v0.33.0

Added

• Added optional toolBudget limits for child subagent tool calls. Runs, steps, and agents can set { soft?, hard, block? }; the child runtime nudges at the soft limit and blocks configured tools after the hard limit so runaway browsing can still finish with final text.
• Added a stable v1 in-process event-bus RPC for other Pi extensions, with ping, status, async-only spawn, interrupt, and async stop over versioned request/reply envelopes.
• Added toolDescriptionMode with full, compact, and custom modes for the parent-facing subagent tool description. Compact mode reduces prompt bloat while keeping safety-critical orchestration guidance, and invalid custom descriptions fall back to full mode.
• Added an optional read-only subagent fleet/status view with /subagents-fleet and subagent({ action: "status", view: "fleet" }), plus view: "transcript" to tail active async child output/session artifacts.
• Added uniform per-child transcript artifacts (<run>_<agent>_transcript.jsonl) for foreground and async subagent runs, gated by subagents.artifacts.includeTranscript (default on). Each transcript is a versioned JSONL stream of child messages, tool starts/ends, and stdout/stderr lines with a byte cap and truncation marker.
• Added subagent({ action: "steer", id, message, index? }) for non-terminal guidance to live async Pi child sessions, with file-backed control requests, per-child steering inboxes, status/event visibility, and queued delivery for pending indexed async children when the runtime supports mid-run steering.
• Added an optional turnBudget (maxTurns with graceTurns) for foreground and async/background subagent runs. At the soft maxTurns limit the child is warned via its system prompt to wrap up; after graceTurns additional assistant turns the run is aborted and partial output is returned. turnBudget, turnBudgetExceeded, and wrapUpRequested propagate through results, async status, and nested summaries.
• Added optional scheduled subagent runs so callers can defer a subagent launch until a future time. subagent({ action: "schedule", agent, task?, schedule: "+10m" | "2030-01-01T09:00:00Z", scheduleName? }) arms a one-shot timer that launches the run as a normal tracked async run once it fires, with schedule-list, schedule-status, and schedule-cancel management actions. Schedules are persisted per session and restored after a Pi restart; jobs missed by more than the configured lateness window are marked missed instead of firing late. The feature is opt-in and requires { "scheduledRuns": { "enabled": true } } in ~/.pi/agent/extensions/subagent/config.json. Only schedule explicit delayed runs the user asked for. Thanks to @tintinweb for the concept.
• Added a real Pi-session E2E test lane with faux provider routing to verify parent-child subagent result delivery without network model calls.
• Hardened the wait tool's wake path so an event wake cancels its poll-interval fallback timer instead of letting both run, and so an already-aborted turn resolves immediately. Added a test that verifies an event wakes wait before the poll interval elapses.
• Added smart completion batching for async subagent notifications. Successful sibling completions that finish within a short window now arrive as a single grouped message instead of separate notifications; a hard max-wait cap prevents holding them indefinitely, and late-finishing siblings join a shorter straggler group. Failed and paused completions bypass batching and fire immediately so failure and attention signals are never delayed. The debounce window, max-wait cap, and straggler windows are configurable via completionBatch in config.json.
• Added subagent({ action: "eject" }), disable, enable, and reset management actions for bundled and custom agents. eject copies a builtin or package agent to user/project scope as an editable custom file that shadows the original; disable/enable toggle a reversible agentOverrides.<name>.disabled settings override without deleting the agent; reset removes the scope's custom agent file and/or settings override to restore the bundled default. All four accept agentScope: "user" | "project" (default user) and are blocked from child-safe fanout mode alongside create/update/delete.
• Added fuzzy model resolution so callers can specify models with provider separator variations, optional date-stamp parts, and case differences instead of exact provider/modelId strings. When subagents.modelScope: { enforce: true, allow: [...] } is configured, explicit caller-supplied out-of-scope models error while frontmatter/parent-inherited/fallback models warn. Inspired by @tintinweb's pi-subagents.
• Added a parent-side wait tool for detached async subagent runs. wait() returns when the next active run finishes or needs attention, wait({ all: true }) drains all active runs, wait({ id }) targets one run, and wait({ timeoutMs }) caps the block. This lets background-launching skills and non-interactive pi -p runs keep going without sleep/status-polling loops or abandoned children. Thanks to RoboBryce (@robobryce) for #365.
• Added an opt-in memory frontmatter field for agent definitions so recurring custom agents can maintain role-specific durable memory (e.g. a security reviewer accumulating threat-model notes). memory: { scope: "project" | "user", path: "<name>" } resolves a safe agent-memory/ directory, injects the first 200 lines of a MEMORY.md into the child system prompt, and falls back to a read-only memory block for agents without write tools. Memory lives under a dedicated namespace that does not conflict with Pi's parent/session/project memory system. Inspired by @tintinweb's pi-subagents.
• Added native supervisor coordination for child subagents. Children can use contact_supervisor without installing pi-intercom, and parent-side requests are scoped to the exact session id that spawned the child.
• Added native prompt workflow commands: /prompt-workflow runs a prompt template through a subagent, and /chain-prompts turns prompt templates into native subagent chain steps.

Fixed

• Let foreground sequential chain tool calls launch directly when clarify is omitted; use clarify: true to opt into the clarify UI. Addresses #385.
• Tolerate execution-mode action aliases such as single, parallel, PARALLEL, and tasks when the matching execution fields are present, while preserving clear runtime errors for unknown management actions, addressing #382.
• Removed companion-package recommendation messages from session start, subagent({ action: "list" }), and /subagents-doctor, addressing #381.
• Scope async subagent completion notifications to the exact owning Pi session so another session in the same repo no longer receives result notices.
• Harden scheduled-run timestamp parsing and persisted store validation so ambiguous absolute times and corrupted job records fail clearly instead of being normalized or dropped.
• Derive live-detail and full-notification hints from Pi's configured expand key instead of hard-coding Ctrl+O. Thanks to Kylegl (@kylegl) for #364.
• Tolerate transient Windows EPERM/EBUSY/EACCES locks when atomically replacing async JSON files. Thanks to ThanhNT29Jacky (@ThanhNT29Jacky) for #380.
• Hardened the async timeout integration test to wait for the mock child to spawn before asserting the timeout result, fixing a race where the timeout could fire before the child existed.