@xzzpig/pi-subagents 0.16.0 → 0.19.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +233 -1
- package/README.md +5 -3
- package/agents/claude-code-writer.md +1 -0
- package/agents/codex-exec-writer.md +1 -0
- package/agents/cursor-agent-writer.md +1 -0
- package/agents/reviewer.md +3 -2
- package/agents/worker.md +3 -2
- package/docs/agents.md +34 -21
- package/docs/configuration.md +82 -7
- package/docs/extension-api.md +75 -8
- package/docs/missions.md +13 -13
- package/docs/models.md +7 -5
- package/docs/observability.md +23 -13
- package/docs/standalone-background.md +5 -5
- package/docs/tool-reference.md +98 -100
- package/docs/watchdog.md +2 -0
- package/docs/workflows.md +214 -162
- package/inspector-runner.mjs +1 -1
- package/node_modules/@xzzpig/pi-components/package.json +4 -4
- package/package.json +15 -9
- package/prompts/council.md +6 -3
- package/prompts/review-loop.md +1 -1
- package/runner-peer-loader.mjs +4 -7
- package/runner-peer-preload.mjs +5 -7
- package/skills/council-mode/SKILL.md +1 -1
- package/skills/pi-subagents/SKILL.md +13 -5
- package/skills/pi-subagents/references/constraints-and-recipes.md +8 -5
- package/skills/pi-subagents/references/execution-controls.md +72 -69
- package/skills/pi-subagents/references/management-authoring-rpc.md +4 -4
- package/skills/pi-subagents/references/multi-lane-orchestration.md +9 -1
- package/skills/pi-subagents/references/prompting-and-roles.md +52 -54
- package/src/agents/advertised-agent-prompt.ts +21 -41
- package/src/agents/agent-eject.ts +3 -3
- package/src/agents/agent-management.ts +63 -54
- package/src/agents/agent-memory.ts +90 -3
- package/src/agents/agent-serializer.ts +4 -4
- package/src/agents/agents.ts +132 -51
- package/src/agents/global-npm-root.ts +58 -0
- package/src/agents/proactive-skills.ts +4 -1
- package/src/agents/runtime-agent-registry.ts +14 -11
- package/src/agents/skills.ts +42 -9
- package/src/api/delegation.ts +15 -0
- package/src/api/inspectors.ts +27 -0
- package/src/api/preflight.ts +7 -2
- package/src/extension/config.ts +12 -4
- package/src/extension/control-notices.ts +3 -0
- package/src/extension/doctor.ts +10 -4
- package/src/extension/fanout-child.ts +20 -3
- package/src/extension/herdr-pi-bridge.ts +2 -0
- package/src/extension/index.ts +168 -206
- package/src/extension/public-execution.ts +69 -35
- package/src/extension/reply-workflow-script.ts +58 -0
- package/src/extension/rpc.ts +39 -11
- package/src/extension/schemas.ts +47 -138
- package/src/extension/subagent-guide.ts +12 -4
- package/src/extension/tool-activation.ts +146 -0
- package/src/extension/tool-description.ts +62 -27
- package/src/extension/upgrade-notice.ts +40 -0
- package/src/inspectors/ghostty/plugin.ts +13 -1
- package/src/inspectors/plugins.ts +70 -3
- package/src/integrations/herdr-status.ts +19 -3
- package/src/intercom/intercom-bridge.ts +2 -0
- package/src/intercom/native-supervisor-channel.ts +26 -16
- package/src/intercom/result-intercom.ts +4 -0
- package/src/runs/background/active-async-capacity.ts +3 -25
- package/src/runs/background/async-execution.ts +60 -95
- package/src/runs/background/async-job-tracker.ts +91 -56
- package/src/runs/background/async-resume.ts +16 -8
- package/src/runs/background/async-retention.ts +46 -16
- package/src/runs/background/async-status.ts +2 -0
- package/src/runs/background/await-async-run.ts +76 -0
- package/src/runs/background/binary-bootstrap.ts +34 -6
- package/src/runs/background/chain-root-attachment.ts +4 -4
- package/src/runs/background/control-channel.ts +18 -2
- package/src/runs/background/fleet-view.ts +51 -7
- package/src/runs/background/notify.ts +98 -7
- package/src/runs/background/pid-namespace.ts +18 -0
- package/src/runs/background/process-terminal-candidate.ts +98 -0
- package/src/runs/background/process-terminal.ts +17 -96
- package/src/runs/background/result-watcher.ts +1 -1
- package/src/runs/background/retained-children.ts +3 -2
- package/src/runs/background/run-child-session.ts +20 -6
- package/src/runs/background/run-id-resolver.ts +10 -5
- package/src/runs/background/run-status.ts +16 -4
- package/src/runs/background/runner-aliases.ts +54 -16
- package/src/runs/background/runner-child-launch.ts +4 -2
- package/src/runs/background/runner-startup-failure.ts +56 -0
- package/src/runs/background/scheduled-runs.ts +5 -5
- package/src/runs/background/stale-run-reconciler.ts +19 -3
- package/src/runs/background/subagent-runner-bootstrap.ts +276 -0
- package/src/runs/background/subagent-runner.ts +111 -288
- package/src/runs/background/wait-tool.ts +2 -0
- package/src/runs/background/workflow-terminal-proof.ts +68 -0
- package/src/runs/foreground/async-stop-action.ts +17 -3
- package/src/runs/foreground/execution.ts +111 -139
- package/src/runs/foreground/prompt-audit.ts +3 -9
- package/src/runs/foreground/subagent-executor.ts +715 -258
- package/src/runs/shared/acceptance.ts +167 -68
- package/src/runs/shared/async-status-projection.ts +5 -0
- package/src/runs/shared/capability-ceiling.ts +4 -1
- package/src/runs/shared/child-hooks.ts +1 -16
- package/src/runs/shared/child-launch.ts +37 -16
- package/src/runs/shared/child-runtime-config.ts +3 -0
- package/src/runs/shared/child-session.ts +144 -8
- package/src/runs/shared/child-tool-plan.ts +38 -116
- package/src/runs/shared/dynamic-fanout.ts +1 -1
- package/src/runs/shared/external-cli-runner.ts +3 -1
- package/src/runs/shared/external-job-bridge.ts +54 -0
- package/src/runs/shared/git-environment.ts +29 -0
- package/src/runs/shared/mcp-config-sources.ts +5 -1
- package/src/runs/shared/mcp-direct-tool-allowlist.ts +104 -12
- package/src/runs/shared/mcp-direct-tool-grant.ts +22 -6
- package/src/runs/shared/model-resolution.ts +35 -10
- package/src/runs/shared/model-scope.ts +28 -9
- package/src/runs/shared/nested-events.ts +12 -0
- package/src/runs/shared/orca-progress-tabs.ts +3 -2
- package/src/runs/shared/parallel-utils.ts +4 -1
- package/src/runs/shared/pi-spawn.ts +1 -3
- package/src/runs/shared/single-output.ts +11 -2
- package/src/runs/shared/structured-output.ts +227 -7
- package/src/runs/shared/subagent-control.ts +2 -16
- package/src/runs/shared/subagent-prompt-runtime.ts +29 -5
- package/src/runs/shared/tool-availability.ts +2 -2
- package/src/runs/shared/tool-budget.ts +21 -0
- package/src/runs/shared/usage-reconciliation.ts +73 -0
- package/src/runs/shared/worktree.ts +36 -9
- package/src/shared/child-session-name.ts +4 -2
- package/src/shared/disabled-features.ts +123 -0
- package/src/shared/extension-context.ts +13 -0
- package/src/shared/fork-context.ts +11 -4
- package/src/shared/launch-contract.ts +1 -1
- package/src/shared/model-info.ts +9 -0
- package/src/shared/pruned-fork.ts +69 -56
- package/src/shared/settings.ts +1 -1
- package/src/shared/types.ts +73 -16
- package/src/slash/delegation-adapters.ts +25 -1
- package/src/slash/prompt-template-bridge.ts +18 -3
- package/src/slash/prompt-workflows.ts +12 -1
- package/src/slash/slash-commands.ts +17 -246
- package/src/slash/subagent-cost.ts +313 -0
- package/src/slash/subagents-admin.ts +4 -5
- package/src/tui/fleet-status.ts +38 -8
- package/src/tui/fleet.ts +21 -6
- package/src/tui/render.ts +166 -71
- package/src/tui/running-tone.ts +28 -0
- package/src/watchdog/diff-tool.ts +47 -12
- package/src/watchdog/permission-arbiter.ts +13 -15
- package/src/watchdog/register-child.ts +13 -5
- package/src/watchdog/register-main.ts +3 -3
- package/src/watchdog/review.ts +16 -16
- package/src/watchdog/runtime.ts +2 -1
- package/src/watchdog/turn-delta.ts +12 -6
- package/src/workflows/chat-progress.ts +2 -2
- package/src/workflows/scripted-workflow.ts +225 -59
- package/src/workflows/structured-workflow-scripts.ts +177 -0
- package/src/workflows/workflow-checklist.ts +6 -0
- package/src/workflows/workflow-child-summary.ts +4 -2
- package/src/workflows/workflow-receipt.ts +8 -2
- package/src/workflows/workflow-resources.ts +37 -12
- package/src/workflows/workflow-reuse.ts +120 -0
- package/src/workflows/workflow-revival.ts +123 -0
- package/src/workflows/workflow-settlement.ts +4 -1
- package/src/runs/shared/completion-evidence.ts +0 -89
- package/src/runs/shared/completion-guard.ts +0 -255
- package/src/runs/shared/llm-intent-arbiter.ts +0 -321
- package/src/runs/shared/task-intent.ts +0 -244
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,104 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## [Unreleased]
|
|
4
|
+
|
|
5
|
+
### Changed
|
|
6
|
+
|
|
7
|
+
- **Synced upstream `v0.72.0` → `v0.74.0`**: fenced ```` ```js workflow ```` blocks
|
|
8
|
+
replacing `workflowScript`/`workflowScriptPath` (`workflow: true`), `toolActivation`
|
|
9
|
+
(eager/dynamic/auto) and `disabledFeatures` config, Pi built-in MCP selections
|
|
10
|
+
(`mcp:` tools, codemode in children), `subagents.modelScope` `scoped` token,
|
|
11
|
+
`agentOverrides.<name>.advertise`, untrusted-project respect for children,
|
|
12
|
+
`/reload` no longer killing background workflows, and the undici 8.10.2 security
|
|
13
|
+
bump. The fork's projectTrusted/sandbox/permissionProfile threading, native
|
|
14
|
+
fleet transcript, context injection, and `as StreamFn` casts were re-applied;
|
|
15
|
+
upstream's duplicate `sessionProjectTrust` fields were dropped in favor of the
|
|
16
|
+
fork's `currentProjectTrusted`/`trustedProjectCwd`. The shim fixture gains the
|
|
17
|
+
Pi 1.0.0 normalized `systemPromptOptions` shape.
|
|
18
|
+
- Peer range follows the workspace Pi 1.0.0 baseline (`>=1.0.0 <2` for pi-ai);
|
|
19
|
+
devDeps pin pi-agent-core/pi-ai/pi-tui at exact `1.0.0` per the fork manifest
|
|
20
|
+
invariant.
|
|
21
|
+
- Synced upstream `v0.71.0` → `v0.72.0`: lazy subagent executor/Fleet loading,
|
|
22
|
+
global npm root discovery for package agents, external inspector
|
|
23
|
+
registration (`pi-subagents/inspectors` API, lazy `openSubagentFleet`
|
|
24
|
+
loading with the `getInspectorPlugins` getter), fast-mode accepting any
|
|
25
|
+
native `openai-codex/*` model via provider-prefix matching, watchdog helper
|
|
26
|
+
model calls routed through `modelRegistry.streamSimple`, `typebox` moved to
|
|
27
|
+
an optional peer dependency, and the `before_agent_start` advertised-agent
|
|
28
|
+
wait. The fork's `events`/inspector wiring, context injection,
|
|
29
|
+
sandbox/permission-profile threading, and the eject delegation were
|
|
30
|
+
re-applied on top; SDK pins stay at pi `0.87.0` (upstream pairing) with the
|
|
31
|
+
fork's `as StreamFn` casts extended to the three retargeted watchdog/audit
|
|
32
|
+
stream call sites.
|
|
33
|
+
- Synced upstream `v0.68.0` → `v0.71.0`: workflow terminal proof and readable
|
|
34
|
+
child session names, runner-side stripping of inherited Git routing
|
|
35
|
+
environment, symlinked prompt workflow file discovery, runner exit
|
|
36
|
+
code/signal reporting for dead runners, structured-only child terminal
|
|
37
|
+
settlement, compiled Bun host package root discovery, and the
|
|
38
|
+
`subagent-runner-bootstrap` entry with tool-activation smoke coverage.
|
|
39
|
+
- SDK baseline raised to pi `0.87.0` (devDependencies); the
|
|
40
|
+
`pi-coding-agent` type/runtime shim gains the `streamSimple` registry
|
|
41
|
+
member.
|
|
42
|
+
- Fork `sandbox` / `permissionProfile` / `hostAvailableBuiltins` threading
|
|
43
|
+
and the fleet-native transcript renderer were re-applied on top of the
|
|
44
|
+
upstream runner refactor; upstream's removal of `completionGuard` was
|
|
45
|
+
adopted.
|
|
46
|
+
|
|
47
|
+
## [0.74.0] - 2026-09-30
|
|
48
|
+
|
|
49
|
+
### Highlights
|
|
50
|
+
|
|
51
|
+
- Workflow scripts are now written as a normal ```` ```js workflow ```` code block in the reply and run with `workflow: true`, with no JSON escaping. This replaces `workflowScript` and `workflowScriptPath`.
|
|
52
|
+
- On models that cannot add a tool mid-conversation, `subagent` is now available from the start, so turning it on no longer reprocesses the whole conversation at full price.
|
|
53
|
+
- The new `disabledFeatures` setting hides parts of the `subagent` tool you do not use, and with `workflow-scripts` turned off you can run children with simple `chain` and `tasks` lists.
|
|
54
|
+
- `/reload` and session resumes no longer kill running background workflows, and relaunching one reuses the children that already finished.
|
|
55
|
+
- Subagent children now respect an untrusted project the same way the main session does.
|
|
56
|
+
|
|
57
|
+
### Added
|
|
58
|
+
|
|
59
|
+
- `disabledFeatures` in `config.json` removes feature groups you do not use from the `subagent` tool, such as agent management, watchdog, panes, missions, lane management, and per-call options like `toolBudget` or `machine`. Their parameters disappear from the tool, the tool description stops mentioning them, and calls that still use them fail with an error that names the setting. `scheduledRuns.enabled: false` now removes the schedule parameters the same way, and a malformed `scheduledRuns` value is now a config error. Nothing changes unless you opt in. With everything disabled, the tool declaration shrinks from 18,239 to 10,263 characters. See [configuration](docs/configuration.md#disabledfeatures). Thanks to [@tmustier](https://github.com/tmustier) for [#2542](https://github.com/nicobailon/pi-subagents/pull/2542).
|
|
60
|
+
- `disabledFeatures` also accepts `workflow-scripts`. It removes the `workflow`, `args`, `preflight`, `globalConcurrencyLimit`, and `maxSubagentSpawnsPerRun` parameters and the `validate` action, and the tool description no longer explains how to write scripts. In their place, the tool takes `tasks: [{ agent, task }]` to run children in parallel and `chain: [{ agent, task?, as? } | { parallel: [{ agent, task }] }]` to run steps in order. Chain tasks can use `{task}` (the top-level `task`), `{previous}`, and `{outputs.name}`. If a child fails, the run fails but still returns the results of the children that finished. Scripts that still arrive from RPC, `/prompt-workflow`, saved schedules, or delegated launches fail with an error that names the setting; `/run` still works. This mode saves about 2,000 more characters of tool declaration. Without it, the tool is unchanged. In both modes, extensions can no longer register workflow resources named `chain` or `tasks`. See [configuration](docs/configuration.md#chain-and-tasks-without-workflow-scripts).
|
|
61
|
+
- On Pi 0.99 and later without pi-mcp-adapter, `mcp:server` and `mcp:server/tool` entries in an agent's `tools` now select tools from Pi's built-in MCP, and the child gets exactly those tools. Servers from `mcp.json` work in foreground and background children; servers that extensions add with `pi.registerMcpServer()` work in background children. With pi-mcp-adapter installed, nothing changes. Thanks to [@fmoda3](https://github.com/fmoda3) for [#2555](https://github.com/nicobailon/pi-subagents/issues/2555).
|
|
62
|
+
- `subagents.modelScope` allow lists accept a `scoped` token, which stands for the parent session's scoped models (Pi's `/scoped-models`). Subagent model limits then follow Pi's model scoping without a second copy of the list. In an unscoped session, `scoped` means the same as `inherit`. Error messages list at most 8 patterns before summarizing the rest. Thanks to [@coreyryanhanson](https://github.com/coreyryanhanson) for [#2538](https://github.com/nicobailon/pi-subagents/pull/2538).
|
|
63
|
+
- `subagents.agentOverrides.<name>.advertise` lists an agent in the parent's agent catalog from settings, so you no longer have to copy a builtin agent file just to advertise it. Agents registered at runtime still cannot be advertised. Thanks to [@strive-run](https://github.com/strive-run) for [#2534](https://github.com/nicobailon/pi-subagents/pull/2534).
|
|
64
|
+
- Native Pi subagents can use Pi's built-in `codemode` tool when their tool selection allows it. It is loaded only in the child, so the main session can keep codemode off. Older Pi versions without codemode still report it as unavailable when an agent asks for it. Thanks to [@albertgwo](https://github.com/albertgwo) for [#2574](https://github.com/nicobailon/pi-subagents/pull/2574).
|
|
65
|
+
- After you upgrade pi-subagents, your first interactive session shows a short notice with the highlights of each new version and a link to the changelog. It is shown once and never enters the conversation, so it does not affect the model's context or prompt cache. Fresh installs and child sessions show nothing.
|
|
66
|
+
|
|
67
|
+
### Changed
|
|
68
|
+
|
|
69
|
+
- **Breaking:** Workflow scripts had to be passed to the `subagent` tool as a JSON string, so every quote and newline was escaped. The tool now takes one `workflow` field with three forms: `workflow: true` runs the single ```` ```js workflow ```` code block written in the same reply; a string containing `/` (such as `"./ci/sweep.js"`) loads a script file relative to `cwd`; any other string runs a named workflow. The `workflowScript` and `workflowScriptPath` parameters were removed, and calls that still pass them fail with an error that shows the new forms. RPC `spawn` takes inline script text as `script` and a path or workflow name as `workflow`. Saved schedules and run records keep working.
|
|
70
|
+
- On models that cannot take a new tool mid-conversation, calling `subagents_enable` made the provider reprocess the whole conversation at the uncached price. New sessions on those models now start with `subagent` already available. Models that can add tools mid-conversation still start with `subagents_enable`. Resumed sessions keep the tools they had, and switching models mid-session does not change them. The new `toolActivation` setting in `config.json` chooses `"auto"` (the default), `"dynamic"` (always start with `subagents_enable`, the old behavior), or `"eager"` (always start with `subagent`, like `--exclude-tools subagents_enable`). See [configuration](docs/configuration.md#toolactivation). Thanks to [@tinoy1336](https://github.com/tinoy1336) for [#2589](https://github.com/nicobailon/pi-subagents/issues/2589).
|
|
71
|
+
- After `subagents_enable`, the model was sometimes told to wait for the next prompt even when `subagent` was already usable. It is now told to check its tool list: use `subagent` if it is there, otherwise wait for the next prompt instead of retrying.
|
|
72
|
+
- CI now runs the tool-activation smoke test as a required check. Thanks to [@quifox](https://github.com/quifox) for [#2528](https://github.com/nicobailon/pi-subagents/pull/2528).
|
|
73
|
+
|
|
74
|
+
### Fixed
|
|
75
|
+
|
|
76
|
+
- Subagent children now follow the parent session's project trust. Before, a child in an untrusted project still loaded that project's settings, system prompt files, skills and, for background children, its extensions. Fixes [#2569](https://github.com/nicobailon/pi-subagents/issues/2569).
|
|
77
|
+
- `/reload`, a session resume, or a pi-web project switch stopped running background workflows and their children, and relaunching the script ran every child again, including ones that had already finished. Background children now keep running, the workflow's notice says to relaunch it, and relaunching the same script with the same args reuses finished children and waits for running ones. Failed children run again. The stop is recorded as `workflow.stopCause: "runtime-replaced"`. Fixes [#2546](https://github.com/nicobailon/pi-subagents/issues/2546).
|
|
78
|
+
- Stopping a background workflow by a short id, its tool-call id, its run directory, or from the Fleet view did nothing, so the workflow and its children kept running. These stops now work, and the workflow ends as stopped. Fixes [#2571](https://github.com/nicobailon/pi-subagents/issues/2571).
|
|
79
|
+
- Reviving a failed background workflow child with `subagent({ action: "resume", id })` did not show up in the workflow: its status, receipt and keyed `latest: true` resume still pointed at the failed run. Workflow `status` now shows `Revived → <run>: <state>` under the failed key, keyed resume continues from the revived run, and a workflow that finishes afterwards records the revival in its receipt and completion notice. The workflow's return value is unchanged. Thanks to [@l3gz](https://github.com/l3gz) for reporting [#2579](https://github.com/nicobailon/pi-subagents/issues/2579).
|
|
80
|
+
- When a workflow script failed and stopped a sibling that was still running, the sibling got a "Workflow child failed" notice whose error began with a "Run fan-out: N/M used, K remaining" line. The notice now says the child was stopped and gives only the reason. Fixes [#2562](https://github.com/nicobailon/pi-subagents/issues/2562) and [#2567](https://github.com/nicobailon/pi-subagents/issues/2567).
|
|
81
|
+
- After pi-subagents was updated on disk while Pi was running, for example by `git pull` in a local checkout or a package update, the first `subagent` call could fail with an error such as `(0 , _publicExecution.isWorkflowScriptPath) is not a function`, because it mixed new and old code. pi-subagents now loads all of its code shortly after a session starts, without slowing startup. After an update, run `/reload` or restart Pi to use the new version.
|
|
82
|
+
- With Pi 0.99's `codemode` turned on, codemode scripts could call `subagent`, `subagents_enable`, `subagent_supervisor`, `contact_supervisor` and `structured_output`, none of which work from a script: a `subagent` run there had no progress card and was cancelled unless awaited, `contact_supervisor` blocked the script, and `structured_output` had no effect. Codemode also added the whole `subagent` schema to its own description, about 2,200 extra tokens per request. The model can still call these tools directly, but scripts can no longer call them. Older Pi versions are unaffected.
|
|
83
|
+
- With the `subagent` tool registered, every request to llama.cpp (`llama-server --jinja`) failed with a 400 error because one parameter's pattern was not anchored at both ends, which llama.cpp requires. The pattern is now anchored and accepts the same values. Thanks to [@tychart](https://github.com/tychart) for reporting [#2581](https://github.com/nicobailon/pi-subagents/issues/2581).
|
|
84
|
+
- With pi-mcp-adapter 3.x on Pi 0.99 or later, `mcp:` entries in an agent's `tools` looked up Pi's built-in MCP instead of the adapter, so choosing an adapter server failed the launch. The adapter now takes priority whenever it is loaded. Fixes [#2575](https://github.com/nicobailon/pi-subagents/issues/2575).
|
|
85
|
+
- After upgrading pi-mcp-adapter to 3.1.0, `mcp:` tool selections for stdio servers stopped resolving, because the adapter started including `inheritEnv` and `literalEnv` in its config hash. pi-subagents now computes the same hash. Thanks to [@qsgy-edge](https://github.com/qsgy-edge) for [#2539](https://github.com/nicobailon/pi-subagents/pull/2539).
|
|
86
|
+
- When the async widget did not have room for its full view, its compact card showed one line per run and filled the rest with blank rows, hiding a workflow's lanes. The card now shows the lanes in that space and is only as tall as its content. Thanks to [@l3gz](https://github.com/l3gz) for reporting [#2578](https://github.com/nicobailon/pi-subagents/issues/2578).
|
|
87
|
+
- The async widget and the Fleet view counted running agents differently: with a 4-lane workflow and one other run, the widget said `2 agents running` and the Fleet view said `5 active agents`. The widget now counts each running workflow lane and each agent of a parallel run, like the Fleet view. Thanks to [@l3gz](https://github.com/l3gz) for reporting [#2578](https://github.com/nicobailon/pi-subagents/issues/2578).
|
|
88
|
+
- Herdr's subagent count no longer counts a workflow's coordinator as a child, and it updates as soon as a foreground workflow child starts or finishes instead of up to 45 seconds later. Thanks to [@xadips](https://github.com/xadips) for [#2556](https://github.com/nicobailon/pi-subagents/pull/2556).
|
|
89
|
+
- Dynamic tool activation now works when Pi runs inside another app, such as pi-web. Those hosts no longer print "Could not locate the running Pi installation" and no longer fall back to keeping `subagent` always loaded. Thanks to [@q107580018](https://github.com/q107580018) for [#2526](https://github.com/nicobailon/pi-subagents/issues/2526).
|
|
90
|
+
- Answering a background subagent's supervisor request no longer triggers a stale "needs attention" notice afterwards. The notice now waits 60 seconds and is sent only if the request is still unanswered and the run is still active. Status views still show the request right away.
|
|
91
|
+
- `inheritSkills: false` now also removes skills that extensions add to a child session (for example through `subagents.defaultExtensions`), so they no longer appear next to the agent's own skills. Thanks to [@zeezooz](https://github.com/zeezooz) for [#2540](https://github.com/nicobailon/pi-subagents/issues/2540).
|
|
92
|
+
- A child that was aborted by compaction now recovers when Pi reports the compaction late. Thanks to [@jiuai233](https://github.com/jiuai233) for [#2537](https://github.com/nicobailon/pi-subagents/pull/2537).
|
|
93
|
+
- Old background runs that belong to a finished or deleted mission are now cleaned up like other old runs instead of being kept forever. Fixes [#2535](https://github.com/nicobailon/pi-subagents/issues/2535). Thanks to [@LCorleone](https://github.com/LCorleone) for [#2536](https://github.com/nicobailon/pi-subagents/pull/2536).
|
|
94
|
+
- On Windows, the Pi interface froze for about 0.45 seconds once per process while background run cleanup waited on a PowerShell query. The query no longer blocks the interface. Thanks to [@localhedge](https://github.com/localhedge) for reporting [#2559](https://github.com/nicobailon/pi-subagents/issues/2559).
|
|
95
|
+
- On Windows, an idle session no longer checks for supervisor requests every 250 ms for its whole lifetime. Checking stops when no subagent work is pending and starts again when new work begins, as it already did on macOS. Thanks to [@localhedge](https://github.com/localhedge) for reporting [#2558](https://github.com/nicobailon/pi-subagents/issues/2558).
|
|
96
|
+
- Starting, reloading, resuming, or forking a session no longer pauses Pi while the watchdog records the current Git commit (about 50 ms per session start on Windows, even with the watchdog off). The check now runs in the background. Thanks to [@localhedge](https://github.com/localhedge) for reporting [#2560](https://github.com/nicobailon/pi-subagents/issues/2560).
|
|
97
|
+
- Worktree diffs now work with older Git versions that lack the `--default-prefix` option. Thanks to [@quifox](https://github.com/quifox) for [#2527](https://github.com/nicobailon/pi-subagents/pull/2527).
|
|
98
|
+
- Updated `undici` from 8.10.0 to 8.10.2, outside the range of [GHSA-3wwx-pv8p-q78v](https://github.com/advisories/GHSA-3wwx-pv8p-q78v), so projects that install pi-subagents no longer fail `npm audit` because of it. pi-subagents does not use the affected WebSocket client. Thanks to [@advaitpaliwal](https://github.com/advaitpaliwal) for [#2548](https://github.com/nicobailon/pi-subagents/pull/2548).
|
|
99
|
+
- A package-discovery test no longer fails when the system temp directory is inside a Pi project. Thanks to [@abdwhb-png](https://github.com/abdwhb-png) for [#2553](https://github.com/nicobailon/pi-subagents/pull/2553).
|
|
100
|
+
|
|
101
|
+
|
|
3
102
|
## [0.16.0] - 2026-09-22
|
|
4
103
|
|
|
5
104
|
### Changed
|
|
@@ -148,6 +247,136 @@
|
|
|
148
247
|
|
|
149
248
|
## [0.7.0] - 2026-08-24
|
|
150
249
|
|
|
250
|
+
## [0.71.0] - 2026-09-23
|
|
251
|
+
|
|
252
|
+
### Highlights
|
|
253
|
+
|
|
254
|
+
- Other extensions can read subagent spend and follow async workflow progress as data, without scraping terminal output.
|
|
255
|
+
- Workflow status can now confirm that every child process has actually exited.
|
|
256
|
+
- Child sessions keep readable names such as `worker: fix auth refresh` in `/resume` and Herdr.
|
|
257
|
+
- The full `subagent` tool loads only when a request needs it, which keeps unrelated prompts smaller.
|
|
258
|
+
- Background runners, reviewers, and Bun, pnpm, and symlinked installs are more reliable.
|
|
259
|
+
|
|
260
|
+
### Added
|
|
261
|
+
|
|
262
|
+
- In-process RPC `cost` method. It returns the same parent-plus-child spend that `/subagent-cost` shows, as versioned data (`{ version: 1, parent, children, childTotal, total, unresolvedAsyncChildren }`). `ping.capabilities.cost` advertises `{ version: 1 }`. `/subagent-cost` output is unchanged. Thanks to [@raymondtri](https://github.com/raymondtri) for [#2378](https://github.com/nicobailon/pi-subagents/pull/2378).
|
|
263
|
+
- Async `workflowScript` runs and the children they launch now emit public lifecycle events, so companion UIs can follow them without scraping terminal output. Thanks to [@navidemad](https://github.com/navidemad) for [#2382](https://github.com/nicobailon/pi-subagents/pull/2382).
|
|
264
|
+
- Status for an async workflow now includes `details.workflowTerminalProof`. It reports `observed`, with each child's exit evidence, only after the workflow has stopped launching children and every async child has exited or failed to start. Otherwise it reports `pending` or `unknown` with a reason, including when the saved child list is missing. A finished workflow frees its capacity slot using the same check, so the two always agree. Thanks to [@alexei-led](https://github.com/alexei-led) for [#2436](https://github.com/nicobailon/pi-subagents/issues/2436) and [#2442](https://github.com/nicobailon/pi-subagents/pull/2442).
|
|
265
|
+
|
|
266
|
+
### Changed
|
|
267
|
+
|
|
268
|
+
- Packaged `worker` agents now start with fresh context instead of forking the parent's conversation. You can still request fork context per call or set it globally. Thanks to [@eduardopicolo-cb](https://github.com/eduardopicolo-cb) for [#2384](https://github.com/nicobailon/pi-subagents/issues/2384).
|
|
269
|
+
- The full `subagent` tool stays hidden until a request activates it through the small `subagents_enable` loader, which keeps unrelated prompt context smaller. Direct commands, RPC, the TUI, and nested children work as before. Thanks to [@Knimoms](https://github.com/Knimoms) for [#2380](https://github.com/nicobailon/pi-subagents/pull/2380).
|
|
270
|
+
- Child sessions keep a readable name (for example `worker: fix auth refresh`) in session lists, `/resume`, and Herdr while the intercom bridge is active. Nested children now reach their supervisor through the child's intercom ID instead of its session name. This needs a pi-intercom version that supports the `intercom:session-identity` claim; with an older pi-intercom, children keep the previous naming so routing still works. Thanks to [@Q-xuan](https://github.com/Q-xuan) for raising the problem in [#2432](https://github.com/nicobailon/pi-subagents/pull/2432).
|
|
271
|
+
- The optional `@earendil-works/pi-ai` peer dependency now requires 0.86.1 or later, matching the oldest supported Pi host. Thanks to [@samuela](https://github.com/samuela) for [#2373](https://github.com/nicobailon/pi-subagents/issues/2373).
|
|
272
|
+
- When a child's `structured_output` call is rejected, the result now includes a short summary of the validation errors. The missing-structured-output error is used only when the child never called the tool. Thanks to [@rtbe](https://github.com/rtbe) for [#2407](https://github.com/nicobailon/pi-subagents/issues/2407).
|
|
273
|
+
|
|
274
|
+
### Fixed
|
|
275
|
+
|
|
276
|
+
- `subagent` is available again after switching from an inactive session branch to one where it was activated.
|
|
277
|
+
- Background runners and external CLI agents no longer inherit Git's repository variables (`GIT_DIR`, `GIT_WORK_TREE`, `GIT_INDEX_FILE`, `GIT_CONFIG_*`, and the rest of `git rev-parse --local-env-vars`). When Pi was started from a Git hook or with `git --git-dir`, these made a child's Git commands act on the parent's repository instead of the child's working directory. Other variables such as `GIT_AUTHOR_*` still pass through, and an external agent's explicit environment allowlist is unchanged. Thanks to [@alexei-led](https://github.com/alexei-led) for [#2437](https://github.com/nicobailon/pi-subagents/issues/2437) and [#2440](https://github.com/nicobailon/pi-subagents/pull/2440).
|
|
278
|
+
- Retained background runs no longer time out while the packaged runner is still starting. Thanks to [@muermaru](https://github.com/muermaru) for [#2403](https://github.com/nicobailon/pi-subagents/issues/2403), and to [@qsgy-edge](https://github.com/qsgy-edge) for the independent diagnosis and timing evidence in [#2415](https://github.com/nicobailon/pi-subagents/pull/2415).
|
|
279
|
+
- When a background runner exits without writing a result, the failure notice now includes its exit code and signal. Thanks to [@grahama1970](https://github.com/grahama1970) for [#2423](https://github.com/nicobailon/pi-subagents/issues/2423).
|
|
280
|
+
- A child that produced valid structured output keeps it as evidence when a later provider error or abort fails the run. Thanks to [@grahama1970](https://github.com/grahama1970) for [#2411](https://github.com/nicobailon/pi-subagents/issues/2411).
|
|
281
|
+
- Completion notifications are no longer sent twice when the extension is registered more than once for the same session. Thanks to [@hongchu098](https://github.com/hongchu098) for [#2389](https://github.com/nicobailon/pi-subagents/issues/2389).
|
|
282
|
+
- The bundled reviewer works in directories without Git: `watchdog_diff` reports that no baseline is available instead of failing the review. Thanks to [@matthewmathistrellys](https://github.com/matthewmathistrellys) for [#2422](https://github.com/nicobailon/pi-subagents/issues/2422).
|
|
283
|
+
- The bundled reviewer's `watchdog_diff` counts as read-only, so a reviewer given a single output path returns its full report for the runtime to save, as introduced in [#426](https://github.com/nicobailon/pi-subagents/issues/426), with thanks to Alexander Gerdes ([@Avg8888](https://github.com/Avg8888)). Thanks to [@riskywhat](https://github.com/riskywhat) for [#2405](https://github.com/nicobailon/pi-subagents/issues/2405).
|
|
284
|
+
- Watchdog reviews and permission checks work again on the Pi 0.86.1 package layout. Thanks to [@zieglar](https://github.com/zieglar) for the reproduction and version comparison in [#2377](https://github.com/nicobailon/pi-subagents/issues/2377).
|
|
285
|
+
- A workflow child with no `agent` now fails with an error that names it (`Workflow child 'r1' has no agent…`) instead of the generic "Provide exactly one mode" message. Thanks to [@matthewmathistrellys](https://github.com/matthewmathistrellys) for raising the confusing error in [#2422](https://github.com/nicobailon/pi-subagents/issues/2422).
|
|
286
|
+
- `/prompt-workflow` finds prompt files that are symlinks (as installed by dotfile managers such as GNU Stow or homeshick) and skips broken links instead of failing. Thanks to [@nietaki](https://github.com/nietaki) for [#2430](https://github.com/nicobailon/pi-subagents/issues/2430).
|
|
287
|
+
- Completed retained agents can resume even when their own list of allowed child agents excludes them. Parent authority and that restriction both still apply; older retained children without the needed recovery data fail closed. Thanks to [@riskywhat](https://github.com/riskywhat) for [#2379](https://github.com/nicobailon/pi-subagents/issues/2379), building on the allowlist work in [#2338](https://github.com/nicobailon/pi-subagents/pull/2338) credited to [@shkrabov](https://github.com/shkrabov).
|
|
288
|
+
- Guidance now says the list of retained workflow children is not complete: when you know a run's exact id, check its status and try resuming it before falling back to a labeled agent with the same role. Thanks to [@riskywhat](https://github.com/riskywhat) for [#2406](https://github.com/nicobailon/pi-subagents/issues/2406).
|
|
289
|
+
- Skills marked `disable-model-invocation: true` are no longer shown to child agents, even when requested by name, and are no longer suggested to the model. Thanks to [@toRolex](https://github.com/toRolex) for [#2400](https://github.com/nicobailon/pi-subagents/pull/2400).
|
|
290
|
+
- Pi hosts compiled with Bun are found from Pi's package directory or its bundled `share/pi-coding-agent` layout, while unrelated extension dependencies still cannot turn on dynamic tools. Thanks to [@fmoda3](https://github.com/fmoda3) for [#2417](https://github.com/nicobailon/pi-subagents/issues/2417).
|
|
291
|
+
- pnpm installs follow npm-hosted peer aliases through their symlinks to the real package, so the package is not loaded twice. Thanks to [@henriquebastos](https://github.com/henriquebastos) for [#2409](https://github.com/nicobailon/pi-subagents/pull/2409).
|
|
292
|
+
- npm and git installs detect dynamic tool support from the running Pi installation and keep the compact `subagents_enable` loader instead of an always-loaded `subagent` tool. Thanks to [@qsgy-edge](https://github.com/qsgy-edge) for [#2398](https://github.com/nicobailon/pi-subagents/pull/2398).
|
|
293
|
+
- MCP direct tool names now match what pi-mcp-adapter registers, including servers whose tool names already start with the server name, the adapter's `mcp` prefix mode, and per-server `toolPrefix`. Thanks to [@qsgy-edge](https://github.com/qsgy-edge) for [#2395](https://github.com/nicobailon/pi-subagents/pull/2395).
|
|
294
|
+
- Logs from running and failed external CLI agents can be viewed in Fleet, tool status, and the TUI. Thanks to [@Shujakuinkuraudo](https://github.com/Shujakuinkuraudo) for [#2375](https://github.com/nicobailon/pi-subagents/issues/2375).
|
|
295
|
+
- Structured delegation updates report cumulative usage and no longer count missing provider cache numbers as zero. Thanks to [@bioShaun](https://github.com/bioShaun) for [#2374](https://github.com/nicobailon/pi-subagents/pull/2374).
|
|
296
|
+
- Forked sessions keep Pi 0.87 context edits, including replaced content and signed Anthropic thinking blocks.
|
|
297
|
+
## [0.70.1] - 2026-09-20
|
|
298
|
+
|
|
299
|
+
### Highlights
|
|
300
|
+
|
|
301
|
+
- Delegated tasks no longer fail solely because they finish without editing files.
|
|
302
|
+
- Runtime-added agents now honor configured model, provider, and thinking preferences.
|
|
303
|
+
- Foreground children launch reliably when Pi is installed outside the extension's own dependency tree.
|
|
304
|
+
- Pi 0.86.1 support improves watchdog checks, provider-backed summaries, packaging, and standalone use.
|
|
305
|
+
|
|
306
|
+
### Changed
|
|
307
|
+
|
|
308
|
+
- Stop guessing whether task wording requires file edits. Successful tasks now follow their process result and explicitly configured output and acceptance checks. The `completionGuard` setting and `PI_SUBAGENTS_LLM_INTENT_ARBITER` switch have been removed. Thanks to [@SuTang-vain](https://github.com/SuTang-vain) for the reproduction that led to this change in [#2351](https://github.com/nicobailon/pi-subagents/issues/2351).
|
|
309
|
+
- Clarify that a custom agent file fully replaces a bundled agent with the same name. Custom implementation agents must declare `acceptanceRole: writer` to receive writer acceptance defaults.
|
|
310
|
+
- Update delegation guidance so large changes are split only when they contain independently testable parts.
|
|
311
|
+
|
|
312
|
+
### Fixed
|
|
313
|
+
|
|
314
|
+
- Apply `subagents.defaultModel`, `defaultProvider`, `defaultThinking`, and model-tier overrides to runtime-registered agents. Thanks to [@bioShaun](https://github.com/bioShaun) for [#2368](https://github.com/nicobailon/pi-subagents/pull/2368).
|
|
315
|
+
- Show each workflow child's resolved model and thinking level in parent status output. Thanks to [@grahama1970](https://github.com/grahama1970) for [#2364](https://github.com/nicobailon/pi-subagents/pull/2364).
|
|
316
|
+
- Preserve watchdog working-directory context and authenticated provider behavior for pruned-fork overflow summaries on Pi 0.86.1. Thanks to [@chem](https://github.com/chem) for [#2362](https://github.com/nicobailon/pi-subagents/issues/2362).
|
|
317
|
+
- Launch the packaged inspector bootstrap from its compiled JavaScript instead of an absent TypeScript source. Thanks to [@pablog12](https://github.com/pablog12) for [#2360](https://github.com/nicobailon/pi-subagents/issues/2360).
|
|
318
|
+
- Resolve the host `pi-coding-agent` package and its exports from the Pi installation that owns the session, so foreground children work across npm-hosted layouts without loading a second SDK instance. Thanks to [@nazerim](https://github.com/nazerim) for [#2348](https://github.com/nicobailon/pi-subagents/issues/2348).
|
|
319
|
+
- Show an actionable expand shortcut when a host cannot provide its configured keybinding label.
|
|
320
|
+
- Stop test-only background runners when their owning test process exits, and isolate test temporary data to reduce filesystem and Spotlight load.
|
|
321
|
+
|
|
322
|
+
## [0.70.0] - 2026-09-19
|
|
323
|
+
|
|
324
|
+
### Highlights
|
|
325
|
+
|
|
326
|
+
- Control which extensions children load and which agents descendants may launch without widening their permissions.
|
|
327
|
+
- Background workflows remain visible and recoverable through detaches, interruptions, restarts, and supervisor handoffs.
|
|
328
|
+
- Invalid workflows, unsafe worktree launches, and blocked tool budgets now fail earlier with clearer results.
|
|
329
|
+
- Linked worktrees, Windows supervisor polling, source-layout runners, and Orca progress tabs are more reliable.
|
|
330
|
+
|
|
331
|
+
### Added
|
|
332
|
+
|
|
333
|
+
- Add `subagents.defaultSubagentOnlyExtensions` for loading shared child-only extensions without disabling ambient extension discovery. Thanks to [@Shujakuinkuraudo](https://github.com/Shujakuinkuraudo) for #2284.
|
|
334
|
+
- Allow agent frontmatter and `subagents.agentOverrides.<name>.allowedAgents` to restrict which canonical agents a child may launch without granting delegation or widening capability ceilings. Thanks to [@shkrabov](https://github.com/shkrabov) for #2312.
|
|
335
|
+
|
|
336
|
+
### Changed
|
|
337
|
+
|
|
338
|
+
- Document `/subagent-cost` as the combined accounting view for parent and asynchronous child usage. Thanks to [@swarajban](https://github.com/swarajban) for #2313.
|
|
339
|
+
|
|
340
|
+
### Fixed
|
|
341
|
+
|
|
342
|
+
- Wake root `bg_wait` calls when an owned nested child is waiting on `contact_supervisor`. Thanks to [@geril07](https://github.com/geril07) for #2344.
|
|
343
|
+
- Keep explicitly detached workflow children visible, preserve their result lookup after the coordinator exits, and avoid treating launch receipts as completed results. Thanks to [@shaharmor](https://github.com/shaharmor) for #2299.
|
|
344
|
+
- Settle interrupted, stopped, or timed-out background runs even when child session creation hangs. Thanks to [@onorua](https://github.com/onorua) for #2320.
|
|
345
|
+
- Prevent concurrent workflow observers from overwriting retained-session startup confirmation and stranding resumed children. Thanks to [@luigiplr](https://github.com/luigiplr) for #2292.
|
|
346
|
+
- Let children use the tools declared by their own agent configuration instead of incorrectly narrowing them to the parent's `--tools` selection. Thanks to [@carlesba](https://github.com/carlesba) for #2289.
|
|
347
|
+
- Report foreground hard tool-budget blocks as `tool_budget_exhausted`, including calls blocked before execution starts. Thanks to [@kylerberry](https://github.com/kylerberry) for #2302.
|
|
348
|
+
- Keep permission forwarding scoped to the validated launch parent instead of sharing an identity between independent root sessions. Thanks to [@kasumikira](https://github.com/kasumikira) for #2321.
|
|
349
|
+
- Reject malformed inline and file-backed workflow scripts before creating asynchronous run state or launching children. Thanks to [@rtbe](https://github.com/rtbe) for #2309.
|
|
350
|
+
- Reject direct asynchronous managed-worktree launches from a dirty source before creating run state or returning a receipt. Thanks to [@rtbe](https://github.com/rtbe) for #2311.
|
|
351
|
+
- Avoid rejecting keyed property access after a mutable `runs.all(...)` result binding is reassigned.
|
|
352
|
+
- Report useful rooted field paths for failed structured-output `if`/`then`/`else` schemas while preserving root `$defs`. Thanks to [@peedrr](https://github.com/peedrr) for #2317.
|
|
353
|
+
- Give the bundled reviewer a bounded, read-only view of staged, unstaged, and untracked working-tree changes from its launch `HEAD`. Thanks to [@nateberkopec](https://github.com/nateberkopec) for #2306.
|
|
354
|
+
- Show the correct child transcript when inspecting an indexed asynchronous workflow step. Thanks to [@swarajban](https://github.com/swarajban) for #2304.
|
|
355
|
+
- Reconcile foreground and background child usage from terminal session messages when live usage events are missing or incomplete. Thanks to [@riique](https://github.com/riique) for #2295 and #2296.
|
|
356
|
+
- Keep project-scoped agent memory stable across linked Git worktrees. Thanks to [@freezscholte](https://github.com/freezscholte) for #2293.
|
|
357
|
+
- Keep Fleet workflow coverage stable during heartbeat, counter, and token updates without resetting an unchanged layout. Thanks to [@swarajban](https://github.com/swarajban) for #2305.
|
|
358
|
+
- Continue supervisor polling on Windows when a temporary channel directory disappears during a scan. Thanks to [@asher-aqi](https://github.com/asher-aqi) for #2303.
|
|
359
|
+
- Keep source-layout asynchronous runners on native Node TypeScript when child extensions are configured, with consistent peer-module resolution. Thanks to [@qsgy-edge](https://github.com/qsgy-edge) for #2314.
|
|
360
|
+
- Make Orca progress tabs work under `fish`. Thanks to [@yourfriendaaron](https://github.com/yourfriendaaron) for #2294.
|
|
361
|
+
- Prevent publishing the TypeScript source checkout directly to npm; only the compiled package is publishable. Thanks to [@niko-operal](https://github.com/niko-operal) for #2300.
|
|
362
|
+
|
|
363
|
+
## [0.69.0] - 2026-09-18
|
|
364
|
+
|
|
365
|
+
### Highlights
|
|
366
|
+
- Gates can now return a JSON verdict. Point `gate` at a script that prints JSON, and its output becomes the child's structured output, so workflows can branch on a post-run check without the parent reading the child's report.
|
|
367
|
+
- Ghostty detection no longer misfires inside terminals like cmux that embed Ghostty, so you stop seeing AppleScript `-1728`/`-2741` errors or the wrong window being targeted.
|
|
368
|
+
- Hosts without `npm` start up quietly instead of printing `npm: command not found`.
|
|
369
|
+
|
|
370
|
+
### Added
|
|
371
|
+
|
|
372
|
+
- Typed gates: `gate` accepts `{ command, output: "json", schema?, timeoutMs? }` alongside the plain string form. When the command passes, its JSON stdout becomes the child's `structuredOutput` (validated against `schema` when given). Empty, truncated, or invalid output fails the gate rather than silently dropping the verdict. Typed gates always run (they are never cached), and a run cannot combine one with an `outputSchema`. See `docs/` for using command-runner agents as typed workflow steps and `examples/typed-gate` for a runnable example.
|
|
373
|
+
|
|
374
|
+
### Fixed
|
|
375
|
+
|
|
376
|
+
- The Ghostty inspector only activates when the macOS host bundle id identifies the standalone Ghostty app. Terminals that embed Ghostty (such as cmux) set `TERM_PROGRAM=ghostty` too, which previously targeted an unrelated Ghostty window or emitted `-1728`/`-2741` AppleScript errors; those hosts now fall back to the `inspector.command` hint. Thanks to [@wangpi26](https://github.com/wangpi26) for #2281.
|
|
377
|
+
- Hosts without `npm` no longer print `/bin/sh: npm: command not found` during startup; global package-root discovery is optional and now stays silent when the package manager is missing. Thanks to [@PhrZer](https://github.com/PhrZer) for #2287.
|
|
378
|
+
- Fixed `docs/tool-reference.md`, which claimed a default `maxOutput` cap of 200 KB / 5,000 lines. The cap applies only when `maxOutput` is set.
|
|
379
|
+
|
|
151
380
|
## [0.68.0] - 2026-09-15
|
|
152
381
|
|
|
153
382
|
### Highlights
|
|
@@ -155,7 +384,7 @@
|
|
|
155
384
|
- Reuse workflow scripts with different JSON inputs, including scheduled runs.
|
|
156
385
|
- Start npm-installed children much faster and let slow local models use Pi's configured HTTP timeout.
|
|
157
386
|
- Keep local foreground children on the same extension-provided models as their parent without sharing provider state between sessions.
|
|
158
|
-
-
|
|
387
|
+
- Ask async agents to checkpoint before a hard deadline, giving long-running work a chance to return useful progress instead of being killed.
|
|
159
388
|
|
|
160
389
|
### Added
|
|
161
390
|
|
|
@@ -180,6 +409,9 @@
|
|
|
180
409
|
|
|
181
410
|
### Fixed
|
|
182
411
|
|
|
412
|
+
- Fail managed worktree setup before child launch when a required shared `node_modules` link cannot be created and verified, while preserving absent sources and preexisting destinations (#2283).
|
|
413
|
+
- Allow checked writers to explicitly preserve a host-bound staged index while still rejecting child-created index changes (#2280).
|
|
414
|
+
|
|
183
415
|
- Preserve the main watchdog's user scope across session compaction while clearing temporary activity state. Thanks to [@nimeetshah0](https://github.com/nimeetshah0) for #2263.
|
|
184
416
|
- Resolve provider-extension models in local, in-process foreground children. Such a child never loads the parent's ambient extensions, so its model runtime only knew Pi's built-in providers and every model from an extension-registered provider failed with `Model "…" not found`; the child now inherits the providers registered in the parent session before resolving its model. Pane-native remote foreground children continue to use the remote machine's provider discovery and configuration. Builtin agents on such a model no longer need `async: true`. Thanks to [@lallenlowe](https://github.com/lallenlowe) for #2274.
|
|
185
417
|
- Preserve a readable async result when result indexing or archiving fails, then retry saving it without delivering it twice. Thanks to [@shaharmor](https://github.com/shaharmor) for #2267 and #2266.
|
package/README.md
CHANGED
|
@@ -14,7 +14,7 @@
|
|
|
14
14
|
pi install npm:@xzzpig/pi-subagents
|
|
15
15
|
```
|
|
16
16
|
|
|
17
|
-
That is the only required step. Background children use the host's SDK: npm Pi keeps its detached Node runner; the official Pi 0.
|
|
17
|
+
That is the only required step. Background children use the host's SDK: npm Pi keeps its detached Node runner; the official Pi 0.86.1 Linux x64 standalone release loads the same runner through Pi's embedded SDK, without a separate SDK install. See [Standalone background execution](docs/standalone-background.md) for the supported boundary and validation gate.
|
|
18
18
|
|
|
19
19
|
## Try this first
|
|
20
20
|
|
|
@@ -44,7 +44,9 @@ Pi is the parent session. A subagent is a focused child Pi session with its own
|
|
|
44
44
|
|
|
45
45
|
When you ask for a subagent, Pi starts the child, gives it the task, and brings the result back. Foreground children run as sessions inside the parent Pi process and stream in the conversation. Background children run as sessions inside a detached runner process that keeps working and can be checked later.
|
|
46
46
|
|
|
47
|
-
Installing the extension does not start an automatic reviewer in the background.
|
|
47
|
+
Installing the extension does not start an automatic reviewer in the background. When the session's model can take a new tool mid-conversation, fresh parent sessions initially expose the small `subagents_enable` loader instead of the full `subagent` schema. When your request or applicable instructions authorize delegation, Pi can call the loader itself; the unchanged `subagent` tool is available on the next model request. With other models, fresh sessions start with `subagent` active, because adding a tool later would make the provider miss its prompt cache. The [`toolActivation`](docs/configuration.md#toolactivation) setting changes this. Complexity alone does not authorize delegation. `bg_wait` and supervisor replies remain available without activation.
|
|
48
|
+
|
|
49
|
+
If you want every implementation reviewed, say so in your prompt or project instructions:
|
|
48
50
|
|
|
49
51
|
```text
|
|
50
52
|
When you finish implementing, run a reviewer subagent before summarizing.
|
|
@@ -112,7 +114,7 @@ For bounded orchestration, `maxSubagentSpawnsPerRun` limits cumulative logical c
|
|
|
112
114
|
|
|
113
115
|
or ask: "Check whether subagents and intercom are set up correctly."
|
|
114
116
|
|
|
115
|
-
For installed-version help, use `/subagents-guide [topic]` or `subagent({ action: "guide", topic: "workflows" })`. The default topic is `overview`; available topics are `overview`, `workflows`, `agents`, `missions`, `observability`, `tool-reference`, `configuration`, `models`, `watchdog`,
|
|
117
|
+
For installed-version help, use `/subagents-guide [topic]` or `subagent({ action: "guide", topic: "workflows" })`. The default topic is `overview`; available topics are `overview`, `workflows`, `agents`, `missions`, `observability`, `tool-reference`, `configuration`, `models`, `watchdog`, `extension-api`, and `council`.
|
|
116
118
|
|
|
117
119
|
## Documentation
|
|
118
120
|
|
package/agents/reviewer.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: reviewer
|
|
3
3
|
description: Versatile review specialist for code diffs, plans, proposed solutions, codebase health, and PR/issue validation
|
|
4
|
-
tools: read, grep, find, ls, contact_supervisor
|
|
4
|
+
tools: read, grep, find, ls, watchdog_diff, contact_supervisor
|
|
5
5
|
thinking: high
|
|
6
6
|
systemPromptMode: replace
|
|
7
7
|
inheritProjectContext: true
|
|
@@ -53,7 +53,8 @@ Review a PR or issue by understanding the context, then verifying:
|
|
|
53
53
|
- Start from the exact diff and named source seam for code-behavior review. Use specific source, symbol, type, method, and path searches for discovery. Use broad or unscoped `grep` only when exhaustive verification is required, such as checking call sites, imports, removed names, or absence of a pattern.
|
|
54
54
|
- Read the relevant files first. Read plan and progress when the task supplies them.
|
|
55
55
|
- Repo-local `progress.md` files are allowed scratch/memory files. Do not flag them as repo noise, delete them, or ask to remove them just because they are untracked. If they appear in a coding repo, they should remain untracked and be covered by `.gitignore`.
|
|
56
|
-
-
|
|
56
|
+
- Use `watchdog_diff` to inspect the bounded staged and unstaged working-tree delta against reviewer-launch `HEAD`, plus the bounded untracked-path inventory. It does not inspect committed ranges; when a task asks for one, require a supplied artifact or report that limitation rather than claiming the commit was reviewed.
|
|
57
|
+
- Do not use shell commands, mutate the repository, or request general Git access. Report any test command that a supervisor must run.
|
|
57
58
|
- Do not invent issues. Only report problems you can justify from evidence.
|
|
58
59
|
- Prefer small corrective edits over broad rewrites.
|
|
59
60
|
- If everything looks good, say so plainly.
|
package/agents/worker.md
CHANGED
|
@@ -2,12 +2,13 @@
|
|
|
2
2
|
name: worker
|
|
3
3
|
description: Implementation agent for normal tasks and approved oracle handoffs
|
|
4
4
|
aliases: developer, coder, implementer, develop
|
|
5
|
+
acceptanceRole: writer
|
|
5
6
|
thinking: high
|
|
6
7
|
systemPromptMode: replace
|
|
7
8
|
inheritProjectContext: true
|
|
8
9
|
inheritSkills: false
|
|
9
10
|
tools: read, grep, find, ls, bash, edit, write, contact_supervisor
|
|
10
|
-
defaultContext:
|
|
11
|
+
defaultContext: fresh
|
|
11
12
|
defaultReads: context.md, plan.md
|
|
12
13
|
defaultProgress: true
|
|
13
14
|
---
|
|
@@ -16,7 +17,7 @@ You are `worker`: the implementation subagent.
|
|
|
16
17
|
|
|
17
18
|
You are the single writer thread. Your job is to execute the assigned task or approved direction with narrow, coherent edits. The main agent and user remain the decision authority.
|
|
18
19
|
|
|
19
|
-
Use the provided tools directly. First read the
|
|
20
|
+
Use the provided tools directly. First read the provided context, supplied files, plan, task paths, and named seams. Then implement carefully and minimally. Use broad search only to verify or expand from that starting point.
|
|
20
21
|
|
|
21
22
|
The builtin worker uses a strict tool allowlist. It does not inherit ambient extension tools from the parent session. To use an extension tool, configure a custom agent with the tool name explicitly listed in `tools` and load its provider through `extensions` or `subagentOnlyExtensions`.
|
|
22
23
|
|