@unbrained/pm-cli 2026.10.25 → 2026.10.27

package/docs/QUALITY_EVIDENCE.md

@@ -54,6 +54,15 @@ their real emitted-byte counts may differ. Output growth still fails the
 unchanged ceilings; normalization does not waive accounting, payload parity,
 required-field or executable-recovery checks.
 
+The completion-provenance delivery
+([pm-gh1579](https://github.com/unbraind/pm-cli/blob/main/.agents/pm/issues/pm-gh1579.toon),
+a repository-only tracker record excluded from npm) makes the existing close and
+partial-bulk transcripts consume completion timestamp, source and correction
+guidance. Their reviewed ceilings increase by 76 and 80 estimated tokens
+respectively to account for this new required context. Other task and step
+ceilings, orientation selection, output accounting and the seeded growth
+negative control retain their existing enforcement.
+
 ## SDK mutation testing
 
 `pnpm quality:mutation` uses Stryker's Vitest runner to mutate the SDK cursor and

package/docs/READ_OUTPUT_CONTRACTS.md

@@ -4,6 +4,10 @@ Tracker references: [pm-15yuly](../.agents/pm/issues/pm-15yuly.toon), [pm-g8oh0f
 
 ## Agent Quick Context
 
+Complete package-envelope fitting and session-reference recovery are tracked by
+[pm-gh1567](../.agents/pm/issues/pm-gh1567.toon) and
+[pm-session-reference-recovery](../.agents/pm/issues/pm-session-reference-recovery.toon).
+
 Every built-in read surface uses four output dimensions: what to include, how much to return, how much the result may cost, and how to encode it. The same canonical controls work through the CLI, SDK, MCP, generated schemas, runtime contracts, and shell completions.
 
 | Dimension | CLI                              | SDK and MCP     | Meaning                                                                |
@@ -27,6 +31,56 @@ repeated metadata from results by default. Request
 `--output-row-contract` / `outputRowContract: true` when a consumer needs the
 row paths, jq selector, and active TOON encoding contract.
 
+### Package-defined complete envelopes
+
+`fitOutputEnvelope` is available from `@unbrained/pm-cli/sdk/query`, the
+aggregate SDK, and an extension command's `sdk.fitOutputEnvelope`. It fits
+ordered whole rows into a caller-defined envelope without changing domain
+ranking, metadata or transport policy:
+
+```ts
+import { fitOutputEnvelope } from "@unbrained/pm-cli/sdk/query";
+
+const fitted = fitOutputEnvelope([{ id: "one", title: "Context" }], {
+  tokenBudget: 800,
+  buildEnvelope: (items) => ({ source: "my-package", items }),
+  renderers: { json: (value) => JSON.stringify(value) + "\n" },
+});
+process.stdout.write(fitted.renderings[0]!.text);
+```
+
+The SDK reserves `output_fit`, attaches the omission/accounting receipt, and
+stabilizes its `estimated_tokens` and `output_bytes` against complete output,
+including the receipt itself and caller-supplied framing. Multiple required
+renderers may be supplied, such as JSON and TOON; each must fit, and the receipt
+records the greatest token estimate and byte count independently. Emit a cached
+rendering directly: another serializer or extra newline changes its cost.
+`buildEnvelope` can read the receipt for a package-owned self-accounting field.
+
+The default estimator is `ceil(UTF-8 bytes / 4)`. Supply `estimateTokens` for
+another contract, including a stronger one-token-per-byte bound. Estimates are
+not a tokenizer guarantee. Callbacks must be pure, deterministic, promptly
+returning, and include mandatory metadata in every rendering. The SDK does not
+interpret package fields or provider authentication.
+
+The default `prefix` policy stops at the first row that does not fit. `skip`
+tries later rows without changing their order. The receipt retains original
+`included_indices`, `total_candidates` and `omitted_count`; `complete` on the
+result means all candidate rows fit. Neither policy splits rows or assumes
+serialized size is monotone. A smaller budget does not promise nested selected
+sets under `skip`; use `prefix` when prefix continuity matters.
+
+The empty mandatory envelope must fit before any row is attempted.
+`OutputEnvelopeFitError.code` distinguishes `output_envelope_infeasible`
+(with `minimum_tokens`), `output_envelope_work_limit`, and
+`output_envelope_unstable`. No unverified or oversized packet is returned.
+`maxRenderCalls` defaults to 10,000 across every trial and renderer;
+`maxStabilizationPasses` defaults to 16 per trial. Actual renderer calls and
+evaluated candidates are reported in `work`, outside the measured packet.
+These ceilings bound fitting work; they cannot interrupt arbitrary callback
+execution. Existing candidate-projection packing and pre-receipt token
+attribution retain their distinct contracts.
+
 ### Include Modes
 
 `--output-include` accepts two kinds of token. A **field selector** names a row
@@ -195,7 +249,7 @@ The session ceiling and an explicit `--output-budget` both bind; the smaller
 remaining allowance wins. Rows for item facts already present in the caller's
 context become `{ "id": "pm-a1b2", "context_ref":
 "session:orientation:pm-a1b2" }` instead of repeating prose. References retain
-stable item identity and can be restored with `pm get <item-id> --brief` when
+stable item identity and can be restored with `pm get <item-id> --depth brief` when
 the prior context is unavailable. The receipt reports estimated and charged
 tokens separately when the remaining group allowance is smaller than the
 minimum control envelope, plus the accumulated spend, remaining capacity,

package/docs/RELEASING.md

@@ -572,6 +572,17 @@ never move a published tag or mint a second automatic version for the same UTC d
 - GitHub Release creation
 - GitHub Release metadata verification through the same local verification script
 
+The Auto Release parent has a 180-minute orchestration limit: 60 minutes for
+preparation and gates, 30 for aggregate runner queue delays, the unchanged
+60-minute publication, 15-minute acceptance and 5-minute advertisement job
+limits, and 10 minutes for orchestration overhead. Runner queue time consumes
+the waiting parent's wall time even when no child job is executing. The
+reserve accommodates delays without extending a child job or changing a
+quality gate. Extreme queue delays can still exhaust the parent; recover the
+existing immutable tag after checking its publication evidence rather than
+creating another daily version. Tracked by
+[pm-29bwud](../.agents/pm/issues/pm-29bwud.toon).
+
 Monitor:
 
 ```bash

package/docs/SDK.md

@@ -599,6 +599,17 @@ sentinel rather than presenting it as a mistyped pm id.
 
 ### Agent output budgets and discovery
 
+Package-defined packets can use `fitOutputEnvelope` from the query entrypoint
+or `CommandHandlerContext.sdk.fitOutputEnvelope` to fit complete JSON/TOON
+renderings, including self-accounting receipts and framing. See
+[complete envelope fitting](READ_OUTPUT_CONTRACTS.md#package-defined-complete-envelopes)
+for policies, work ceilings and refusal contracts, tracked by
+[pm-gh1567](../.agents/pm/issues/pm-gh1567.toon).
+Session receipts now advertise `pm get <item-id> --depth brief`; the
+`restore_reference_with` literal type changes accordingly. Hosts constructing
+`ExtensionCommandSdk` implementations must supply `fitOutputEnvelope` from the
+public SDK; host-created command contexts already provide it.
+
 Tracked by [pm-5t33or](../.agents/pm/features/pm-5t33or.toon),
 [pm-gmdzaa](../.agents/pm/issues/pm-gmdzaa.toon), and
 [pm-dpqa3h](../.agents/pm/chores/pm-dpqa3h.toon).
@@ -1123,6 +1134,28 @@ recurrence reason, accepts only the workspace open or in-progress target, and
 returns the terminal evidence captured atomically before the update path clears
 it from active metadata.
 
+Create focus policy is tracked by [pm-gh1577](https://github.com/unbraind/pm-cli/blob/main/.agents/pm/issues/pm-gh1577.toon)
+(this tracker record is repository-only and excluded from npm).
+Programmatic `create`, `PmClient.create`, `runCreate`, and MCP `pm_create`
+ignore saved session focus unless `inheritFocus: true` is supplied. An explicit
+parent, a parent from the selected template, or `unset: ["parent"]` takes
+precedence. Create receipts report `parent_source: "focus"`; the effective
+parent remains in the item and immutable create event. Plan results expose the
+effective parent as `plan.parent`. `pm create` and
+`pm plan create` enable this convenience by default; `--no-inherit-focus` or
+`--parent none` suppresses it (`pm create` also accepts `--unset parent`).
+SDK `planCreate` and MCP plan creation follow the same explicit opt-in policy.
+SDK scheduling shortcuts follow the same opt-in policy; package scheduling
+commands retain their focused creation convenience.
+
+Other create defaults still apply: an explicitly selected template supplies
+options before explicit caller values, workspace governance selects the default
+type/create mode, the type workflow selects its initial status, priority defaults
+to 2, tags to an empty array, and author identity comes from invocation/workspace
+policy. There is no implicit saved assignee or tag default outside the selected
+template. Importers should supply explicit type, status, priority, tags, assignee,
+and parent/unset policy when those values are part of their source contract.
+
 Lifecycle handoff and receipt guidance are tracked by
 [pm-gh1465](../.agents/pm/features/pm-gh1465.toon) and
 [pm-gh1464](../.agents/pm/issues/pm-gh1464.toon). Register a project-specific
@@ -1174,10 +1207,31 @@ If a process stops between the domain write and the journal update, rerunning
 the same plan discovers the already-applied step and continues. An ordinary
 error switches the journal to compensation mode and runs applied steps in
 reverse order, limited to steps whose forward attempt was durably recorded.
+Adapters can opt into `compensatePending: true` when `apply()` may fail after
+an internal write while inspection still reports `pending`. Such compensators
+must handle absent and partial effects idempotently. The default preserves
+applied-only compensation; an inspected `compensated` step is skipped.
+If compensation refuses, the journal retains its started steps
+and recovery data in `compensating` state instead of claiming a rollback.
 Compensations are new item-history or relationship events: the
 coordinator never deletes or rewrites immutable history. A crash during
 compensation resumes compensation before a new attempt begins.
 
+Guarded terminal updates are tracked by
+[pm-pllp78](../.agents/pm/issues/pm-pllp78.toon). A bulk update's `match` guard
+is checked under each item lock and advances to the operation's own committed
+key value before its next internal lifecycle write. A stale starting value
+still refuses without item or history writes. Item updates opt into pending
+compensation and attribute every internal write in immutable history. New
+receipts bind the history fingerprint, integer prefix length and exact version, so writes sharing
+one timestamp remain distinguishable. Recovery restores exclusively owned
+effects and preserves peer-only changes. Mixed ownership, rewritten receipts,
+or a peer write before the restore lock refuse with
+`transaction_partial_mutation`; the surfaced `AggregateError` retains both
+failures and the journal keeps recovery data. Repeated compensation recognizes
+its durable marker even when a peer adds context afterward. Legacy timestamp
+receipts remain supported, with ambiguous partial effects refused.
+
 ### Schema evolution and workspace history
 
 Tracked by [pm-dijg](../.agents/pm/features/pm-dijg.toon) and
@@ -1527,8 +1581,9 @@ handlers remain disabled. Package-backed `--template` create input cannot be
 semantically previewed through its package handler; expand it into explicit core
 mutation options before preview.
 
-Actionable previews are tracked by [pm-ekf2gu](../.agents/pm/issues/pm-ekf2gu.toon)
-and [pm-fa9olc](../.agents/pm/tasks/pm-fa9olc.toon).
+Actionable previews are tracked by [pm-ekf2gu](../.agents/pm/issues/pm-ekf2gu.toon),
+[pm-fa9olc](../.agents/pm/tasks/pm-fa9olc.toon), and
+[pm-jhkzk0](../.agents/pm/features/pm-jhkzk0.toon).
 `previewItemMutations` returns `warnings` grouped by zero-based operation
 `index`, canonical `id`, and `op`. These are the original create lifecycle
 warnings, including advisory `likely_duplicates` and duplicate-recovery tokens.
@@ -1544,7 +1599,14 @@ use this same projection. A `replayed_committed_plan` has no newly evaluated
 warnings; an empty warning list in that state does not certify current policy.
 
 Staging excludes derived `search` and `locks` content and unrelated runtime state,
-retaining registered item folders, explicitly configured schema files, and
+plus `extensions/<directory>/node_modules` dependency trees. These trees are
+excluded before entry inspection or traversal, including dependency links;
+configured schema files and registered item folders take precedence and retain
+the regular-file safety checks even inside a dependency tree. Extension source,
+manifests and managed-package metadata remain in the snapshot. The receipt
+declares `derived_extension_dependencies_excluded` among its unresolved commit
+constraints because executable package dependencies are not validated.
+Staging retains registered item folders, explicitly configured schema files, and
 `runtime/session.json` for core focus and inherited-parent semantics. Root-layout
 trackers copy only tracker-owned files and directories, including standard and
 custom item folders and configured schema files; unrelated project content is
@@ -2067,9 +2129,15 @@ signal-set metadata are supported, its item source matches, and its cursor,
 complete item-id set, and substantive recency-evidence fingerprint match.
 Missing, stale, version-incompatible, or corrupt state is rebuilt from the
 authoritative items and atomically replaced. The result reports `cache_status`
-and non-fatal `context_signal_store_stale`,
-`context_signal_store_invalid`, or `context_signal_store_write_failed`
-warnings. A write failure still serves the in-memory rebuilt candidates because
+without a warning for a successful missing/stale refresh
+([pm-gh1581](https://github.com/unbraind/pm-cli/blob/main/.agents/pm/issues/pm-gh1581.toon);
+this tracker record is repository-only and excluded from npm). Rebuilt signals are used in
+the current response; another read is unnecessary. With `explainRanking`,
+`ranking.feature_store.cache_status` exposes the refresh on context receipts.
+Corrupt/unreadable state and failed persistence retain actionable
+`context_signal_store_invalid` and `context_signal_store_write_failed` warnings.
+The exported stale-warning descriptor remains for compatibility with older
+receipts. A write failure still serves the in-memory rebuilt candidates because
 the snapshot is derived, never authoritative. Optional maps for activity density,
 graph proximity, claim/focus, knowledge density, author affinity, usage
 affinity, and semantic similarity let an index or application-specific host
@@ -3510,6 +3578,20 @@ search degrades gracefully and emits warning codes instead of hard-failing.
 
 ## Completion-aware reporting and migration
 
+Close provenance is tracked by [pm-gh1579](https://github.com/unbraind/pm-cli/blob/main/.agents/pm/issues/pm-gh1579.toon)
+(a repository-only tracker record excluded from npm).
+`closeItem`, `PmClient.close`, CLI/MCP close receipts and successful `closeMany`
+rows return `completion` with the persisted `timestamp` and `source`:
+`asserted` means this close supplied `completedAt`, `existing` preserves an
+earlier metadata value, and `close_time` means completion was inferred from the
+tracker close time. Timestamp and source are sealed in the close event's
+`context.completion`; the local correction hint remains in the response.
+Existing records without it have unknown provenance;
+`existing` does not assert how an earlier value was obtained. No prior events are
+rewritten. Inferred receipts include a tracker-bound `update --completed-at`
+correction hint. Pass `completedAt` (CLI `--completed-at`) when closing delivered
+work retroactively; core never extracts a delivery date from reason prose.
+
 `resolveCompletionTimestamp(item)` gives reports one canonical timestamp plus a
 `source` and `fallback` disclosure. It prefers `completed_at` (when the work
 actually finished), then legacy `closed_at`, then `updated_at`.

package/docs/SDK_CONTEXT_COORDINATION.md

@@ -22,6 +22,8 @@ bounded at scale without shelling out from an SDK host.
 
 ## Durable mutation events
 
+Integrity contracts: [pm-gh1593](https://github.com/unbraind/pm-cli/blob/main/.agents/pm/issues/pm-gh1593.toon).
+
 Read committed history facts as newline-delimited JSON:
 
 ```bash
@@ -33,13 +35,42 @@ pm events --cursor-mode row --since <cursor>
 
 By default, event rows carry `item_id`, `version`, `ts`, `author`, `type`, and
 `patch_count`, followed by one `pm.stream.trailer` record with `count`,
-`has_more`, `next_cursor`, and `source`. Persist the trailer cursor only after
+`has_more`, `next_cursor`, `source`, and `integrity`. Persist the trailer cursor only after
 the batch is durable. A crash before cursor persistence can replay the last
 batch repeatedly, including across multiple crashes. Consumers must process
 idempotently or deduplicate replays. `--cursor-mode row` preserves the previous
 shape with one `cursor` per event and no trailer for consumers that checkpoint
 every row. Already issued version-1 cursors remain accepted by `--since`.
 
+Every SDK page declares `integrity: "unverified"` by default. Full-file content
+matching prevents a stale cache from hiding same-length edits to any record,
+including an earlier record when the final record is unchanged. This freshness
+check alone does not verify the chain.
+The public `readHistorySnapshot` result retains `raw_bytes` alongside decoded
+`raw` and `entries`. Content receipts use those original bytes, including when
+UTF-8 decoding replaces an invalid byte; parsing behavior remains unchanged.
+
+Use `listMutationEvents({ item: "pm-abcd", verify: true })` or
+`pm events --item pm-abcd --verify --json` before acting on verified events.
+The SDK reads authoritative bytes and verifies each complete selected stream
+before applying operation, author, timestamp, cursor, or row-limit filters.
+Selected-record failures are detected even outside the returned page. JSON
+parsing failures from `readHistorySnapshot` report `history_json_invalid`;
+chain-verification failures report `event_history_integrity_failed` with
+history-inspection recovery. Follow the returned typed recovery guidance. Select
+`item` to bound verification cost and exclude unrelated streams. With no item
+filter, all available item and workspace streams are checked. Successful pages
+return `integrity: "verified"`, `verified_streams`, and
+`source: "authoritative_history"`; this proves the recorded chain, not agreement
+with the current materialized item or an external author signature. Empty
+selections report zero verified streams. Subscriptions verify each yielded
+batch with the same options. MCP `pm_events` accepts `verify: true` too.
+Both strict reads and the authoritative fallback preserve typed history refusals
+and report other host read failures as `event_index_unavailable`. Cache receipts
+and ordered rows are published together, including across concurrent reads.
+Batch-mode NDJSON trailers retain the integrity receipt; compatibility row mode
+has no trailer, so use JSON or batch mode when persisting page receipts.
+
 Version-1 cursor ordering uses recorded timestamps, stream ids, and offsets.
 A fact committed later with an older timestamp falls before an advanced cursor.
 Clock-independent ordering and late-commit recovery remain tracked by
@@ -53,15 +84,15 @@ streams with the same ordering, filters, pagination, and cursor contract; pages
 identify that path with `source: "authoritative_history"`.
 Writers without SQLite use the same pending and committed invalidation protocol,
 so a later Node writer cannot certify a cache that omitted their facts.
-Incremental writes also verify the previous size receipt before advancing it,
+Incremental writes also verify the previous full-content receipt before advancing it,
 so merged history cannot be hidden by a later append. Upgraded runtimes rebuild
 legacy projections that could contain omitted facts with apparently current
 receipts; authoritative history does not require a format migration.
 
 Index readers take a synchronous SQLite read transaction containing both event
-rows and their stream-size receipts, then close the database before checking
+rows and their full-stream SHA-256 content receipts, then close the database before checking
 authoritative files. They acquire neither history-index writer lock. File
-identity and write timestamps, authoritative stream sizes, and pending or
+identity and write timestamps, complete authoritative content digests, and pending or
 committed invalidations must still match before a snapshot is returned. A
 concurrent change refuses the optional snapshot; it cannot certify older rows
 using a newer size receipt.

package/docs/TESTING.md

@@ -678,8 +678,21 @@ pm test <item-id> --run --workspace-context snapshot --override-linked-workspace
   `.git`, `.agents`, coverage output, and common cache directories are excluded
   at every directory depth, with reserved names matched case-insensitively for
   portable admission. Git sources receive an independent commit/tag object store
-  with fresh configuration, no source hooks, and no origin remote. Repository
+  with an index initially based on HEAD, fresh configuration, no source hooks,
+  and no origin remote. Repository
   history remains available; this is execution isolation, not history redaction.
+  Receipt verification is tracked by [pm-ycyymg](../.agents/pm/issues/pm-ycyymg.toon).
+  Source-mode tracker copies authenticate matching durable receipts against the
+  explicitly inherited read-only source index. Snapshot-mode copies use their
+  own index and the exact bound tracker path. Only bounded stage-zero receipt
+  blobs from the selected source tracker index are copied into that independent
+  object store and rebased into the snapshot namespace, including staged-only
+  receipts and custom tracker roots. Inherited receipts from another tracker
+  namespace are removed. Untracked, missing, conflicted, malformed, or
+  provenance-divergent sidecars remain untrusted; no source receipt, index,
+  or history is written by verification. A failed source index/object read aborts
+  snapshot setup before its receipt namespace is changed. A workspace without
+  Git authority or without indexed receipts still supplies no durable proof.
   See [Faithful package acceptance](PACKAGE_GATE_ACCEPTANCE.md) for limits.
   Each existing root or nested `node_modules`
   directory is linked at its original relative path, including installations

package/docs/WORKFLOW_POLICIES.md

@@ -80,7 +80,20 @@ reviewable history and skip approval requirements; use `transition` rules with
 of the current record, using the same content and independent-actor checks.
 
 Refused mutations preserve item state and item history, and append a workspace
-refusal event. Accepted mutations attach bounded policy decisions to their normal
+refusal event. This append changes the tracked `history/_workspace.jsonl` file
+under the selected tracker. Retain it with the workspace changes. The typed SDK
+error's `context.side_effects` and CLI JSON `side_effects` disclose the
+tracker-relative `path`, `op: "policy_refused"`, and sealed `record_hash`; MCP
+error details retain the same context. Human-readable diagnostics also name the
+write. Every refused attempt records a distinct event and returns its own record
+identity, including repeated identical requests. This preserves attempt history
+instead of silently coalescing it. Dry-run refusals have `side_effects: []` and
+append nothing. An audit failure retains its separate error contract below and
+does not claim a completed append. This disclosure is tracked by
+[pm-gh1585](https://github.com/unbraind/pm-cli/blob/main/.agents/pm/issues/pm-gh1585.toon)
+(a repository-only tracker record excluded from npm).
+
+Accepted mutations attach bounded policy decisions to their normal
 history event. Diagnostics contain policy ids and missing field paths, without
 copying reviewed content into errors.
 If the mandatory refusal audit cannot be appended, the mutation instead raises

package/docs/agent-task-token-baseline.json

@@ -1 +1 @@
-{"version":5,"transcript_version":2,"transcript_digest":"sha256:6d4041acfaa4075dde1972d6127a74f18916f7661738b4f5d5fd47a61c179a78","estimator":"ceil(utf8_bytes / 4)","comparison_scope":"plan_recovery_tracker_root_canonicalized","measurement_scope":"output_before_token_accounting","published_with_release":true,"orientation":{"canonical_task_id":"orientation-context-intent","required_capabilities":["actionable_work","active_ownership","workspace_state"],"measured_winner_tokens":1087,"protocols":[{"task_id":"orientation-context-intent","command_count":1,"estimated_tokens":1087,"capabilities":["actionable_work","active_ownership","workspace_state"],"capability_evidence":{"actionable_work":[{"step_id":"context","field_path":"hierarchy"}],"active_ownership":[{"step_id":"context","field_path":"activity"}],"workspace_state":[{"step_id":"context","field_path":"summary.active_items"}]}},{"task_id":"orientation-operating-rules","command_count":4,"estimated_tokens":2139,"capabilities":["actionable_work","active_ownership","workspace_state"],"capability_evidence":{"actionable_work":[{"step_id":"open","field_path":"items"}],"active_ownership":[{"step_id":"in-progress","field_path":"items"}],"workspace_state":[{"step_id":"context","field_path":"summary.active_items"}]}},{"task_id":"orientation-contracts-next","command_count":2,"estimated_tokens":5203,"capabilities":["actionable_work","active_ownership","workspace_state"],"capability_evidence":{"actionable_work":[{"step_id":"next","field_path":"recommended.id"}],"active_ownership":[{"step_id":"next","field_path":"held_by_others"}],"workspace_state":[{"step_id":"next","field_path":"summary.in_progress"}]}}]},"tasks":[{"id":"orientation-context-intent","max_estimated_tokens":1087,"steps":[{"id":"context","max_estimated_tokens":1087,"accounting_mode":"self_reported"}]},{"id":"orientation-contracts-next","max_estimated_tokens":5203,"steps":[{"id":"contracts","max_estimated_tokens":4481,"accounting_mode":"self_reported"},{"id":"next","max_estimated_tokens":722,"accounting_mode":"self_reported"}]},{"id":"orientation-operating-rules","max_estimated_tokens":2139,"steps":[{"id":"context","max_estimated_tokens":1087,"accounting_mode":"self_reported"},{"id":"search","max_estimated_tokens":164,"accounting_mode":"self_reported"},{"id":"open","max_estimated_tokens":712,"accounting_mode":"self_reported"},{"id":"in-progress","max_estimated_tokens":176,"accounting_mode":"self_reported"}]},{"id":"context-bootstrap","max_estimated_tokens":2077,"steps":[{"id":"triage","max_estimated_tokens":619,"accounting_mode":"self_reported"},{"id":"orient","max_estimated_tokens":1087,"accounting_mode":"self_reported"},{"id":"inspect","max_estimated_tokens":371,"accounting_mode":"self_reported"}]},{"id":"closed-domain-recovery","max_estimated_tokens":630,"steps":[{"id":"refuse-intent","max_estimated_tokens":259,"accounting_mode":"self_reported"},{"id":"retry-intent","max_estimated_tokens":371,"accounting_mode":"self_reported"}]},{"id":"unknown-option-recovery","max_estimated_tokens":596,"steps":[{"id":"refuse-option","max_estimated_tokens":433,"accounting_mode":"self_reported"},{"id":"retry-option","max_estimated_tokens":163,"accounting_mode":"self_reported"}]},{"id":"lifecycle-mutation","max_estimated_tokens":812,"steps":[{"id":"create","max_estimated_tokens":20,"accounting_mode":"self_reported"},{"id":"inspect-open","max_estimated_tokens":363,"accounting_mode":"self_reported"},{"id":"close","max_estimated_tokens":31,"accounting_mode":"self_reported"},{"id":"inspect-closed","max_estimated_tokens":398,"accounting_mode":"self_reported"}]},{"id":"bulk-effect-outcomes","max_estimated_tokens":326,"steps":[{"id":"create-bulk-target","max_estimated_tokens":20,"accounting_mode":"self_reported"},{"id":"partial-effect","max_estimated_tokens":174,"accounting_mode":"self_reported"},{"id":"no-effect","max_estimated_tokens":132,"accounting_mode":"self_reported"}]},{"id":"plan-execution-mutations","max_estimated_tokens":806,"steps":[{"id":"create-plan","max_estimated_tokens":21,"accounting_mode":"self_reported"},{"id":"add-step","max_estimated_tokens":254,"accounting_mode":"self_reported"},{"id":"complete-step","max_estimated_tokens":253,"accounting_mode":"self_reported"},{"id":"inspect-plan","max_estimated_tokens":278,"accounting_mode":"self_reported"}]}],"composite_max_estimated_tokens":13676}
+{"version":5,"transcript_version":2,"transcript_digest":"sha256:83d4523ca528ad5e8801cf5c7c02dcebbf2b87dc72422d4b8e648755dcdc36c2","estimator":"ceil(utf8_bytes / 4)","comparison_scope":"plan_recovery_tracker_root_canonicalized","measurement_scope":"output_before_token_accounting","published_with_release":true,"orientation":{"canonical_task_id":"orientation-context-intent","required_capabilities":["actionable_work","active_ownership","workspace_state"],"measured_winner_tokens":1087,"protocols":[{"task_id":"orientation-context-intent","command_count":1,"estimated_tokens":1087,"capabilities":["actionable_work","active_ownership","workspace_state"],"capability_evidence":{"actionable_work":[{"step_id":"context","field_path":"hierarchy"}],"active_ownership":[{"step_id":"context","field_path":"activity"}],"workspace_state":[{"step_id":"context","field_path":"summary.active_items"}]}},{"task_id":"orientation-operating-rules","command_count":4,"estimated_tokens":2139,"capabilities":["actionable_work","active_ownership","workspace_state"],"capability_evidence":{"actionable_work":[{"step_id":"open","field_path":"items"}],"active_ownership":[{"step_id":"in-progress","field_path":"items"}],"workspace_state":[{"step_id":"context","field_path":"summary.active_items"}]}},{"task_id":"orientation-contracts-next","command_count":2,"estimated_tokens":5203,"capabilities":["actionable_work","active_ownership","workspace_state"],"capability_evidence":{"actionable_work":[{"step_id":"next","field_path":"recommended.id"}],"active_ownership":[{"step_id":"next","field_path":"held_by_others"}],"workspace_state":[{"step_id":"next","field_path":"summary.in_progress"}]}}]},"tasks":[{"id":"orientation-context-intent","max_estimated_tokens":1087,"steps":[{"id":"context","max_estimated_tokens":1087,"accounting_mode":"self_reported"}]},{"id":"orientation-contracts-next","max_estimated_tokens":5203,"steps":[{"id":"contracts","max_estimated_tokens":4481,"accounting_mode":"self_reported"},{"id":"next","max_estimated_tokens":722,"accounting_mode":"self_reported"}]},{"id":"orientation-operating-rules","max_estimated_tokens":2139,"steps":[{"id":"context","max_estimated_tokens":1087,"accounting_mode":"self_reported"},{"id":"search","max_estimated_tokens":164,"accounting_mode":"self_reported"},{"id":"open","max_estimated_tokens":712,"accounting_mode":"self_reported"},{"id":"in-progress","max_estimated_tokens":176,"accounting_mode":"self_reported"}]},{"id":"context-bootstrap","max_estimated_tokens":2077,"steps":[{"id":"triage","max_estimated_tokens":619,"accounting_mode":"self_reported"},{"id":"orient","max_estimated_tokens":1087,"accounting_mode":"self_reported"},{"id":"inspect","max_estimated_tokens":371,"accounting_mode":"self_reported"}]},{"id":"closed-domain-recovery","max_estimated_tokens":630,"steps":[{"id":"refuse-intent","max_estimated_tokens":259,"accounting_mode":"self_reported"},{"id":"retry-intent","max_estimated_tokens":371,"accounting_mode":"self_reported"}]},{"id":"unknown-option-recovery","max_estimated_tokens":596,"steps":[{"id":"refuse-option","max_estimated_tokens":433,"accounting_mode":"self_reported"},{"id":"retry-option","max_estimated_tokens":163,"accounting_mode":"self_reported"}]},{"id":"lifecycle-mutation","max_estimated_tokens":888,"steps":[{"id":"create","max_estimated_tokens":20,"accounting_mode":"self_reported"},{"id":"inspect-open","max_estimated_tokens":363,"accounting_mode":"self_reported"},{"id":"close","max_estimated_tokens":107,"accounting_mode":"self_reported"},{"id":"inspect-closed","max_estimated_tokens":398,"accounting_mode":"self_reported"}]},{"id":"bulk-effect-outcomes","max_estimated_tokens":406,"steps":[{"id":"create-bulk-target","max_estimated_tokens":20,"accounting_mode":"self_reported"},{"id":"partial-effect","max_estimated_tokens":254,"accounting_mode":"self_reported"},{"id":"no-effect","max_estimated_tokens":132,"accounting_mode":"self_reported"}]},{"id":"plan-execution-mutations","max_estimated_tokens":806,"steps":[{"id":"create-plan","max_estimated_tokens":21,"accounting_mode":"self_reported"},{"id":"add-step","max_estimated_tokens":254,"accounting_mode":"self_reported"},{"id":"complete-step","max_estimated_tokens":253,"accounting_mode":"self_reported"},{"id":"inspect-plan","max_estimated_tokens":278,"accounting_mode":"self_reported"}]}],"composite_max_estimated_tokens":13832}

package/docs/agent-task-transcripts.json

@@ -1 +1 @@
-{"version":2,"orientation":{"canonical_task_id":"orientation-context-intent","required_capabilities":["workspace_state","active_ownership","actionable_work"],"protocols":[{"task_id":"orientation-context-intent","capabilities":["workspace_state","active_ownership","actionable_work"],"capability_evidence":{"workspace_state":[{"step_id":"context","field_path":"summary.active_items"}],"active_ownership":[{"step_id":"context","field_path":"activity"}],"actionable_work":[{"step_id":"context","field_path":"hierarchy"}]}},{"task_id":"orientation-contracts-next","capabilities":["workspace_state","active_ownership","actionable_work"],"capability_evidence":{"workspace_state":[{"step_id":"next","field_path":"summary.in_progress"}],"active_ownership":[{"step_id":"next","field_path":"held_by_others"}],"actionable_work":[{"step_id":"next","field_path":"recommended.id"}]}},{"task_id":"orientation-operating-rules","capabilities":["workspace_state","active_ownership","actionable_work"],"capability_evidence":{"workspace_state":[{"step_id":"context","field_path":"summary.active_items"}],"active_ownership":[{"step_id":"in-progress","field_path":"items"}],"actionable_work":[{"step_id":"open","field_path":"items"}]}}]},"tasks":[{"id":"orientation-context-intent","description":"Build sufficient cold-start workspace, ownership, and actionable-work context with the bounded orientation intent.","steps":[{"id":"context","args":["context","--for","orient","--limit","10"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["summary.active_items","hierarchy","activity"]}]},{"id":"orientation-contracts-next","description":"Compare the proposed contracts-summary plus next cold-start protocol on the same fixed workspace.","steps":[{"id":"contracts","args":["contracts","--summary"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["commands"]},{"id":"next","args":["next","--for","execute","--ready-only","--limit","3"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["summary.in_progress","held_by_others","recommended.id"]}]},{"id":"orientation-operating-rules","description":"Compare the historical context, search, open-list, and in-progress-list orientation sequence.","steps":[{"id":"context","args":["context","--for","orient","--limit","10"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["summary.active_items","hierarchy","activity"]},{"id":"search","args":["search","agent task","--status","all","--limit","10"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"]},{"id":"open","args":["list","--status","open","--limit","20"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"]},{"id":"in-progress","args":["list","--status","in_progress","--limit","20"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"]}]},{"id":"context-bootstrap","description":"Orient in a scaled workspace and inspect the canonical focus item.","steps":[{"id":"triage","args":["list","--for","triage","--limit","2"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"]},{"id":"orient","args":["context","--for","orient","--limit","5"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["summary.active_items","hierarchy","activity"]},{"id":"inspect","args":["get","$ANCHOR_ID","--for","inspect"],"expected_exit_code":0,"expected_output_kind":"entity","expected_accounting_mode":"self_reported","required_fields":["item.id"]}]},{"id":"closed-domain-recovery","description":"Reject an invalid context intent and execute the advertised shell-free retry.","steps":[{"id":"refuse-intent","args":["get","$ANCHOR_ID","--for","invalid-agent-intent"],"expected_exit_code":2,"expected_output_kind":"refusal","expected_accounting_mode":"self_reported","required_fields":["code","refusal","recovery"],"expected_error_code":"unknown_context_intent","expected_field_values":{"recovery.recovery_mode":"compact"},"expected_refusal_surface":"--for"},{"id":"retry-intent","args":["get","$ANCHOR_ID","--for","inspect"],"expected_exit_code":0,"expected_output_kind":"entity","expected_accounting_mode":"self_reported","required_fields":["item.id"],"recovery_for":"refuse-intent"}]},{"id":"unknown-option-recovery","description":"Identify an unsupported option after valid flags and continue with the corrected command.","steps":[{"id":"refuse-option","args":["search","agent task","--status","open","--limit","5","--include-body"],"expected_exit_code":2,"expected_output_kind":"refusal","expected_accounting_mode":"self_reported","required_fields":["code","refusal","recovery"],"expected_error_code":"unknown_option","expected_refusal_surface":"--include-body"},{"id":"retry-option","args":["search","agent task","--status","open","--limit","5"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"],"recovery_for":"refuse-option"}]},{"id":"lifecycle-mutation","description":"Create, inspect, close, and confirm a project item through public CLI receipts.","steps":[{"id":"create","args":["create","--id","$LIFECYCLE_ID","--title","Transcript lifecycle item","--description","Golden multi-step lifecycle task","--type","Task","--status","open","--create-mode","progressive"],"expected_exit_code":0,"expected_output_kind":"mutation_receipt","expected_accounting_mode":"self_reported","required_fields":["id","changed_field_count"]},{"id":"inspect-open","args":["get","$LIFECYCLE_ID","--for","inspect"],"expected_exit_code":0,"expected_output_kind":"entity","expected_accounting_mode":"self_reported","required_fields":["item.id","item.status"],"expected_field_values":{"item.status":"open"}},{"id":"close","args":["close","$LIFECYCLE_ID","Golden task completed"],"expected_exit_code":0,"expected_output_kind":"mutation_receipt","expected_accounting_mode":"self_reported","required_fields":["id","status","close_reason"]},{"id":"inspect-closed","args":["get","$LIFECYCLE_ID","--for","inspect"],"expected_exit_code":0,"expected_output_kind":"entity","expected_accounting_mode":"self_reported","required_fields":["item.id","item.status"],"expected_field_values":{"item.status":"closed"}}]},{"id":"bulk-effect-outcomes","description":"Preserve successful partial-effect and no-effect outcomes across a bulk lifecycle task.","steps":[{"id":"create-bulk-target","args":["create","--id","$BULK_ID","--title","Transcript bulk effect target","--description","Golden bulk outcome transcript target","--type","Task","--status","open","--create-mode","progressive"],"expected_exit_code":0,"expected_output_kind":"mutation_receipt","expected_accounting_mode":"self_reported","required_fields":["id","status","changed_field_count"]},{"id":"partial-effect","args":["close-many","--ids","$BULK_ID,pm-transcript-missing","--reason","Golden partial-effect transcript","--validate-close","off","--no-checkpoint"],"expected_exit_code":7,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["rows","outcome","exit_code"],"expected_field_values":{"outcome":"partial_effect"}},{"id":"no-effect","args":["close-many","--ids","$BULK_ID","--reason","Golden no-effect transcript","--validate-close","off","--no-checkpoint"],"expected_exit_code":6,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["rows","outcome","exit_code"],"expected_field_values":{"outcome":"no_effect"}}]},{"id":"plan-execution-mutations","description":"Create a Plan, add and complete a step, then inspect its durable evidence without echoing the full Plan on each mutation.","steps":[{"id":"create-plan","args":["create","--id","pm-transcript-plan","--type","Plan","--title","Transcript execution Plan","--create-mode","progressive"],"expected_exit_code":0,"expected_output_kind":"mutation_receipt","expected_accounting_mode":"self_reported","required_fields":["id","status"]},{"id":"add-step","args":["plan","add-step","pm-transcript-plan","--step-title","Verify result","--step-body","Durable execution context retained for later inspection."],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["id","step.id","steps_summary.total","inspection_command"],"expected_field_values":{"kind":"plan_mutation","steps_summary.total":1}},{"id":"complete-step","args":["plan","complete-step","pm-transcript-plan","plan-step-001","--step-evidence","Verified result"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["id","step.status","steps_summary.completed","omission_receipt"],"expected_field_values":{"step.status":"completed","steps_summary.completed":1}},{"id":"inspect-plan","args":["plan","show","pm-transcript-plan","--depth","deep"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["plan.steps","plan.steps_summary.completed"],"expected_field_values":{"plan.steps_summary.completed":1}}]}]}
+{"version":2,"orientation":{"canonical_task_id":"orientation-context-intent","required_capabilities":["workspace_state","active_ownership","actionable_work"],"protocols":[{"task_id":"orientation-context-intent","capabilities":["workspace_state","active_ownership","actionable_work"],"capability_evidence":{"workspace_state":[{"step_id":"context","field_path":"summary.active_items"}],"active_ownership":[{"step_id":"context","field_path":"activity"}],"actionable_work":[{"step_id":"context","field_path":"hierarchy"}]}},{"task_id":"orientation-contracts-next","capabilities":["workspace_state","active_ownership","actionable_work"],"capability_evidence":{"workspace_state":[{"step_id":"next","field_path":"summary.in_progress"}],"active_ownership":[{"step_id":"next","field_path":"held_by_others"}],"actionable_work":[{"step_id":"next","field_path":"recommended.id"}]}},{"task_id":"orientation-operating-rules","capabilities":["workspace_state","active_ownership","actionable_work"],"capability_evidence":{"workspace_state":[{"step_id":"context","field_path":"summary.active_items"}],"active_ownership":[{"step_id":"in-progress","field_path":"items"}],"actionable_work":[{"step_id":"open","field_path":"items"}]}}]},"tasks":[{"id":"orientation-context-intent","description":"Build sufficient cold-start workspace, ownership, and actionable-work context with the bounded orientation intent.","steps":[{"id":"context","args":["context","--for","orient","--limit","10"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["summary.active_items","hierarchy","activity"]}]},{"id":"orientation-contracts-next","description":"Compare the proposed contracts-summary plus next cold-start protocol on the same fixed workspace.","steps":[{"id":"contracts","args":["contracts","--summary"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["commands"]},{"id":"next","args":["next","--for","execute","--ready-only","--limit","3"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["summary.in_progress","held_by_others","recommended.id"]}]},{"id":"orientation-operating-rules","description":"Compare the historical context, search, open-list, and in-progress-list orientation sequence.","steps":[{"id":"context","args":["context","--for","orient","--limit","10"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["summary.active_items","hierarchy","activity"]},{"id":"search","args":["search","agent task","--status","all","--limit","10"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"]},{"id":"open","args":["list","--status","open","--limit","20"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"]},{"id":"in-progress","args":["list","--status","in_progress","--limit","20"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"]}]},{"id":"context-bootstrap","description":"Orient in a scaled workspace and inspect the canonical focus item.","steps":[{"id":"triage","args":["list","--for","triage","--limit","2"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"]},{"id":"orient","args":["context","--for","orient","--limit","5"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["summary.active_items","hierarchy","activity"]},{"id":"inspect","args":["get","$ANCHOR_ID","--for","inspect"],"expected_exit_code":0,"expected_output_kind":"entity","expected_accounting_mode":"self_reported","required_fields":["item.id"]}]},{"id":"closed-domain-recovery","description":"Reject an invalid context intent and execute the advertised shell-free retry.","steps":[{"id":"refuse-intent","args":["get","$ANCHOR_ID","--for","invalid-agent-intent"],"expected_exit_code":2,"expected_output_kind":"refusal","expected_accounting_mode":"self_reported","required_fields":["code","refusal","recovery"],"expected_error_code":"unknown_context_intent","expected_field_values":{"recovery.recovery_mode":"compact"},"expected_refusal_surface":"--for"},{"id":"retry-intent","args":["get","$ANCHOR_ID","--for","inspect"],"expected_exit_code":0,"expected_output_kind":"entity","expected_accounting_mode":"self_reported","required_fields":["item.id"],"recovery_for":"refuse-intent"}]},{"id":"unknown-option-recovery","description":"Identify an unsupported option after valid flags and continue with the corrected command.","steps":[{"id":"refuse-option","args":["search","agent task","--status","open","--limit","5","--include-body"],"expected_exit_code":2,"expected_output_kind":"refusal","expected_accounting_mode":"self_reported","required_fields":["code","refusal","recovery"],"expected_error_code":"unknown_option","expected_refusal_surface":"--include-body"},{"id":"retry-option","args":["search","agent task","--status","open","--limit","5"],"expected_exit_code":0,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["items"],"recovery_for":"refuse-option"}]},{"id":"lifecycle-mutation","description":"Create, inspect, close, and confirm a project item through public CLI receipts.","steps":[{"id":"create","args":["create","--id","$LIFECYCLE_ID","--title","Transcript lifecycle item","--description","Golden multi-step lifecycle task","--type","Task","--status","open","--create-mode","progressive"],"expected_exit_code":0,"expected_output_kind":"mutation_receipt","expected_accounting_mode":"self_reported","required_fields":["id","changed_field_count"]},{"id":"inspect-open","args":["get","$LIFECYCLE_ID","--for","inspect"],"expected_exit_code":0,"expected_output_kind":"entity","expected_accounting_mode":"self_reported","required_fields":["item.id","item.status"],"expected_field_values":{"item.status":"open"}},{"id":"close","args":["close","$LIFECYCLE_ID","Golden task completed"],"expected_exit_code":0,"expected_output_kind":"mutation_receipt","expected_accounting_mode":"self_reported","required_fields":["id","status","close_reason","completion.timestamp","completion.source","completion.hint"],"expected_field_values":{"completion.source":"close_time"}},{"id":"inspect-closed","args":["get","$LIFECYCLE_ID","--for","inspect"],"expected_exit_code":0,"expected_output_kind":"entity","expected_accounting_mode":"self_reported","required_fields":["item.id","item.status"],"expected_field_values":{"item.status":"closed"}}]},{"id":"bulk-effect-outcomes","description":"Preserve successful partial-effect and no-effect outcomes across a bulk lifecycle task.","steps":[{"id":"create-bulk-target","args":["create","--id","$BULK_ID","--title","Transcript bulk effect target","--description","Golden bulk outcome transcript target","--type","Task","--status","open","--create-mode","progressive"],"expected_exit_code":0,"expected_output_kind":"mutation_receipt","expected_accounting_mode":"self_reported","required_fields":["id","status","changed_field_count"]},{"id":"partial-effect","args":["close-many","--ids","$BULK_ID,pm-transcript-missing","--reason","Golden partial-effect transcript","--validate-close","off","--no-checkpoint"],"expected_exit_code":7,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["rows","outcome","exit_code","rows.0.completion.timestamp","rows.0.completion.source","rows.0.completion.hint"],"expected_field_values":{"outcome":"partial_effect","rows.0.completion.source":"close_time"}},{"id":"no-effect","args":["close-many","--ids","$BULK_ID","--reason","Golden no-effect transcript","--validate-close","off","--no-checkpoint"],"expected_exit_code":6,"expected_output_kind":"collection","expected_accounting_mode":"self_reported","required_fields":["rows","outcome","exit_code"],"expected_field_values":{"outcome":"no_effect"}}]},{"id":"plan-execution-mutations","description":"Create a Plan, add and complete a step, then inspect its durable evidence without echoing the full Plan on each mutation.","steps":[{"id":"create-plan","args":["create","--id","pm-transcript-plan","--type","Plan","--title","Transcript execution Plan","--create-mode","progressive"],"expected_exit_code":0,"expected_output_kind":"mutation_receipt","expected_accounting_mode":"self_reported","required_fields":["id","status"]},{"id":"add-step","args":["plan","add-step","pm-transcript-plan","--step-title","Verify result","--step-body","Durable execution context retained for later inspection."],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["id","step.id","steps_summary.total","inspection_command"],"expected_field_values":{"kind":"plan_mutation","steps_summary.total":1}},{"id":"complete-step","args":["plan","complete-step","pm-transcript-plan","plan-step-001","--step-evidence","Verified result"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["id","step.status","steps_summary.completed","omission_receipt"],"expected_field_values":{"step.status":"completed","steps_summary.completed":1}},{"id":"inspect-plan","args":["plan","show","pm-transcript-plan","--depth","deep"],"expected_exit_code":0,"expected_output_kind":"diagnostic","expected_accounting_mode":"self_reported","required_fields":["plan.steps","plan.steps_summary.completed"],"expected_field_values":{"plan.steps_summary.completed":1}}]}]}

package/docs/generated/FLAG_LEXICON_BUDGETS.md

@@ -12,7 +12,7 @@ This file is generated by `listPmFlagLexicon()`. Compatibility aliases do not co
 | `packages` | extensions | 56 | 56 |
 | `install` | extensions | 27 | 27 |
 | `upgrade` | extensions | 29 | 29 |
-| `create` | intake | 100 | 100 |
+| `create` | intake | 102 | 102 |
 | `copy` | intake | 24 | 24 |
 | `focus` | intake | 22 | 22 |
 | `list` | context | 86 | 86 |
@@ -33,7 +33,7 @@ This file is generated by `listPmFlagLexicon()`. Compatibility aliases do not co
 | `eval` | context | 25 | 25 |
 | `next` | context | 38 | 38 |
 | `history` | evidence | 35 | 35 |
-| `events` | evidence | 33 | 33 |
+| `events` | evidence | 34 | 34 |
 | `history-attest` | evidence | 23 | 23 |
 | `history-redact` | evidence | 27 | 27 |
 | `history-repair` | evidence | 27 | 27 |
@@ -56,7 +56,7 @@ This file is generated by `listPmFlagLexicon()`. Compatibility aliases do not co
 | `files` | evidence | 39 | 39 |
 | `docs` | evidence | 30 | 30 |
 | `deps` | graph | 32 | 32 |
-| `plan` | graph | 109 | 109 |
+| `plan` | graph | 111 | 111 |
 | `test` | quality | 56 | 56 |
 | `test-all` | quality | 40 | 40 |
 | `telemetry` | workspace | 21 | 21 |
@@ -91,7 +91,7 @@ This file is generated by `listPmFlagLexicon()`. Compatibility aliases do not co
 | `ops telemetry` | workspace | 21 | 21 |
 | `ops eval` | context | 25 | 25 |
 | `ops test-all` | quality | 40 | 40 |
-| `history events` | evidence | 33 | 33 |
+| `history events` | evidence | 34 | 34 |
 | `update many` | lifecycle | 146 | 146 |
 | `close many` | lifecycle | 72 | 72 |
 | `close delete` | lifecycle | 24 | 24 |

package/docs/generated/REFUSAL_CLOSURE_CENSUS.md

@@ -4,12 +4,12 @@ Tracker: `pm-f05lsg`.
 
 Every catalog code is listed. An `uncovered` row is an explicit closure obligation, never an omission or implied approval.
 
-- Catalog error codes: 429
+- Catalog error codes: 431
 - Executable error codes: 19
 - Executable-code ratchet floor: 18
 - Required executable canonical codes: `bulk_ids_input_empty`, `bulk_ids_input_missing_path`, `bulk_ids_input_unreadable`, `invalid_argument_value`, `manifest_unknown_key`, `missing_lifecycle_target`, `missing_required_argument`, `no_version_bounds_declared`, `projection_options_mutually_exclusive`, `tracker_not_initialized`, `tracker_root_missing`, `tracker_root_not_directory`, `tracker_root_unreadable`, `unknown_context_intent`, `unknown_field_projection`, `unknown_option`, `unknown_subcommand`
-- Uncovered error codes: 410
-- Coverage fraction: 0.044289
+- Uncovered error codes: 412
+- Coverage fraction: 0.044084
 - Closed-domain probes: 19
 - Grammar probes: 117
 
@@ -84,6 +84,7 @@ Every catalog code is listed. An `uncovered` row is an explicit closure obligati
 | `empty_surface` | `empty_surface` | uncovered | none | 0 |
 | `error_code_mismatch` | `error_code_mismatch` | uncovered | none | 0 |
 | `event_cursor_query_mismatch` | `event_cursor_query_mismatch` | uncovered | none | 0 |
+| `event_history_integrity_failed` | `event_history_integrity_failed` | uncovered | none | 0 |
 | `event_index_unavailable` | `event_index_unavailable` | uncovered | none | 0 |
 | `exit_code_mismatch` | `exit_code_mismatch` | uncovered | none | 0 |
 | `extension_command_activation_failed` | `extension_command_activation_failed` | uncovered | none | 0 |
@@ -350,6 +351,7 @@ Every catalog code is listed. An `uncovered` row is an explicit closure obligati
 | `tracker_root_unreadable` | `tracker_root_unreadable` | executable | owned_state | 1 |
 | `transaction_create_compensated` | `transaction_create_compensated` | uncovered | none | 0 |
 | `transaction_journal_invalid` | `transaction_journal_invalid` | uncovered | none | 0 |
+| `transaction_partial_mutation` | `transaction_partial_mutation` | uncovered | none | 0 |
 | `transaction_plan_mismatch` | `transaction_plan_mismatch` | uncovered | none | 0 |
 | `transaction_preview_external_schema` | `transaction_preview_external_schema` | uncovered | none | 0 |
 | `transaction_preview_non_regular_file` | `transaction_preview_non_regular_file` | uncovered | none | 0 |

package/marketplace.json

@@ -1 +1 @@
-{"name":"pm","owner":{"name":"unbrained","url":"https://github.com/unbraind/pm-cli"},"description":"Official marketplace for pm CLI — native git-based project management for Claude Code and AI coding agents.","version":"2026.10.25","plugins":[{"name":"pm-claude","source":"./plugins/pm-claude","description":"Native pm CLI integration for Claude Code — 32 MCP tools, 14 workflow skills with slash invocations, 4 subagents, hybrid TUI task tracking, session context injection, and coordination subagents for git-based project management without leaving Claude Code.","version":"2026.10.25","author":{"name":"unbrained","url":"https://github.com/unbraind/pm-cli"},"homepage":"https://github.com/unbraind/pm-cli","repository":"https://github.com/unbraind/pm-cli","license":"MIT","keywords":["pm-cli","project-management","mcp","tasks","agents","workflows","git-native","task-tracker","ai"],"category":"productivity"}]}
+{"name":"pm","owner":{"name":"unbrained","url":"https://github.com/unbraind/pm-cli"},"description":"Official marketplace for pm CLI — native git-based project management for Claude Code and AI coding agents.","version":"2026.10.27","plugins":[{"name":"pm-claude","source":"./plugins/pm-claude","description":"Native pm CLI integration for Claude Code — 32 MCP tools, 14 workflow skills with slash invocations, 4 subagents, hybrid TUI task tracking, session context injection, and coordination subagents for git-based project management without leaving Claude Code.","version":"2026.10.27","author":{"name":"unbrained","url":"https://github.com/unbraind/pm-cli"},"homepage":"https://github.com/unbraind/pm-cli","repository":"https://github.com/unbraind/pm-cli","license":"MIT","keywords":["pm-cli","project-management","mcp","tasks","agents","workflows","git-native","task-tracker","ai"],"category":"productivity"}]}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@unbrained/pm-cli",
-  "version": "2026.10.25",
+  "version": "2026.10.27",
   "description": "Git-native project management CLI for humans and agents.",
   "type": "module",
   "packageManager": "pnpm@11.28.5",

package/packages/pm-beads/package.json

@@ -1 +1 @@
-{"name":"@unbrained/pm-beads","version":"2026.10.25","private":true,"type":"module","description":"First-party pm package for importing Beads JSONL records.","homepage":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-beads#readme","repository":{"type":"git","url":"git+https://github.com/unbraind/pm-cli.git","directory":"packages/pm-beads"},"bugs":{"url":"https://github.com/unbraind/pm-cli/issues"},"keywords":["pm-package","project-management","beads"],"pm":{"aliases":["beads"],"extensions":["extensions/beads"],"catalog":{"display_name":"Beads Import","category":"migration","summary":"Import Beads JSONL records into pm while preserving source IDs.","tags":["migration","beads","import"],"links":{"docs":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-beads#readme","repository":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-beads","report":"https://github.com/unbraind/pm-cli/issues"}},"docs":["README.md"],"examples":["README.md"]}}
+{"name":"@unbrained/pm-beads","version":"2026.10.27","private":true,"type":"module","description":"First-party pm package for importing Beads JSONL records.","homepage":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-beads#readme","repository":{"type":"git","url":"git+https://github.com/unbraind/pm-cli.git","directory":"packages/pm-beads"},"bugs":{"url":"https://github.com/unbraind/pm-cli/issues"},"keywords":["pm-package","project-management","beads"],"pm":{"aliases":["beads"],"extensions":["extensions/beads"],"catalog":{"display_name":"Beads Import","category":"migration","summary":"Import Beads JSONL records into pm while preserving source IDs.","tags":["migration","beads","import"],"links":{"docs":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-beads#readme","repository":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-beads","report":"https://github.com/unbraind/pm-cli/issues"}},"docs":["README.md"],"examples":["README.md"]}}

package/packages/pm-calendar/extensions/calendar/shortcuts.ts

@@ -6,10 +6,10 @@
 import { runEvent, runMeet, runRemind, type CommandDefinition } from "@unbrained/pm-cli/sdk";
 import { schedulingCommandDefinitions } from "./command-definitions.ts";
 
-/** Scheduling handlers preserve native SDK validation, history, and output receipts. */
+/** Preserve CLI focus for absent policy, explicit opt-out, and native SDK validation/history/receipts. */
 export const schedulingCommands: CommandDefinition[] = schedulingCommandDefinitions.map((definition) => ({
   ...definition,
   run: (context) => (
     definition.name === "meet" ? runMeet : definition.name === "event" ? runEvent : runRemind
-  )(context.args[0], context.options, context.global),
+  )(context.args[0], { ...context.options, inheritFocus: (context.options.inheritFocus ?? true) === true }, context.global),
 }));

package/packages/pm-calendar/package.json

@@ -1 +1 @@
-{"name":"@unbrained/pm-calendar","version":"2026.10.25","private":true,"type":"module","description":"First-party pm package for calendar and agenda views.","homepage":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-calendar#readme","repository":{"type":"git","url":"git+https://github.com/unbraind/pm-cli.git","directory":"packages/pm-calendar"},"bugs":{"url":"https://github.com/unbraind/pm-cli/issues"},"keywords":["pm-package","project-management","calendar","agenda"],"pm":{"aliases":["calendar"],"extensions":["extensions/calendar"],"catalog":{"display_name":"Calendar Views","category":"workflow","summary":"Show agenda, day, week, and month views for deadlines, reminders, and scheduled events.","tags":["calendar","agenda","workflow"],"links":{"docs":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-calendar#readme","repository":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-calendar","report":"https://github.com/unbraind/pm-cli/issues"}},"docs":["README.md"],"examples":["README.md"]}}
+{"name":"@unbrained/pm-calendar","version":"2026.10.27","private":true,"type":"module","description":"First-party pm package for calendar and agenda views.","homepage":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-calendar#readme","repository":{"type":"git","url":"git+https://github.com/unbraind/pm-cli.git","directory":"packages/pm-calendar"},"bugs":{"url":"https://github.com/unbraind/pm-cli/issues"},"keywords":["pm-package","project-management","calendar","agenda"],"pm":{"aliases":["calendar"],"extensions":["extensions/calendar"],"catalog":{"display_name":"Calendar Views","category":"workflow","summary":"Show agenda, day, week, and month views for deadlines, reminders, and scheduled events.","tags":["calendar","agenda","workflow"],"links":{"docs":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-calendar#readme","repository":"https://github.com/unbraind/pm-cli/tree/main/packages/pm-calendar","report":"https://github.com/unbraind/pm-cli/issues"}},"docs":["README.md"],"examples":["README.md"]}}