join. They contain only closed enums, booleans, bounded counts, the package version, and the random runtime correlation UUID. The extension does not send tasks, personas, prompts, message content, outputs, error text, names, group ids, paths, repositories, artifact/agent/Pi session ids, token usage, cost, or a persistent installation id. PostHog can still observe the connection's source IP while handling the HTTP request. The project-level Discard client IP data setting should also