@xzzpig/pi-subagents 0.14.0 → 0.15.0
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 -0
- package/README.md +6 -5
- package/agents/evidence-auditor.md +34 -0
- package/agents/researcher.md +23 -13
- package/agents/reviewer.md +3 -2
- package/docs/agents.md +56 -15
- package/docs/configuration.md +92 -14
- package/docs/extension-api.md +132 -19
- package/docs/missions.md +10 -2
- package/docs/models.md +11 -22
- package/docs/observability.md +63 -11
- package/docs/standalone-background.md +59 -0
- package/docs/tool-reference.md +42 -23
- package/docs/watchdog.md +39 -10
- package/docs/workflows.md +58 -19
- package/index.ts +5 -2
- package/inspector-runner.mjs +2 -2
- package/node_modules/@xzzpig/pi-components/dist/src/transcript.d.ts +13 -3
- package/node_modules/@xzzpig/pi-components/dist/src/transcript.js +18 -6
- package/node_modules/@xzzpig/pi-components/src/transcript.ts +26 -6
- package/package.json +9 -4
- package/prompts/parallel-review.md +1 -1
- package/runner-peer-loader.mjs +24 -0
- package/runner-peer-preload.mjs +36 -0
- package/skills/pi-subagents/SKILL.md +34 -22
- package/skills/pi-subagents/references/constraints-and-recipes.md +3 -2
- package/skills/pi-subagents/references/execution-controls.md +27 -8
- package/skills/pi-subagents/references/management-authoring-rpc.md +2 -2
- package/skills/pi-subagents/references/multi-lane-orchestration.md +3 -1
- package/skills/pi-subagents/references/prompting-and-roles.md +17 -13
- package/skills/pi-subagents/references/review-and-validation.md +3 -3
- package/src/agents/advertised-agent-prompt.ts +94 -0
- package/src/agents/agent-management.ts +71 -59
- package/src/agents/agent-serializer.ts +6 -3
- package/src/agents/agents.ts +198 -72
- package/src/agents/builtin-names.ts +1 -0
- package/src/agents/chain-serializer.ts +5 -0
- package/src/agents/runtime-agent-registry.ts +7 -6
- package/src/api/delegation.ts +4 -0
- package/src/api/preflight.ts +110 -71
- package/src/api/required-child-extensions.ts +6 -0
- package/src/api/shared-types.ts +3 -1
- package/src/api/workflow-resources.ts +6 -0
- package/src/extension/config.ts +14 -37
- package/src/extension/fanout-child.ts +68 -5
- package/src/extension/herdr-pi-bridge.ts +164 -0
- package/src/extension/index.ts +141 -51
- package/src/extension/public-execution.ts +7 -6
- package/src/extension/rpc.ts +8 -21
- package/src/extension/schemas.ts +86 -84
- package/src/extension/tool-description.ts +32 -79
- package/src/inspectors/actions.ts +148 -0
- package/src/inspectors/ghostty/actions.ts +74 -0
- package/src/inspectors/ghostty/plugin.ts +17 -0
- package/src/inspectors/herdr/actions.ts +99 -179
- package/src/inspectors/herdr/plugin.ts +20 -0
- package/src/inspectors/herdr/project-panes.ts +4 -1
- package/src/inspectors/{herdr/inspector-runner.ts → inspector-runner.ts} +12 -12
- package/src/inspectors/plugins.ts +8 -0
- package/src/inspectors/{herdr/session-roots-codec.ts → session-roots-codec.ts} +3 -14
- package/src/inspectors/types.ts +51 -0
- package/src/integrations/pi-web-session-liveness.ts +73 -0
- package/src/intercom/intercom-bridge.ts +50 -8
- package/src/intercom/native-supervisor-channel.ts +142 -115
- package/src/intercom/supervisor-ui.ts +3 -2
- package/src/missions/workflow-state.ts +37 -16
- package/src/policy/authority.ts +4 -0
- package/src/profiles/profiles.ts +12 -6
- package/src/runs/background/active-async-capacity.ts +22 -18
- package/src/runs/background/active-run-index.ts +17 -1
- package/src/runs/background/async-execution.ts +359 -176
- package/src/runs/background/async-job-tracker.ts +41 -7
- package/src/runs/background/async-resume.ts +19 -12
- package/src/runs/background/async-retention.ts +20 -0
- package/src/runs/background/async-status-snapshot.ts +10 -12
- package/src/runs/background/async-status.ts +32 -13
- package/src/runs/background/auto-drain.ts +59 -35
- package/src/runs/background/binary-bootstrap.ts +38 -0
- package/src/runs/background/chain-append.ts +1 -1
- package/src/runs/background/chain-root-attachment.ts +22 -33
- package/src/runs/background/control-channel.ts +78 -44
- package/src/runs/background/fleet-view.ts +30 -2
- package/src/runs/background/notify.ts +193 -19
- package/src/runs/background/owned-process-tree.ts +35 -8
- package/src/runs/background/process-terminal.ts +23 -23
- package/src/runs/background/result-files.ts +8 -4
- package/src/runs/background/result-watcher.ts +19 -2
- package/src/runs/background/retained-nested-route-tracker.ts +96 -0
- package/src/runs/background/run-child-session.ts +118 -41
- package/src/runs/background/run-status.ts +78 -5
- package/src/runs/background/runner-aliases.ts +22 -5
- package/src/runs/background/runner-child-launch.ts +93 -0
- package/src/runs/background/runner-child-sessions.ts +5 -4
- package/src/runs/background/runner-http-dispatcher.ts +119 -0
- package/src/runs/background/scheduled-runs.ts +51 -18
- package/src/runs/background/stale-run-reconciler.ts +38 -12
- package/src/runs/background/steering.ts +20 -2
- package/src/runs/background/subagent-runner.ts +766 -432
- package/src/runs/background/subagent-wait.ts +179 -28
- package/src/runs/background/wait-completions.ts +79 -27
- package/src/runs/background/wait-subscriptions.ts +9 -3
- package/src/runs/background/wait-tool.ts +5 -3
- package/src/runs/foreground/async-steering-action.ts +37 -7
- package/src/runs/foreground/async-stop-action.ts +93 -3
- package/src/runs/foreground/execution.ts +174 -194
- package/src/runs/foreground/foreground-history.ts +5 -2
- package/src/runs/foreground/prompt-audit.ts +12 -6
- package/src/runs/foreground/subagent-executor.ts +896 -397
- package/src/runs/foreground/workflow-detach-reconcile.ts +10 -5
- package/src/runs/foreground/workflow-foreground-steering.ts +57 -2
- package/src/runs/shared/acceptance.ts +54 -14
- package/src/runs/shared/agent-contract.ts +1 -1
- package/src/runs/shared/async-status-projection.ts +172 -78
- package/src/runs/shared/capability-ceiling.ts +2 -0
- package/src/runs/shared/child-hooks.ts +167 -3
- package/src/runs/shared/child-launch-plan.ts +15 -3
- package/src/runs/shared/child-launch.ts +44 -16
- package/src/runs/shared/child-lifecycle.ts +6 -3
- package/src/runs/shared/child-runtime-config.ts +8 -1
- package/src/runs/shared/child-session.ts +130 -24
- package/src/runs/shared/child-tool-plan.ts +145 -14
- package/src/runs/shared/completion-evidence.ts +2 -2
- package/src/runs/shared/completion-guard.ts +6 -3
- package/src/runs/shared/dynamic-fanout.ts +2 -2
- package/src/runs/shared/effective-system-prompt.ts +33 -0
- package/src/runs/shared/external-cli-contract.ts +11 -1
- package/src/runs/shared/external-cli-preflight.ts +6 -2
- package/src/runs/shared/external-cli-runner.ts +9 -7
- package/src/runs/shared/herdr-connection.ts +134 -0
- package/src/runs/shared/herdr-external-adapters.ts +169 -0
- package/src/runs/shared/herdr-machine.ts +279 -0
- package/src/runs/shared/herdr-pi-protocol.ts +59 -0
- package/src/runs/shared/herdr-placed-run.ts +263 -0
- package/src/runs/shared/host-step-status.ts +11 -11
- package/src/runs/shared/llm-intent-arbiter.ts +40 -21
- package/src/runs/shared/model-resolution-diagnostic.ts +76 -0
- package/src/runs/shared/{model-fallback.ts → model-resolution.ts} +34 -218
- package/src/runs/shared/model-scope.ts +1 -1
- package/src/runs/shared/nested-events.ts +19 -10
- package/src/runs/shared/orca-progress-tabs.ts +7 -1
- package/src/runs/shared/parallel-handoff.ts +57 -12
- package/src/runs/shared/parallel-utils.ts +10 -4
- package/src/runs/shared/pi-spawn.ts +10 -0
- package/src/runs/shared/readonly-drain-observation.ts +42 -0
- package/src/runs/shared/run-fanout-budget.ts +8 -8
- package/src/runs/shared/runtime-acknowledged-extensions.ts +3 -3
- package/src/runs/shared/subagent-prompt-runtime.ts +23 -5
- package/src/runs/shared/task-intent.ts +46 -13
- package/src/runs/shared/workflow-async-child-guidance.ts +18 -0
- package/src/runs/shared/worktree-cleanup-plan.ts +6 -3
- package/src/runs/shared/worktree-setup-command.ts +213 -0
- package/src/runs/shared/worktree.ts +437 -214
- package/src/shared/child-cache-retention.ts +43 -0
- package/src/shared/fork-context.ts +15 -72
- package/src/shared/launch-contract.ts +70 -8
- package/src/shared/model-response-aliases.ts +13 -0
- package/src/shared/opencode-session-headers.ts +30 -0
- package/src/shared/pruned-fork.ts +1 -1
- package/src/shared/required-child-extensions.ts +81 -0
- package/src/shared/settings.ts +5 -2
- package/src/shared/shortcuts.ts +0 -4
- package/src/shared/types.ts +163 -90
- package/src/shared/utils.ts +10 -2
- package/src/shared/watch-strategy.ts +2 -0
- package/src/shared/workflow-child-permit.ts +18 -13
- package/src/slash/delegation-adapters.ts +3 -1
- package/src/slash/delegation-request.ts +14 -0
- package/src/slash/slash-commands.ts +2 -7
- package/src/slash/subagents-admin.ts +31 -14
- package/src/tui/fleet-status.ts +165 -20
- package/src/tui/fleet.ts +30 -19
- package/src/tui/render.ts +210 -50
- package/src/watchdog/child-status.ts +28 -28
- package/src/watchdog/lsp-diagnostics.ts +1 -1
- package/src/watchdog/model-selection.ts +21 -1
- package/src/watchdog/permission-arbiter.ts +5 -2
- package/src/watchdog/register-child.ts +10 -2
- package/src/watchdog/register-main.ts +39 -35
- package/src/watchdog/render.ts +1 -1
- package/src/watchdog/review.ts +122 -74
- package/src/watchdog/rules.ts +1 -1
- package/src/watchdog/runtime.ts +100 -27
- package/src/watchdog/scope.ts +1 -1
- package/src/watchdog/settings.ts +3 -0
- package/src/watchdog/tool-actions.ts +13 -12
- package/src/watchdog/turn-delta.ts +23 -0
- package/src/watchdog/types.ts +5 -3
- package/src/watchdog/warning-format.ts +1 -1
- package/src/workflows/chat-progress.ts +3 -3
- package/src/workflows/scripted-workflow.ts +349 -26
- package/src/workflows/workflow-checklist.ts +17 -20
- package/src/workflows/workflow-child-summary.ts +57 -8
- package/src/workflows/workflow-preflight.ts +19 -19
- package/src/workflows/workflow-receipt.ts +24 -6
- package/src/workflows/workflow-resources.ts +108 -22
- package/src/workflows/workflow-settlement.ts +3 -0
- package/src/runs/shared/model-exclusions.ts +0 -373
- /package/src/inspectors/{herdr/shell-command.ts → shell-command.ts} +0 -0
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,13 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## [0.15.0] - 2026-09-17
|
|
4
|
+
|
|
5
|
+
### Changed
|
|
6
|
+
|
|
7
|
+
- **Synced to upstream v0.68.0 (adopted upstream removal of automatic model switching).** The upstream architecture no longer retries a different model within the same launch (`fallbackModels`), continues read-only HTTP 429 work on a different model, or persists model exclusions; each launch now resolves exactly one model and retries that same model at most twice. The fork adopts that removal wholesale while keeping its sandbox-profile, permission-profile, context-injection, silent-span, ejectable-agent, and fleet-native-transcript features on top.
|
|
8
|
+
- **Pane-native remote Pi placement (Herdr) is now part of the fork.** Upstream v0.68.0 adds running subagents on saved remote machines via Herdr panes, consolidates `src/inspectors/herdr/` into `src/inspectors/`, and splits the async execution tests into part files; the fork keeps its own `openSubagentFleetFromStatus` wrapper with an `inspectorPlugins` passthrough.
|
|
9
|
+
- Test fixtures were adapted for the fork's own version number (the bridge identity check compares `packageVersion` to the fork's package version) and for NixOS hosts where `/usr/bin`/`/bin` are not FHS-populated (mock `mktemp`/`rm`/`cat` are supplied in the deterministic remote PATH and the deterministic-PATH assertion tolerates host-injected suffixes).
|
|
10
|
+
|
|
3
11
|
## [0.14.0] - 2026-09-13
|
|
4
12
|
|
|
5
13
|
### Fixed
|
|
@@ -120,6 +128,231 @@
|
|
|
120
128
|
|
|
121
129
|
## [0.7.0] - 2026-08-24
|
|
122
130
|
|
|
131
|
+
## [0.68.0] - 2026-09-15
|
|
132
|
+
|
|
133
|
+
### Highlights
|
|
134
|
+
- Run Pi, Claude Code, Codex, and Cursor subagents on saved remote machines through Herdr.
|
|
135
|
+
- Reuse workflow scripts with different JSON inputs, including scheduled runs.
|
|
136
|
+
- Start npm-installed children much faster and let slow local models use Pi's configured HTTP timeout.
|
|
137
|
+
- Keep local foreground children on the same extension-provided models as their parent without sharing provider state between sessions.
|
|
138
|
+
- Get simpler, more predictable failures: each launch uses one resolved model instead of switching models automatically.
|
|
139
|
+
|
|
140
|
+
### Added
|
|
141
|
+
|
|
142
|
+
- Accept bounded JSON `args` for inline, file-backed, validated, and scheduled workflow scripts. Scripts receive immutable arguments, and schedules retain them for later runs (#2233).
|
|
143
|
+
- Left-click the async widget header in mouse-enabled Pi fullscreen mode to fold it into a live status summary and unfold it again, independently of global tool expansion. Progress updates preserve the fold state; run execution and notifications are unchanged. Thanks to [@pstanton237](https://github.com/pstanton237) for #2235.
|
|
144
|
+
- Allow agents to declare an inline JSON Schema `outputSchema` default, with launch objects overriding it and explicit `false` opting out. Thanks to [@peedrr](https://github.com/peedrr) for #2180.
|
|
145
|
+
- Add `PI_SUBAGENT_CACHE_RETENTION` to set a prompt-cache retention tier for child sessions only, so a parent on the 1h tier can keep children on the cheaper-to-write 5m tier they are too short-lived to benefit from. Unset by default, leaving children on the parent's retention. Spawned children take it through the launch environment; in-process children pin it per request on their own session rather than on shared process state. Thanks to [@johnwards](https://github.com/johnwards) for #2190.
|
|
146
|
+
- Add a session-scoped host API for extensions that every native child must load. Required extensions survive agent overrides and nested launches, and child startup fails clearly when one is denied or cannot load. Thanks to [@gkoreli](https://github.com/gkoreli) for #2153.
|
|
147
|
+
- Run Pi, Claude Code, Codex, and Cursor subagents on another computer by setting `machine` to a saved Herdr machine.
|
|
148
|
+
- Add `checkpointBeforeDeadlineMs` for async single-agent runs. It asks the child to checkpoint and stop before the hard `timeoutMs` deadline; without it, timeout behavior is unchanged. Thanks to [@freezscholte](https://github.com/freezscholte) for #2141.
|
|
149
|
+
- Add `subagents.agentExcludeDirs` to exclude directory trees from agent discovery, including nested plugin sources and symlink aliases. Thanks to [@xarillian](https://github.com/xarillian) for #2131.
|
|
150
|
+
|
|
151
|
+
### Changed
|
|
152
|
+
|
|
153
|
+
- Add `inspectorOpen` and `projectOpen` to `authorityPolicy`. Inspector opening remains automatic by default, while project opening now asks for confirmation because it starts Herdr and opens another Pi session. Set `"projectOpen": "auto"` to restore unprompted project opening. The Fleet TUI is unchanged. Thanks to [@kevthedawg](https://github.com/kevthedawg) for #2269.
|
|
154
|
+
- Ship compiled JavaScript in the npm package so Pi no longer transpiles the extension and detached runner when they load. On the reported cold-start path, the extension entry loaded in about 226 ms instead of 2,831 ms. Thanks to [@821869798](https://github.com/821869798) for #2248.
|
|
155
|
+
|
|
156
|
+
### Removed
|
|
157
|
+
|
|
158
|
+
- Remove `fallbackModels`, all same-launch model switching (including read-only HTTP 429 continuation), and persistent model exclusions. Retry another model only with a later explicit launch; guarded retained-session compaction recovery may continue once on the already resolved model.
|
|
159
|
+
- Drop the bundled `@earendil-works/pi-server` copy that filled in the dependency Pi 0.85.0 forgot to ship. Background children on a Pi 0.85.0 host now fail to launch with a clear error; upgrade to Pi 0.85.1 or newer, which ships the package itself. Foreground children on 0.85.0 are unaffected.
|
|
160
|
+
|
|
161
|
+
### Fixed
|
|
162
|
+
|
|
163
|
+
- Preserve the main watchdog's user scope across session compaction while clearing temporary activity state. Thanks to [@nimeetshah0](https://github.com/nimeetshah0) for #2263.
|
|
164
|
+
- 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.
|
|
165
|
+
- 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.
|
|
166
|
+
- Honor `PI_SUBAGENTS_PI_CODING_AGENT_PACKAGE_ROOT` for background children, fixing launches from wrapper installs and other non-standard Pi layouts. Thanks to [@Yaphet2015](https://github.com/Yaphet2015) for #2254.
|
|
167
|
+
- Keep a foreground child's report available when acceptance rejects saved output instead of replacing it with only a file reference. Thanks to [@pgoodjohn](https://github.com/pgoodjohn) for #2255.
|
|
168
|
+
- Add the ambient-extension rule to Pi's model-not-found error when a child's model comes from an extension-registered provider that was not loaded for it: a foreground child now reports that agents needing a provider extension's models must run as background children (`async: true`) or load the extension explicitly through `subagentOnlyExtensions`/`extensions`, and a background child launched without the ambient extensions gets the matching remedies. When `capabilityCeiling.denyExtensions` blocks every extension, both hosts report the policy instead of remedies the ceiling discards. The core error, exit code, and failure detection are unchanged. Thanks to [@pwguler](https://github.com/pwguler) for #2240.
|
|
169
|
+
- Remote Herdr bridge discovery no longer blocks the parent session while waiting for the remote Pi to start.
|
|
170
|
+
- Recognize Windows Bun virtual entrypoints when launching standalone background children, retaining the existing Linux and npm paths. Windows coverage remains experimental; see `docs/standalone-background.md`. Thanks to [@JohnsonRan](https://github.com/JohnsonRan) for #2241.
|
|
171
|
+
- Keep supervisor progress updates out of parent model turns while still waking for decisions and structured questions. Thanks to [@moofone](https://github.com/moofone) for #2229 and [@dajiaohuang](https://github.com/dajiaohuang) for #2230.
|
|
172
|
+
- Keep routine successful child updates out of parent model turns, and wake the parent when saving an async workflow result fails. Thanks to [@moofone](https://github.com/moofone) for #2262.
|
|
173
|
+
- Start background cleanup, wait reconciliation, and retention timers with the session and clear them during shutdown. Thanks to [@freezscholte](https://github.com/freezscholte) for #2244.
|
|
174
|
+
- Apply Pi's `httpIdleTimeoutMs` setting to the detached async runner's HTTP dispatcher on both the Node and standalone binary host launch paths (project `.pi/settings.json` over `~/.pi/agent/settings.json`, `0` disables; an invalid value warns and falls back to 300s). The runner previously kept undici's 300s header/body defaults, so async children against a slow local model were cut at about five minutes while foreground children waited as configured. Thanks to [@JordiPosthumus](https://github.com/JordiPosthumus) for the incident analysis in #2199.
|
|
175
|
+
- Restore direct parent ownership as the default. The bundled skill delegates only when the operator asks; complexity alone no longer starts child workflows. Thanks to [@AlexDochioiu](https://github.com/AlexDochioiu) for #2216.
|
|
176
|
+
- Stop external runs from leaving Windows worktrees locked by Git fsmonitor processes after cancellation (#2207 recurrence).
|
|
177
|
+
- Include each agent's acceptance policy and role in `capabilities: true` results. Thanks to [@Alice39s](https://github.com/Alice39s) for #2210.
|
|
178
|
+
- Recover when a parent workflow's previous checkout directory was removed before another child starts. Thanks to [@trewwwsec](https://github.com/trewwwsec) for #2211.
|
|
179
|
+
- Keep resumed-run startup non-blocking and fail clearly when the runner exits before it is ready. Thanks to [@qsgy-edge](https://github.com/qsgy-edge) for #2219.
|
|
180
|
+
- Prefer exact agent names over packaged short-name matches, and never treat home-level agent directories as project configuration. This prevents names such as `scout` and `code-analysis.scout` from becoming ambiguous. Thanks to [@ton77v](https://github.com/ton77v) for #2214.
|
|
181
|
+
- Avoid Jiti for native async runner startup on supported Node versions. Thanks to [@qsgy-edge](https://github.com/qsgy-edge) for #2220.
|
|
182
|
+
- Stop registering and advertising a default global `Ctrl+Alt+F` Fleet shortcut; `/subagents-fleet` and FleetView remain available. Thanks to [@miaomiaozii](https://github.com/miaomiaozii) for #2196.
|
|
183
|
+
- Require low, medium, or high importance on watchdog findings. Low and medium stay visible to the user without entering model context; high findings still reach the model (#2201).
|
|
184
|
+
- Let headless parents and nested coordinators answer blocking child questions without deadlocking shutdown. Thanks to [@ProDrifterDK](https://github.com/ProDrifterDK) for #2185.
|
|
185
|
+
- Keep nested stop, interrupt, and timeout propagation inside the issuing run's descendant subtree while preserving root-wide controls. Thanks to [@freezscholte](https://github.com/freezscholte) for #2243.
|
|
186
|
+
- Keep read-only reviews free of implementation acceptance requirements when their topic mentions releases, migrations, or security. Explicit acceptance and write tasks are unchanged. Thanks to [@qsgy-edge](https://github.com/qsgy-edge) for #2191.
|
|
187
|
+
- Include async result, output, and structured-output paths in completion notices. Thanks to [@peedrr](https://github.com/peedrr) for #2181.
|
|
188
|
+
- Remove one-shot workflow result files and their indexes after successful consumption. Thanks to [@peedrr](https://github.com/peedrr) for #2182.
|
|
189
|
+
- Show runtime-registered agents in `/subagents` while keeping their extension-owned definitions read-only and rejecting collisions with disabled configured agents. Thanks to [@mystery4f](https://github.com/mystery4f) for #2169.
|
|
190
|
+
- Save readable JSON to configured background output files when a successful child returns structured output without final prose. Thanks to [@rtbe](https://github.com/rtbe) for #2163.
|
|
191
|
+
- Surface the provider error text of a failed watchdog review in `/subagents-watchdog status` `Last error` (bounded to 600 chars). Previously only `stop reason 'error'` was recorded, so a watchdog failing every review (rate limit, rejected model, auth) was indistinguishable from a clean one. Thanks to [@freezscholte](https://github.com/freezscholte) for #2166.
|
|
192
|
+
- Finalize paused async runs after the runner has actually stopped, while keeping them resumable until then. Thanks to [@neruok](https://github.com/neruok) for #2170.
|
|
193
|
+
- Keep explicitly stopped aggregate children non-resumable while allowing completed siblings to resume. Thanks to [@freezscholte](https://github.com/freezscholte) for #2242.
|
|
194
|
+
- Group workflow children under their status rows without duplicate entries and show reliable completion times. Thanks to [@niko-operal](https://github.com/niko-operal) for #2168.
|
|
195
|
+
- Refresh external-run activity from stdout, stderr, and Git changes without repeatedly polling Git. Thanks to [@DeLuke84](https://github.com/DeLuke84) for #2167.
|
|
196
|
+
- Remove expired partial and rejected jobs from the widget while preserving live nested children. Thanks to [@ashlineldridge](https://github.com/ashlineldridge) for #2159.
|
|
197
|
+
- Reject unsupported bare acceptance strings at the provider schema boundary while preserving shorthand levels and JSON-encoded acceptance objects. Thanks to [@vrolok](https://github.com/vrolok) for #2152.
|
|
198
|
+
- Let Pi finish automatic compaction without an extra extension resume while preserving manual continuation for active async work. Thanks to [@mxp7064](https://github.com/mxp7064) for #2144.
|
|
199
|
+
- Preserve wrapped Pi core tools and explicitly requested non-core tools in child launches. Core slots still respect host availability; non-core tools are validated in the child's runtime after ceilings and exclusions (#2132, #2133, #2134, #2135, #2140). Thanks to [@carlesba](https://github.com/carlesba) for #2137 and [@clementprevot](https://github.com/clementprevot) for #2138.
|
|
200
|
+
|
|
201
|
+
## [0.67.0] - 2026-09-10
|
|
202
|
+
|
|
203
|
+
### Highlights
|
|
204
|
+
- Launch previews now match what actually runs, including Intercom and prompt and tool customization.
|
|
205
|
+
- Parallel workflows are easier to write and follow, with natural promise composition and per-child completion updates.
|
|
206
|
+
- Child-facing tool instructions use less context, leaving more of the token budget available for the task itself.
|
|
207
|
+
- Steering, follow-ups, resumed work, and detached processes finish more reliably.
|
|
208
|
+
- FleetView and workflow status are clearer, with better grouping, timing, usage, and colors.
|
|
209
|
+
|
|
210
|
+
### Added
|
|
211
|
+
- Add optional watchdog fallback models for the main session, children, and individual agents. Fallback happens only for provider failures before tool use and within the existing review timeout. Thanks to [@dwizzle204](https://github.com/dwizzle204) for #2075.
|
|
212
|
+
- Add portable Inspect commands and a terminal-neutral integration point, including open-only Ghostty 1.3+ right splits on macOS. Thanks to [@tiratatp](https://github.com/tiratatp) for #2046.
|
|
213
|
+
- Add `quiet: true` for recurring schedules. Successful automatic runs stay visible without waking the parent; failures, stops, and pauses still wake it. One-shot and manually started schedules remain noisy unless explicitly made quiet. Thanks to [@pablontiv](https://github.com/pablontiv) for #2055.
|
|
214
|
+
- Add optional watchdog questions that flag possible task drift before a main-session change finishes (#2010).
|
|
215
|
+
- Add the built-in `evidence-auditor` for checking whether important research claims are supported by their sources. Thanks to [@Muskos](https://github.com/Muskos) for #2023.
|
|
216
|
+
- Notify the parent as each asynchronous workflow child finishes instead of waiting for every sibling. Notifications include the workflow, child, outcome, and result location (#2027).
|
|
217
|
+
- Add per-launch `intercomBridge` overrides to delegation and preflight, plus `orchestratorTarget` for custom bridge templates that name the parent. Invalid overrides now fail clearly (#2127). Thanks to [@Yivas](https://github.com/Yivas) for the instrumented reproduction.
|
|
218
|
+
|
|
219
|
+
### Changed
|
|
220
|
+
- Make the default Intercom bridge prompt independent of the parent session while preserving `{orchestratorTarget}` in custom templates. Launch contracts are now version 3 and launch-binding projections version 2, so launch-contract digests change in this release; existing saved runs still resume (#2127). Thanks to [@Yivas](https://github.com/Yivas) for the instrumented reproduction.
|
|
221
|
+
- Include removed child tools and their active restrictions in launch warnings without changing launch behavior. Follow-up for #2058.
|
|
222
|
+
- Shorten the default child-facing instructions while keeping the full typed API and detailed guides. Thanks to [@Whamp](https://github.com/Whamp) for the prompt-footprint measurements and proposal in #2048.
|
|
223
|
+
- Give FleetView agents stable identity colors. Thanks to [@savinofiore](https://github.com/savinofiore) for #2056.
|
|
224
|
+
- Preserve a forked child's requested thinking level after incompatible signed Anthropic thinking blocks are removed. This requires Pi 0.85.0 or newer. Thanks to [@hank-warren](https://github.com/hank-warren) for #2021.
|
|
225
|
+
- Scope parallel-review findings to the requested target, while diff reviews continue to report only issues caused or exposed by the diff. Thanks to [@jmclaughlin724](https://github.com/jmclaughlin724) for #2042.
|
|
226
|
+
- Simplify watchdog clarification to one visible question followed by native continuation, removing reply tracking and mandatory follow-up reviews.
|
|
227
|
+
- Show task-based labels for workflow launches, reviews, and continued child work.
|
|
228
|
+
|
|
229
|
+
### Fixed
|
|
230
|
+
- Accept `runs.run(...)` promises in `runs.all(...)`, including the natural `items.map(...)` form, instead of reporting an invalid key. A one-time warning explains when config objects are still required for batch validation, grouping, and `collectFailure`. Thanks to [@karandhillon1995](https://github.com/karandhillon1995) for #2128.
|
|
231
|
+
- Make Intercom-aware preflight produce the same launch digest as foreground and background execution, while keeping the parsed agent definition independent of runtime bridge changes (#2127 and #2112). Thanks to [@Yivas](https://github.com/Yivas) for the instrumented reproduction.
|
|
232
|
+
- Apply project refinements during preflight so its launch digest matches the completed run. Thanks to [@Yivas](https://github.com/Yivas) for #2112.
|
|
233
|
+
- Report steering and follow-up requests as delivered only after the child consumes them, and report unconsumed requests accurately when the child finishes (#2116 and #2121). Thanks to [@yanqianglu](https://github.com/yanqianglu) for #2057.
|
|
234
|
+
- Keep native children alive during final shutdown when queued steering or follow-up work is still pending (#2117). Thanks to [@yanqianglu](https://github.com/yanqianglu) for #2057.
|
|
235
|
+
- Prevent stale shutdown timers from aborting resumed foreground or background work. Thanks to [@harche](https://github.com/harche) for #2025.
|
|
236
|
+
- Wait for remembered detached descendants before their parent finishes, without aborting children that already produced a result. Thanks to [@shaharmor](https://github.com/shaharmor) for #2051.
|
|
237
|
+
- Keep paused background runs from failing on checks that apply only at completion. Thanks to [@yanqianglu](https://github.com/yanqianglu) for #2022.
|
|
238
|
+
- Report process-tree cleanup as complete only after detached descendants have actually stopped. Thanks to [@rtbe](https://github.com/rtbe) for #2053.
|
|
239
|
+
- Let approved child coordinators answer supervisor questions from their own children while preserving immediate-parent ownership and tool restrictions. Thanks to [@shaharmor](https://github.com/shaharmor) for #2087.
|
|
240
|
+
- Allow read-only reviewers to quote phrases such as “must fix before” without being mistaken for implementation requests. Thanks to [@freezscholte](https://github.com/freezscholte) for #2079.
|
|
241
|
+
- Preserve explicitly read-only requests after tool restrictions are applied, while still rejecting implementation work without write tools. Thanks to [@stekman08](https://github.com/stekman08) for #2060.
|
|
242
|
+
- Stop review and scout launches before startup when requested repository tools are unavailable. Explicitly empty or restricted tool sets remain valid. Follow-up for #2058.
|
|
243
|
+
- Keep workflow child tools aligned with the selected agent when extensions wrap Pi built-ins, and place automatic extension-repository worktrees outside extension discovery (#2059).
|
|
244
|
+
- Validate worktree repositories and cleanliness before starting parallel workflow children. Thanks to [@yanqianglu](https://github.com/yanqianglu) for #2076.
|
|
245
|
+
- Reject workflows whose known child count exceeds `maxSubagentSpawnsPerRun` before starting any child; dynamic counts remain limited at runtime. Thanks to [@ton77v](https://github.com/ton77v) for #2101.
|
|
246
|
+
- Show workflow usage on child rows instead of displaying overlapping or misleading wrapper totals. Thanks to [@expoli](https://github.com/expoli) for #2085.
|
|
247
|
+
- Keep live workflow timers advancing, nest loaded children correctly, collapse only fully represented duplicate groups, and freeze completed durations accurately. Thanks to [@expoli](https://github.com/expoli) for #2085.
|
|
248
|
+
- Preserve the parent's theme in foreground children, initialize themes in detached children, and refresh command-result rendering. Thanks to [@kubahasek](https://github.com/kubahasek) for #2089.
|
|
249
|
+
- Parse complete Orca creation output so observer handles, tab IDs, and titles are stored correctly. Thanks to [@G0-0000](https://github.com/G0-0000) for #2063.
|
|
250
|
+
- Keep the configured watchdog model and thinking level when recommending models. Thanks to [@freezscholte](https://github.com/freezscholte) for #2078.
|
|
251
|
+
- Recognize OpenRouter's status-prefixed 401 response as eligible for configured fallback before tool use. Thanks to [@freezscholte](https://github.com/freezscholte) for #2077.
|
|
252
|
+
- Keep internal OpenCode helper requests in the same provider session as normal Pi traffic. Thanks to [@IdrisGit](https://github.com/IdrisGit) for #2041.
|
|
253
|
+
- Run the child prompt filter before extensions inspect the final prompt, preserving intentional global-context and parent-only skill exclusions. Thanks to [@leftytennis](https://github.com/leftytennis) for #2043.
|
|
254
|
+
- Intersect agent tool declarations with tools available from the host, so restricted hosts reject unavailable tools before starting a child. Thanks to [@BioInfo](https://github.com/BioInfo) for #2034.
|
|
255
|
+
- Allow `fast` to round-trip through background recovery and follow-up. Thanks to [@isty2e](https://github.com/isty2e) for #2045.
|
|
256
|
+
- Use the detected npm Pi package root in detached runners instead of an inherited host path. Thanks to [@alvarosevilla95](https://github.com/alvarosevilla95) for #2050.
|
|
257
|
+
- Restore background SDK sessions for the official Pi 0.85.1 Linux standalone while retaining Pi 0.85.0 support. Thanks to [@xz-dev](https://github.com/xz-dev) for #2049.
|
|
258
|
+
- Resolve Pi TUI aliases correctly in unusual package layouts. Thanks to [@kroediger](https://github.com/kroediger) for #2020.
|
|
259
|
+
- Avoid requiring newer chord aliases on Pi versions before 0.85 while keeping required runtime aliases strict. Thanks to [@samuela](https://github.com/samuela) for #2026.
|
|
260
|
+
- Use `git wt` for Worktrunk on Windows to avoid the Windows Terminal `wt.exe` conflict. Thanks to [@Zethu5](https://github.com/Zethu5) for #2033.
|
|
261
|
+
- Prevent manually started schedules from firing again at their next natural time. Thanks to [@brandonmwest](https://github.com/brandonmwest) for #2052.
|
|
262
|
+
- Allow terminal schedules owned by an earlier session to be deleted when their exact run is known to have finished (#2125).
|
|
263
|
+
- Show exact child IDs and usable steering guidance in workflow status when a workflow no longer has a foreground route (#2011).
|
|
264
|
+
- Ignore action-like words inside filenames and paths when deciding whether a task requests implementation. Thanks to [@SiebertLanhove](https://github.com/SiebertLanhove) for #2039.
|
|
265
|
+
- Bound transcript previews by line and total size while preserving recent context and artifact links. Thanks to [@rtbe](https://github.com/rtbe) for #2015.
|
|
266
|
+
- Refresh the local model registry before opening model and thinking selectors, and warn when refresh fails. Thanks to [@ianbmacdonald](https://github.com/ianbmacdonald) for #2008.
|
|
267
|
+
- Preserve string, string-array, and undefined system-prompt shapes in `before_agent_start`. Thanks to [@luqman-v1](https://github.com/luqman-v1) for #2107.
|
|
268
|
+
|
|
269
|
+
## [0.66.0] - 2026-09-06
|
|
270
|
+
|
|
271
|
+
### Highlights
|
|
272
|
+
- Background results and completion notifications arrive more reliably, including after storage problems.
|
|
273
|
+
- Steering and supervisor replies reach the right run, with clearer guidance when a reply is needed first.
|
|
274
|
+
- Read-only tasks can continue after a rate limit on a compatible fallback model without starting over.
|
|
275
|
+
- Live progress, transcripts, and stable status displays make ongoing work easier to follow.
|
|
276
|
+
- Custom agents can opt into discovery, and trusted extensions can provide named workflows.
|
|
277
|
+
|
|
278
|
+
### Added
|
|
279
|
+
- Let agents appear in the parent prompt with `advertise: true`. Thanks to [@nwalke](https://github.com/nwalke) for #1972.
|
|
280
|
+
- Allow one read-only continuation after an HTTP 429 rate limit on a compatible fallback model from the same configured provider. Keep the session without replaying the task, within existing recovery, time, and budget limits (#1936). Thanks to [@peedrr](https://github.com/peedrr).
|
|
281
|
+
- Add targeted source checks and clearer evidence, confidence, and uncertainty reporting to researcher responses (#1932). Thanks to [@Muskos](https://github.com/Muskos).
|
|
282
|
+
- Let trusted extensions register session-scoped named workflows with validated arguments and permission to run specific host commands (#1907).
|
|
283
|
+
- Add opt-in completion notification diagnostics with `NODE_DEBUG=pi-subagents-notify` (#1981). Thanks to [@brandonmwest](https://github.com/brandonmwest) for the report and diagnostic sessions.
|
|
284
|
+
|
|
285
|
+
### Changed
|
|
286
|
+
- Explain model-verification failures and how to configure exact `modelResponseAliases` (#1922). Thanks to [@sixtus](https://github.com/sixtus).
|
|
287
|
+
- Clarify when startup fallback and read-only rate-limit continuation are supported (#1936). Thanks to [@peedrr](https://github.com/peedrr).
|
|
288
|
+
- Document steering delivery modes and `scheduledRuns.storeRoot` (#1933). Thanks to [@G0-0000](https://github.com/G0-0000).
|
|
289
|
+
- Remove generation suffixes from developer-facing types and helpers without changing request shapes, saved formats, or behavior (#1913).
|
|
290
|
+
|
|
291
|
+
### Fixed
|
|
292
|
+
- Deliver background results and completion notices reliably after early failures, delayed publication, or storage-capacity recovery. Save results before reporting successful completion, without adding idle polling (#1981). Thanks to [@brandonmwest](https://github.com/brandonmwest).
|
|
293
|
+
- Keep completion requirements intact when child sessions compact their context (#1996). Thanks to [@Zsbyqx20](https://github.com/Zsbyqx20).
|
|
294
|
+
- Correct supervisor action names and reply and steering guidance. Thanks to [@rtbe](https://github.com/rtbe) for #2002.
|
|
295
|
+
- Require an explicit answer to a pending supervisor question before steering or following up on a single background run; include the request ID in the response (#1980). Thanks to [@brandonmwest](https://github.com/brandonmwest).
|
|
296
|
+
- Detect supervisor questions when background or scheduled workflows start, including after earlier work finishes, while keeping macOS idle polling disabled (#1977). Thanks to [@brandonmwest](https://github.com/brandonmwest) and [@youlikemodernart](https://github.com/youlikemodernart) for #1220 and #1228.
|
|
297
|
+
- Queue steering for workflows owned by another runtime without incorrectly claiming delivery or taking over the run (#1978). Thanks to [@brandonmwest](https://github.com/brandonmwest).
|
|
298
|
+
- Find supervisor questions without a UI, keep notification failures from interrupting discovery, and require explicit answers (#1975, #1982). Thanks to [@brandonmwest](https://github.com/brandonmwest).
|
|
299
|
+
- Deliver background workflow steering to the intended child and report requests that cannot be delivered before shutdown (#1976, #1983). Thanks to [@brandonmwest](https://github.com/brandonmwest) for the diagnosis, reproduction, implementation, and tests.
|
|
300
|
+
- Leave the prompt runtime inactive when it is not configured. Thanks to [@lertian](https://github.com/lertian) for #1973.
|
|
301
|
+
- Return `invalid_state` instead of queuing stop requests that cannot reach a live workflow (#1965).
|
|
302
|
+
- Retain unreadable stop requests for retry, reject invalid workflow arguments even when validation returns an empty error message, and preserve worktree timeout details.
|
|
303
|
+
- Show live tool activity, timing, model, effort, and counters for foreground workflow children without forwarding full transcripts (#1964).
|
|
304
|
+
- Allow `action: "status", view: "transcript"` to inspect live foreground child output on demand (#1963).
|
|
305
|
+
- Keep the background status widget in place during progress updates (#1931). Thanks to [@DraconDev](https://github.com/DraconDev).
|
|
306
|
+
- Recognize `REQUEST_LIMIT_EXCEEDED` rate limits and avoid excluding healthy models because of invalid requests or context overflow (#1955, #1957). Thanks to [@slyons-vamp](https://github.com/slyons-vamp).
|
|
307
|
+
- Wait for resumed workflow results to be saved before reporting them missing on Windows (#1906).
|
|
308
|
+
- Send foreground workflow progress to RPC, headless, and cross-repository hosts even when the live chat card is off (#1951). Thanks to [@yanqianglu](https://github.com/yanqianglu).
|
|
309
|
+
- Resolve undici from the official npm registry for npm 12 compatibility (#1935). Thanks to [@chem](https://github.com/chem).
|
|
310
|
+
- Fix background launches on stable Pi 0.85.1 without experimental packages, while retaining Pi 0.85.0 support (#1944). Thanks to [@geril07](https://github.com/geril07).
|
|
311
|
+
- Include the saved workflow receipt path in wait results, notifications, and status and debug responses (#1938).
|
|
312
|
+
- Show structured output in completion notices when text is blank or contains only a closing think-tag (#1945). Thanks to [@npfedwards](https://github.com/npfedwards).
|
|
313
|
+
- Validate workflow `baseRef` values before execution and clarify supported refs (#1934, #1937). Thanks to [@jeanduplessis](https://github.com/jeanduplessis).
|
|
314
|
+
- Make boolean tool options compatible with restricted Gemini schema converters without changing which values are accepted (#1950). Thanks to [@Biaogo94](https://github.com/Biaogo94).
|
|
315
|
+
- Keep Fleet runs in start-time order instead of reshuffling them as activity changes (#1923, #1924). Thanks to [@expoli](https://github.com/expoli).
|
|
316
|
+
- Preserve links to previous runs when continuing a workflow by its string ID (#1920).
|
|
317
|
+
- Clear recovered errors after successful tool use or structured output (#1919). Thanks to [@Jonathanm10](https://github.com/Jonathanm10).
|
|
318
|
+
- Report empty final responses as empty-output failures instead of blaming earlier tool errors (#1921).
|
|
319
|
+
- Avoid missing-edit failures for successful read-only background tasks misclassified as implementation work (#1911). Thanks to [@yanqianglu](https://github.com/yanqianglu).
|
|
320
|
+
- Batch background streaming updates while showing child activity changes immediately (#1901).
|
|
321
|
+
- Honor new output paths on workflow follow-ups without overwriting the original report (#1903).
|
|
322
|
+
- Keep worktree setup responsive and cancellable, and preserve uncertain allocations for manual inspection (#1902).
|
|
323
|
+
|
|
324
|
+
## [0.65.1] - 2026-09-04
|
|
325
|
+
|
|
326
|
+
### Highlights
|
|
327
|
+
- Background sessions stay alive until their work and result delivery finish.
|
|
328
|
+
- Background runs work on Pi 0.85.0 without missing-package errors.
|
|
329
|
+
- Custom-provider models and proxy connections work more reliably in background runs.
|
|
330
|
+
- Parallel children keep separate session logs, even with a shared log directory.
|
|
331
|
+
- Worktree cleanup preserves changes until a complete, usable patch has been saved.
|
|
332
|
+
|
|
333
|
+
### Changed
|
|
334
|
+
- Clarify that switching execution modes after a failed run requires your approval (#1879).
|
|
335
|
+
|
|
336
|
+
### Fixed
|
|
337
|
+
- Accept configured model aliases returned by gateways without changing the requested model. Thanks to [@drudko-ias](https://github.com/drudko-ias) for #1897.
|
|
338
|
+
- Hide the empty, unlimited async capacity summary in Fleet. Thanks to [@youssefsiam38](https://github.com/youssefsiam38) for #1892.
|
|
339
|
+
- Fix missing-server import errors in Pi 0.85.0 background runs, including runs that load extensions.
|
|
340
|
+
- Remove repeated metadata and reply instructions from supervisor request cards. Thanks to [@youssefsiam38](https://github.com/youssefsiam38) for #1893.
|
|
341
|
+
- Stop foreground runs before contacting a provider when required tools are missing. Respect workflow async defaults and show each failure once. Thanks to [@youssefsiam38](https://github.com/youssefsiam38) for #1891.
|
|
342
|
+
- Keep pi-web parent sessions alive while subagent work or completion delivery remains active. Thanks to [@vcing](https://github.com/vcing) for #1857.
|
|
343
|
+
- Avoid unnecessary startup delays and preserve active locks when process IDs are reused. Thanks to [@ducaoya](https://github.com/ducaoya) for #1878.
|
|
344
|
+
- Make extension-provided models available before starting child sessions, including on Pi versions without native provider queues. Thanks to [@kevinkirkup](https://github.com/kevinkirkup) for #1885.
|
|
345
|
+
- Handle long or unusual workflow IDs without creating invalid file paths. Thanks to [@jstillwa](https://github.com/jstillwa) for #1875.
|
|
346
|
+
- Avoid startup import errors when optional Pi packages are not installed beside the extension. Thanks to [@VladimirGVP](https://github.com/VladimirGVP) for #1860.
|
|
347
|
+
- Use custom provider streams for task classification only when they match the selected model's API. Thanks to [@pwguler](https://github.com/pwguler) for #1874.
|
|
348
|
+
- Give concurrent children separate session files under an explicit `sessionDir`. Thanks to [@dat9uy](https://github.com/dat9uy) for #1859 and #1858.
|
|
349
|
+
- Honor proxy environment variables in detached background runs. Thanks to [@jasonrale](https://github.com/jasonrale) for #1867 and #1866.
|
|
350
|
+
- Allow previously unavailable models to run once they reappear in the model registry. Thanks to [@x1prog](https://github.com/x1prog) for #1862.
|
|
351
|
+
- Resolve Pi package imports correctly in detached runs, including subpath imports. Thanks to [@plopezlpz](https://github.com/plopezlpz) for #1871 and [@pwguler](https://github.com/pwguler) for #1880.
|
|
352
|
+
- Initialize the theme before child extensions access `ctx.ui.theme`. Thanks to [@danielmarbach](https://github.com/danielmarbach) for #1865.
|
|
353
|
+
- Save complete worktree patches, including binary changes, regardless of Git display settings. Validate them before removing worktrees. Thanks to [@jeanduplessis](https://github.com/jeanduplessis) for #1868.
|
|
354
|
+
- Accept `acceptance: false` alongside `gate`, treating it as omitted.
|
|
355
|
+
|
|
123
356
|
## [0.65.0] - 2026-09-04
|
|
124
357
|
|
|
125
358
|
### Highlights
|
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
|
|
17
|
+
That is the only required step. Background children use the host's SDK: npm Pi keeps its detached Node runner; the official Pi 0.85.1 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
|
|
|
@@ -61,13 +61,14 @@ The extension ships with agents you can use immediately:
|
|
|
61
61
|
| Agent | Use it when you want... |
|
|
62
62
|
|-------|--------------------------|
|
|
63
63
|
| `scout` | Fast local codebase recon: relevant files, entry points, data flow, risks. |
|
|
64
|
-
| `researcher` | Web/docs research with sources and a concise research brief. |
|
|
64
|
+
| `researcher` | Web/docs research with sources and a concise research brief. Requires [pi-web-access in the child](docs/agents.md#web-research-prerequisites). |
|
|
65
|
+
| `evidence-auditor` | Independently checks whether important research claims are supported by their sources. Requires [pi-web-access in the child](docs/agents.md#web-research-prerequisites). |
|
|
65
66
|
| `worker` | Implementation work. Edits files, validates, escalates unapproved decisions instead of guessing. |
|
|
66
67
|
| `reviewer` | Code review and small fixes against the task/plan, tests, edge cases, and simplicity. |
|
|
67
68
|
| `oracle` | A second opinion before acting. Challenges assumptions without editing. |
|
|
68
69
|
| `delegate` | A lightweight general delegate that behaves close to the parent session. |
|
|
69
70
|
|
|
70
|
-
Rule of thumb: `scout` before you understand the code, `researcher` before you trust external facts, `worker` to implement, `reviewer` to check, and `oracle` when the decision itself feels risky.
|
|
71
|
+
Rule of thumb: `scout` before you understand the code, `researcher` before you trust external facts, `evidence-auditor` before you rely on important research, `worker` to implement, `reviewer` to check, and `oracle` when the decision itself feels risky.
|
|
71
72
|
|
|
72
73
|
## Common workflows
|
|
73
74
|
|
|
@@ -120,11 +121,11 @@ The full reference lives in `docs/`:
|
|
|
120
121
|
| Doc | What's in it |
|
|
121
122
|
|-----|--------------|
|
|
122
123
|
| [Agents](https://github.com/nicobailon/pi-subagents/blob/main/docs/agents.md) | Custom agents, frontmatter reference, overriding builtins, tools, extensions, skills, per-agent memory. |
|
|
123
|
-
| [Models](https://github.com/nicobailon/pi-subagents/blob/main/docs/models.md) |
|
|
124
|
+
| [Models](https://github.com/nicobailon/pi-subagents/blob/main/docs/models.md) | Single-model selection and launch, defaults, per-role overrides, recommended tiering, thinking levels, model scope enforcement, profiles. |
|
|
124
125
|
| [Workflows](https://github.com/nicobailon/pi-subagents/blob/main/docs/workflows.md) | Orchestration patterns, prompt shortcuts, scripted workflows, worktree isolation, child-to-parent coordination, the recursion guard. |
|
|
125
126
|
| [Watchdog](https://github.com/nicobailon/pi-subagents/blob/main/docs/watchdog.md) | The opt-in adversarial change reviewer, scope monitoring, LSP checks, and child tool permissions. |
|
|
126
127
|
| [Tool reference](https://github.com/nicobailon/pi-subagents/blob/main/docs/tool-reference.md) | Every `subagent` parameter, management actions, status/control actions, acceptance gates, external CLI runners. |
|
|
127
128
|
| [Observability](https://github.com/nicobailon/pi-subagents/blob/main/docs/observability.md) | FleetView, the fleet inspector, lifecycle artifacts, events, logs, session sharing. |
|
|
128
129
|
| [Missions and schedules](https://github.com/nicobailon/pi-subagents/blob/main/docs/missions.md) | Durable mission records, delivery receipts, timed and recurring runs. |
|
|
129
130
|
| [Configuration](https://github.com/nicobailon/pi-subagents/blob/main/docs/configuration.md) | Every `config.json` key and environment variable. |
|
|
130
|
-
| [Extension API](https://github.com/nicobailon/pi-subagents/blob/main/docs/extension-api.md) | The RPC, delegation API, preflight, capability ceilings, background-work providers, Herdr integration. |
|
|
131
|
+
| [Extension API](https://github.com/nicobailon/pi-subagents/blob/main/docs/extension-api.md) | The RPC, delegation API, preflight, capability ceilings, [trusted workflow resources](docs/extension-api.md#trusted-workflow-resources), background-work providers, Herdr integration. |
|
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: evidence-auditor
|
|
3
|
+
description: Independent evidence reviewer for checking whether important research claims are supported by their sources
|
|
4
|
+
tools: read, web_search, fetch_content, get_search_content, source_check
|
|
5
|
+
thinking: high
|
|
6
|
+
systemPromptMode: replace
|
|
7
|
+
inheritProjectContext: true
|
|
8
|
+
inheritSkills: false
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
You are an evidence-auditing subagent.
|
|
12
|
+
|
|
13
|
+
Given research findings or a brief produced by another agent, independently audit the evidence behind the small set of claims that could change the conclusion. Do not redo the original research or treat a supplied citation as proof. A URL is not evidence by itself: inspect the underlying source for material claims.
|
|
14
|
+
|
|
15
|
+
Working rules:
|
|
16
|
+
- Identify the decision-critical claims and prioritize claims that materially affect the recommendation or conclusion. Do not audit trivial details.
|
|
17
|
+
- Distinguish evidence, source interpretation, and inference. Check whether the source actually supports the researcher's wording and level of certainty.
|
|
18
|
+
- Prefer original, official, authoritative, and directly relevant sources. Flag material stale, weak, secondary, or circular sourcing.
|
|
19
|
+
- Use `source_check` for important, disputed, surprising, or decision-relevant claims. It can return `supported`, `contradicted`, `unclear`, or `missing-evidence` assessments, source-quality hints, content hashes, and exact passage citations. Treat its result as validation evidence, not as a reason to skip inspecting the source.
|
|
20
|
+
- Use `fetch_content` to inspect cited source pages and `get_search_content` to retrieve bounded slices of stored search or source-check content. Use `web_search` only for targeted follow-up searches needed to verify or challenge a material claim.
|
|
21
|
+
- Record contradictions between claims or sources instead of silently resolving them. Preserve uncertainty when evidence is incomplete or conflicting.
|
|
22
|
+
- Keep verification bounded. Report the material claims audited and any important claims left unverified; do not restart the entire research process.
|
|
23
|
+
|
|
24
|
+
Output a concise audit with these sections:
|
|
25
|
+
|
|
26
|
+
1. Verified claims
|
|
27
|
+
2. Contradicted claims
|
|
28
|
+
3. Weak / unclear / unsupported claims
|
|
29
|
+
4. Material source-quality concerns
|
|
30
|
+
5. Missing evidence
|
|
31
|
+
6. Material contradictions
|
|
32
|
+
7. Implications for the original conclusion
|
|
33
|
+
|
|
34
|
+
For each material claim, include the claim, status (`supported`, `contradicted`, `unclear`, or `missing evidence`), relevant source(s), short reasoning, and confidence where useful. Explicitly label interpretation or inference. Say when no material issues were found.
|
package/agents/researcher.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: researcher
|
|
3
3
|
description: Autonomous web researcher — searches, evaluates, and synthesizes a focused research brief
|
|
4
|
-
tools: read, write, web_search, fetch_content, get_search_content
|
|
4
|
+
tools: read, write, web_search, fetch_content, get_search_content, source_check
|
|
5
5
|
thinking: medium
|
|
6
6
|
systemPromptMode: replace
|
|
7
7
|
inheritProjectContext: true
|
|
@@ -16,12 +16,15 @@ Given a question or topic, run focused web research and produce a concise, well-
|
|
|
16
16
|
|
|
17
17
|
Working rules:
|
|
18
18
|
- Break the problem into 2-4 distinct research angles.
|
|
19
|
-
- Use `web_search` with `queries` so the search covers multiple angles instead of one generic query.
|
|
20
|
-
-
|
|
21
|
-
-
|
|
22
|
-
-
|
|
23
|
-
-
|
|
24
|
-
-
|
|
19
|
+
- Use `web_search` with `queries` so the search covers multiple angles instead of one generic query. Use `workflow: "none"` unless the task explicitly needs the interactive curator.
|
|
20
|
+
- Treat search-result summaries as discovery aids, not final evidence for important claims. Fetch the original source when a claim is important, disputed, surprising, or decision-relevant.
|
|
21
|
+
- Prefer primary, official, authoritative, or directly relevant sources. Keep a smaller set of strong sources rather than many weak or redundant ones; reject stale, redundant, or SEO-heavy sources, and flag stale evidence when freshness materially affects the answer.
|
|
22
|
+
- Use `source_check` against fetched source content for decision-critical or disputed claims, benchmark/performance claims, pricing/licensing claims, security claims, and wording that could materially affect a recommendation. Do not use it for every trivial fact.
|
|
23
|
+
- `source_check` must be registered by the loaded provider before launch. If a registered `source_check` call fails, continue by fetching and inspecting the original source directly, and disclose the validation limitation rather than failing the research run.
|
|
24
|
+
- Label direct evidence, source interpretation, and researcher inference distinctly. Never present an inference as if the source stated it directly.
|
|
25
|
+
- Record contradictions instead of silently resolving them. Record missing evidence when a claim cannot be verified.
|
|
26
|
+
- Never invent dates, quotations, citations, or unsupported precision.
|
|
27
|
+
- Stay bounded: if the first pass leaves a decision-relevant gap, run a tighter follow-up search; then report remaining uncertainty and stop.
|
|
25
28
|
|
|
26
29
|
Search strategy:
|
|
27
30
|
- direct answer query
|
|
@@ -37,16 +40,23 @@ Output format:
|
|
|
37
40
|
2-3 sentence direct answer.
|
|
38
41
|
|
|
39
42
|
## Findings
|
|
40
|
-
Numbered findings
|
|
41
|
-
1. **
|
|
42
|
-
|
|
43
|
+
Numbered, concise findings. For each decision-relevant finding include:
|
|
44
|
+
1. **Claim:** the finding. **Sources:** [Source](url). **Support:** direct evidence | interpretation. **Confidence:** high | medium | low.
|
|
45
|
+
|
|
46
|
+
Label any researcher inference explicitly in the explanation.
|
|
47
|
+
|
|
48
|
+
## Contradictions
|
|
49
|
+
Contradictory or disputed evidence, with sources. Say "None found" when applicable.
|
|
50
|
+
|
|
51
|
+
## Missing evidence
|
|
52
|
+
Unverified claims and unresolved questions.
|
|
43
53
|
|
|
44
54
|
## Sources
|
|
45
55
|
- Kept: Source Title (url) — why it matters
|
|
46
|
-
-
|
|
56
|
+
- Rejected/deprioritized: Source Title — short reason
|
|
47
57
|
|
|
48
|
-
##
|
|
49
|
-
|
|
58
|
+
## Next steps
|
|
59
|
+
Only the most useful follow-up research.
|
|
50
60
|
|
|
51
61
|
## Supervisor coordination
|
|
52
62
|
If runtime bridge instructions identify a safe supervisor target and you are blocked or need a decision, use `contact_supervisor` with `reason: "need_decision"` and wait for the reply. Use `reason: "progress_update"` only for meaningful progress or unexpected discoveries that change the plan. Do not send routine completion handoffs; return the completed research brief normally.
|
package/agents/reviewer.md
CHANGED
|
@@ -79,8 +79,9 @@ Structure your findings clearly:
|
|
|
79
79
|
When reviewing code, cite file paths and line numbers. When reviewing plans, cite specific sections and assumptions.
|
|
80
80
|
|
|
81
81
|
Filter findings by evidence, not by severity. Report only concrete current issues
|
|
82
|
-
|
|
83
|
-
|
|
82
|
+
within the named review target, and support each one with source proof, a test
|
|
83
|
+
or repro, or a contract contradiction. For a diff review, require that the issue
|
|
84
|
+
is caused or made reachable by that diff. Use P0 for issues
|
|
84
85
|
that block merge, P1 for issues that should be fixed before release, and P2 for
|
|
85
86
|
report-only notes. Say exactly `No issues found.` when nothing qualifies.
|
|
86
87
|
|