opensec-pi-subagents 0.20.4 → 0.20.6

package/CHANGELOG.md

@@ -7,6 +7,86 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.20.6] - 2026-10-17
+
+Restores four fixes the Bun build had in 0.19.5-bun.6 to bun.8 (and 0.19.4-bun.0) that were lost when 0.20.x was
+cut from the Node sources. Both builds have them again.
+
+### Added
+
+- **Codemode scripts get a deadline.** Pi runs a `codemode` script with no time limit unless its first line sets
+  `timeout_ms`, so one stuck call held the agent forever. Scripts that set none now get `codemodeTimeoutSeconds`
+  (setting; default 1800, 0 = off), in the main session and in subagents; a deadline the script sets is kept.
+- **Codemode audit trail.** Every call a codemode script makes is written to
+  `$PI_CODEMODE_AUDIT_DIR/<session>/<call id>.log` (default `<agent dir>/opensec/codemode/`): the structured output
+  the script received (bash: up to 1 MiB), the exit code and the full-output path, capped per script by
+  `PI_CODEMODE_AUDIT_MAX_BYTES` (default 16 MiB). The script's result names the file and says that its filtered
+  output is not proof that something is absent; the script's structured result is kept.
+
+### Fixed
+
+- **A subagent's `bash` calls made by another tool are bounded too.** The subagent tool timeout only reached calls
+  the model made directly; calls a codemode script, `ctx.executeTool()` or a deferred tool made ran without a limit.
+  Since 0.20.3 loads codemode in every subagent, that was most of them. The subagent's tool-scope guard now sets the
+  timeout on every call path.
+- **Workflow scripts report the right line numbers on Bun.** Bun ignores a negative `lineOffset`, so every stack
+  frame pointed one line below the line the author wrote. The wrapper now needs no offset on either runtime.
+
+## [0.20.5] - 2026-10-16
+
+Orchestration results the main agent can act on: failed runs are error results with what they produced, unfinished
+agents point at the completion notification instead of inviting polling, and a released agent's result stays readable.
+
+> **Possibly breaking:**
+> - **Failed, aborted and stopped runs return `isError: true`**, as do unknown-agent lookups and refused steers or
+>   resumes. Pi shows them as tool errors and the main agent reads them as failures.
+> - **A model name whose closest matches span several providers is refused** instead of resolving to one of them,
+>   unless the parent's provider is among them. Use the exact `provider/id` to choose another provider.
+
+### Added
+
+- **`get_subagent_result` reads a released agent's result from its saved session.** After the 10-minute cleanup it
+  used to answer `Agent not found`; it now answers with the status and model from the kept resume state and the final
+  result read from the session file, marked as such. Nothing is held in memory longer: the file is read on demand. The
+  resume state now records the run's status.
+- **Each run records the model and thinking level it ran with**, a resumed run its own. The foreground result's
+  stats, `get_subagent_result` (`Model:`) and the completion notification (`<model>`, `<thinking>`) show them.
+- **Malformed tool arguments from weak models are repaired before validation** (`prepareArguments`) on the top-level
+  and nested `Agent`, `get_subagent_result` and `steer_subagent` tools: the arguments object sent as a JSON string or
+  stuffed into one string field, arrays where a string is expected, `null` optional fields, booleans and numbers sent
+  as strings, and a missing `subagent_type` on the top-level `Agent` tool, which goes to the default type under the
+  `fallbackSubagent` policy (`Note: No agent type given — using …`). A missing prompt is never invented.
+
+### Changed
+
+- **Failed runs are error results.** The foreground `Agent` result, resumed runs and `get_subagent_result`, top-level
+  and nested, set `isError` for `error`, `aborted` and `stopped`. The result renderer keeps the agent's status line for
+  these. A stopped run's headline reads `Agent was stopped by the user after …`, an aborted one `Agent was aborted
+  after …`, instead of `Agent completed in …`.
+- **Failure results keep the partial output and name the session file.** The run's last assistant text is kept also
+  when the run threw or a stopped run was abandoned, bounded to the run's own turns, and the result names the agent's
+  saved session file, which holds every turn (`<session-file>` in the notification). No separate files are written.
+- **No more polling prompts.** `get_subagent_result` on a running, queued or still-stopping agent says a completion
+  notification arrives on its own, to continue with other work, and not to call it again for that agent until then.
+  Its description and the `wait` parameter say the same; `wait` stays `false` by default. Background spawn and resume
+  results and the refused resume of a running agent no longer suggest `get_subagent_result` to wait.
+- **Notifications preview the first 10 lines of a result**, still capped at 500 characters (300 per agent in a group)
+  so one long line cannot flood the context, and carry the full result's size in `<result_bytes>`. The truncation note
+  says how many lines and bytes were left out.
+- **Model names no longer resolve across providers by guessing.** An exact `provider/id` (case-insensitive) resolves
+  as before. Among a short name's closest matches (`haiku`, `sonnet`), the parent's provider wins when it serves one;
+  matches from a single provider resolve to the tightest, as before (ties by id). Only matches that still span several
+  providers are an error naming up to five closest candidates. An exact id two providers serve follows the same rule.
+  A per-call model that does not resolve stays a tool error on every path.
+- **An agent file's model that does not resolve is reported.** The run still falls back to the parent's model, but its
+  results say which model was asked for, why it was not used and which model ran instead (the `Agent` and nested
+  `Agent` results, `get_subagent_result`, `<model-note>` in the notification). Spawns that resolve the agent file's
+  model by exact `provider/id` only (`@mentions`, RPC, scheduled jobs) and scheduled jobs whose model no longer
+  resolves note it the same way; workflows show it as a warning once per run.
+- **More released agents stay addressable:** 2000 top-level and 4000 nested or workflow entries (was 100 and 200).
+  An entry holds ids, paths and settings, about 450 bytes (700 with a worktree), never the conversation. Restoring
+  them at session start trims once instead of rescanning per entry.
+
 ## [0.20.4] - 2026-10-16
 
 The conversation viewer draws a subagent's transcript with Pi's own chat components, so it looks exactly like Pi's

package/README.md

@@ -117,6 +117,8 @@ locations are those of `@tintinweb/pi-subagents`.
 
 Based on `@tintinweb/pi-subagents` 0.19:
 
+- **0.20.6:** four fixes this build had in 0.19.5-bun.6 to bun.8 are back: a subagent's `bash` calls made by another tool (a codemode script, `ctx.executeTool()`) get the tool timeout; codemode scripts that set no `timeout_ms` get `codemodeTimeoutSeconds` (default 1800 s, 0 = off); every call a codemode script makes is logged raw to `$PI_CODEMODE_AUDIT_DIR/<session>/<call id>.log` (default `<agent dir>/opensec/codemode/`, capped by `PI_CODEMODE_AUDIT_MAX_BYTES`, default 16 MiB) and the script's result names the file; workflow scripts report the right line numbers on Bun again.
+- **0.20.5:** failed, aborted and stopped agents come back as error results with their last output and session file; weak models' malformed tool arguments are repaired; a running agent's reply asks the model to wait for its notification instead of polling; notifications preview 10 lines and give the result's size; each run's model is recorded and shown; an ambiguous model name is no longer settled by a guess across providers.
 - **0.20.4:** the conversation viewer draws a subagent's transcript with Pi's own chat components, as Pi's main session does; `ctrl+o` expands and collapses tool output. The `viewerMarkdown` setting and the `m` key are gone.
 - **0.20.3:**
   - From upstream 0.20–0.22: completions reach a busy parent before its next model call; an agent file's `isolated:`/`isolation:` hold on every spawn path; tool scoping covers tools called from other tools; `ctrl+b`; the fullscreen viewer, built on the incremental viewer (a frame in about 10 µs at 500 messages without a JIT).