@aeondave/pi-persona 1.17.3 → 1.17.5

package/AGENTS.md

@@ -37,8 +37,13 @@ the shared behavioral prompt layer: [`docs/SPINE.md`](docs/SPINE.md).
   `@earendil-works/pi-*`; never bundle copies.
 - npm publishes as `@aeondave/pi-persona`. Pi supplies the four `@earendil-works/pi-*` packages
   and `typebox`: keep them as `peerDependencies: "*"` with development-only copies, never runtime
-  dependencies. The supported host floor is Pi ≥ 1.0.0 (`MIN_PI_VERSION` and the README); Node.js
-  must be ≥ 22.19 to match that host. Keep the npm
+  dependencies. Target the latest stable Pi only (currently 1.4.0, aligned with `MIN_PI_VERSION`,
+  the four development pins and README); do not maintain historical-host compatibility branches.
+  **No legacy or deferred cleanup:** remove dead code, obsolete options, superseded implementations
+  and compatibility-only aliases with their replacement. Update every caller, fixture and document
+  in the same change. A completed feature must not leave temporary scaffolding or cleanup debt.
+  Keep a path only when it serves the current host/runtime or a demonstrated current data contract.
+  Node.js must be ≥ 22.19 to match that host. Keep the npm
   `files` allowlist explicit for docs/artwork, inspect `npm pack --dry-run`, and never publish drafts.
 - Supply-chain controls: pin every GitHub Action to a verified full commit SHA; keep top-level
   token permissions read-only, grant write permissions only to the reporting job that needs them,
@@ -175,7 +180,7 @@ the shared behavioral prompt layer: [`docs/SPINE.md`](docs/SPINE.md).
   a live, capability-filtered roster (agents, teams and flows, with descriptions and gated flows tagged in
   headless sessions) + a hand-off default (with one decision-class → method line, checked against the
   registry) to the system-prompt TAIL every turn — discovery that survives context burn.
-- **Sibling peer comm (in-process)**: a strategy can opt a run into direct sibling messaging
+- **Sibling peer comm**: a strategy can opt a run into direct sibling messaging
   (`AgentRunSpec.peers` — the `debate` strategy does). The child gets a `contact_peer` tool
   (`bus/peers.ts`): `list`/`send`, ONE-WAY only (blocking stays supervisor-only, so peers can
   never deadlock), peer list scoped per engine instance (never the whole bus), send budget 20,
@@ -183,7 +188,11 @@ the shared behavioral prompt layer: [`docs/SPINE.md`](docs/SPINE.md).
   Delivery: the in-process engine's bridge steers incoming bus messages into the child session,
   fenced with the sender attributed OUTSIDE the fence — the same bridge delivers the supervisor's
   `intercom send` (previously a dead letter). Gated by `EffectiveCapabilities.canUseBus` (OFF iff
-  the persona explicitly denies `intercom`). The child engine ignores `peers`.
+  the persona explicitly denies `intercom`). Child-process legs use the broker's engine-scoped
+  peer roster; `contact_peer` is installed only when that run opts in and the bus is allowed.
+  Granted communication tools join a nonempty child tool allowlist; explicit empty lists and
+  tool exclusions still win. In-process supervisor contact additionally requires `coaching`;
+  broker-connected children expose it when the bus is allowed.
   Design: [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md#the-comm-plane-in-practice) + [`docs/STRATEGIES.md`](docs/STRATEGIES.md).
   On the peer plane: `debate` and `pair` always; `map`/`synthesize` opt-in via `params.peers`.
   `magi`/`judge`/`fanout` stay peer-less BY DESIGN — independence is their bias guard
@@ -191,38 +200,37 @@ the shared behavioral prompt layer: [`docs/SPINE.md`](docs/SPINE.md).
   this. `compete` runs its competitors with `isolation: worktree` (REQUIRES a clean git repo; missing
   repo/dirty checkout/worktree failure fails closed and never falls back to the real tree) and returns
   the winning diff for the SUPERVISOR to apply.
-- **exocom** (`src/exocom/*`, `src/tools/exocom*.ts`; opt-in `PI_PERSONA_EXOCOM=1` / `--exocom`,
-  capability-gated): a plane apart from everything above — those are all INTERNAL to one supervisor's
-  own run (hierarchical, session-keyed children); exocom is FLAT and EXTERNAL, between independent
-  top-level pi instances sharing one selected scope, no parent/child relationship. Bare `--exocom`
-  keeps the current workspace scope; exact `--exocom=Ab0T` joins that existing workspace's scope from
-  another cwd through a persistent, collision-aware, case-sensitive four-character Base62 alias.
-  The scope selects registry/transport/ledger/artifacts, while every peer advertises its actual home
-  workspace id/code/safe label so external file sets are explicit. A foreign peer is advisory for
-  writes: it can inspect its own files and use postcards/ask/answer/wait/progress/release, but
-  `exocom_claim` is inactive and rejected because the ledger's paths are repository-relative to the
-  scope workspace. The code is a same-host/same-agent-dir join reference, not authentication.
-  Postcards remain one-way and non-blocking: `exocom_list`/`exocom_send`
-  plus `exocom_name` (a reply is a send with `in_reply_to` set). The separate shared JSONL work
-  ledger adds `claim`/`ask`/`answer`/`decline`/non-blocking `wait`/`progress`/`release`: overlapping
-  open write sets NACK atomically, and a pending targeted ask gates that participant to answer/decline,
-  read-only tools, and `exocom_name` identity metadata. Semantic frames are signed immediate-wake signals; the ledger is authoritative
-  if delivery is deferred. This is cooperative runtime coordination, not OS authorization. All ten
-  tools remain in `EXOCOM_TOOL_NAMES` (with `claim` withheld for a foreign member), targeted denies win independently, and joining requires
-  `canUseBus` plus at least one callable closer (`answer` or `decline`) so a published peer cannot be
-  wedged by an obligation it has no way to settle. If `exocom_name` is permitted, an unnamed top-level
-  Pi is prompted to invent a task-derived call-sign on its first user or inbound peer turn
-  (no catalog or extra model call). Naming is metadata permitted during pending asks, without
-  settling them; a targeted deny suppresses the prompt. Session identity is shared with standalone
-  `agent_name` and persisted across resume/persona changes. Until a handle is chosen, its actionable
-  naming bootstrap is delivered through the `context` hook because custom Exocom wakes can bypass
-  `before_agent_start`; after selection the hook stays silent. The session-hash suffix of a qualified target survives renames and telemetry resolves the
-  same canonical session.
-  Reuses the broker's wire framing
-  (`bus/broker/framing.ts`) and the
-  core fence (`fenceUntrusted`/`attributeInbound`) — no new trust-sensitive code path; inbound
-  attribution is resolved from the registry, never the envelope's self-reported `from_name`.
-  Design: [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md#exocom--the-external-plane).
+- **Exocom** (`src/exocom/*`, `src/tools/exocom*.ts`; opt-in `PI_PERSONA_EXOCOM=1` / `--exocom`;
+  see [the collaboration guide](docs/COLLABORATION.md)): a flat external plane between independent,
+  top-level Pi sessions, separate from one supervisor's internal workers. Bare `--exocom` selects the
+  current workspace; exact `--exocom=Ab0T` joins that existing scope from another cwd through a
+  persistent, case-sensitive four-character Base62 alias. The scope selects registry, transport,
+  ledger and artifacts; each member still advertises its actual home workspace. The code is a
+  same-host/same-agent-dir join reference, not authentication.
+  `EXOCOM_TOOL_NAMES` contains 15 call-time-gated tools: `exocom_list`, `exocom_send`, `exocom_name`,
+  `exocom_claim`, `exocom_ask`, `exocom_answer`, `exocom_decline`, `exocom_wait`, `exocom_release`,
+  `exocom_progress`, `exocom_status`, `exocom_task`, `exocom_offer`, `exocom_publish`, and
+  `exocom_profile`. A joined foreign-workspace peer cannot use `exocom_claim`; write-set task create
+  and pickup also require local scope and callable claim permission. Ledger paths are advisory
+  coordination, never filesystem authorization.
+  `exocom_task create` declares a voluntary task but does not start work or reserve files. The
+  immutable `task_id` is the creation frame's `msg_id`; carry it with `work_key` for take, progress,
+  finish, offer and publish so a reused work key cannot select another generation. Write-set pickup
+  and its claim are one locked ledger transaction; read-only tasks may be taken from a foreign scope.
+  An optional `exocom_offer` expires in at most 24 hours (one hour by default) and creates no answer
+  obligation. Use `exocom_ask` for an explicit blocking question. `exocom_publish` shares a bounded,
+  explicitly written excerpt, not another session's terminal-result archive. Peer prose is fenced and
+  attributed using the registry identity.
+  Tasks, offers and evidence are each capped at 64 records and 128 KiB aggregate. Terminal or stale
+  task facts and expired offers are retained for up to one hour; evidence is retained for up to one
+  hour. `exocom_profile` reports self-described capabilities (up to 8 tags, 48 characters each) and
+  optional `available`/`busy`/`away` status; absent status is unknown, and profiles confer no access.
+  During a pending ask, only settlement, `exocom_name`, status, explicit collaboration reads and
+  read-only filesystem tools remain available: profile `get` is allowed, but `set` and `clear` are not.
+  Naming remains metadata and does not answer the ask. Joining requires `canUseBus` plus at least one
+  callable ask closer (`exocom_answer` or `exocom_decline`) and is rechecked on persona changes.
+  Design: [architecture](docs/ARCHITECTURE.md#exocom--the-external-plane) and
+  [collaboration guide](docs/COLLABORATION.md).
 
 ## Testing
 
@@ -260,6 +268,19 @@ the shared behavioral prompt layer: [`docs/SPINE.md`](docs/SPINE.md).
   option (a terminal event is observed before the permission gate). A countdown replaces the stall clock; `x`
   cancels one via the stop registry; `X`, the `N agents` count and telemetry exclude them.
 
+- Loaded companions: `core/companion.ts` defines the public local presence, live memory-owner and
+  activity contracts; `extension/{companion,memory-owner}.ts` bind them to the current native owner.
+  Mind requires a compatible loaded partner, never a settings-file inference. Actual selection is
+  authoritative with persistence off; both engines freeze it for delegated legs (private per-child
+  factory in-process, spawn-local environment for child processes). `ui/activity-rows.ts` projects
+  bounded local Mind work without agent counts, controls, wakes, model usage or agent telemetry.
+  Automatic semantic review instead uses `pi-persona:mind-worker:v1`: one real tracked Mind worker,
+  with the current session model/effort, no tools/fallback/bus, normal shared concurrency and F9
+  controls, a 180s deadline, and a terminal archive. Memory/delegate/target permissions still apply.
+  Its completion belongs to Mind; it never wakes the supervisor. See the companion architecture contract.
+  These cooperative contracts are not authentication; see the loaded-companion section
+  in `docs/ARCHITECTURE.md`.
+
 - `src/core/` — pure kernel: frontmatter, permissions, contract (+`parseContract`), config, discovery, fence (`fenceUntrusted`), brief (`buildDelegationBrief` — the per-turn roster + standing hand-off default; `buildExocomBrief` — the per-turn exocom peer roster, the peer-vs-sub-agent split, and the relevance bound on a peer exchange), timer (`TimerScheduler` — the alarm engine behind the `timer` tool), session-runs (pure restore-notice helper: what a reload/resume lost + the run-id counter), types.
 - `src/engine/` — `child.ts`, `inproc.ts` (default), `adapter.ts`, `async.ts` (async tracker/peek), `worktree.ts` (git-worktree isolation), `stream.ts` (event→state).
 - `src/orchestration/` — `sdk.ts` (`agent`/`parallel`/`reduce`), `strategy.ts` (registry), `strategies/*.ts`, `voting.ts`, `flow*.ts` (DAG + JSONL journal + checkpoint gates), `roster.ts` (teams + `rosterSpec`: a roster member is a bare name OR an inline `{ agent, role, model, skills }` that specialises one agent — every strategy runs members through `rosterSpec`).

package/CHANGELOG.md

@@ -4,7 +4,112 @@ All notable changes to this project are documented here. The format follows
 [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); this project follows the version scheme
 used in its [GitHub releases](https://github.com/AeonDave/pi-persona/releases).
 
-## [Unreleased]
+## [1.17.5](https://github.com/AeonDave/pi-persona/releases/tag/v1.17.5) - 2026-10-25
+
+### Added
+
+- A visible asynchronous Mind maintenance worker, pinned to the current session model and effort.
+  It shares normal concurrency, F9 controls and result archival, has no tools or model fallback,
+  and returns its completion to Mind without starting another supervisor turn.
+- Loaded-companion presence, live memory ownership and bounded `Mind` activity rows. Mind can
+  require the actual loaded Persona partner and follow persona changes even with persistence off;
+  both engines freeze that owner for delegated legs. Activity stays separate from agents, controls,
+  wakes and model usage. These paired contracts require the updated Mind and Persona together.
+
+### Fixed
+
+- Council, MAGI, auxiliary actors and flow legs keep their own model and effort in the live
+  tree and F9 when abbreviated roles collide or identical roles use different inline pins.
+  Runtime callbacks carry exact attempt identity; retries clear stale observations and terminal
+  rows use the engine's observed model. Saved model assignments remain keyed by the full role.
+- Terminal-result capture survives reactivation of the same extension and tracker. Shutdown
+  revokes the old archive owner without removing the capture observers or changing their order
+  before completion notifications; late results cannot enter another session's archive.
+- Child broker contacts confirm one-way delivery only after admission to the host bus.
+  Full inboxes, disconnects, cancellation and missing receipts no longer report `delivered: true`.
+  Receipts are bounded and never count as a supervisor answer or authorization.
+  Unconfirmed sends and errors after admission no longer claim that the message was dropped;
+  the supervisor may already have received it.
+- Reference-flow diagnostics fence worker excerpts even on the defensive missing-reference path.
+- A worker-provided patch remains usable after worktree capture fails, with an explicit warning
+  that the patch was not verified against the final worktree state.
+
+## [1.17.4](https://github.com/AeonDave/pi-persona/releases/tag/v1.17.4) - 2026-10-25
+
+### Added
+
+- Voluntary Exocom collaboration: generation-bound shared tasks with atomic pickup/write claims,
+  expiring optional invitations, bounded attributed evidence publication and self-reported profiles.
+  Stale ownership remains visible without automatic takeover; task/evidence reads are paginated.
+  See [the collaboration guide](docs/COLLABORATION.md) for the authority and retention contracts.
+- Uniform operator views across every pi-persona surface: tool cards and commands use compact
+  purpose lines with shared-literal expansion (monitor, timer, models, read_result, agent_name,
+  contact_supervisor, contact_peer); session cards share the delegate-family frame (`Event · datum`
+  titles, indented clipped lines, boilerplate-free compact with drift-guarded projections, full
+  payload on expansion); the agent tree and F9 overlay show each leg's effort sigla (`mn l m h xh mx`,
+  off renders nothing) with honest requested→observed divergence, and delegate launch cards show the
+  full effort level next to the model.
+- Audited all operator notifications: bounded and sanitized toasts, single-surface settlement
+  announcements (done/stopped announce once via the follow-up card; failures keep their immediate
+  durable surface).
+- Installed-tarball qualification harness (`scripts/qualify-package.mjs`): packs and inspects the
+  artifact, installs it into isolated temporary hosts, and exercises real delegation, stop and
+  shutdown on both engines with a faux provider, network tripwires and empty credential stores.
+  Current policy: latest stable Pi only (1.4.0); historical host versions are rejected.
+- Per-leg thinking/effort: a typed `thinking` level on agents, delegate single/batch calls, roster
+  and council members, and auxiliary actors. Precedence is explicit leg/member > agent definition >
+  the existing configured/inherited child setting; malformed values fail before launch. Both engines
+  report requested and observed Pi effort separately (an observation is Pi's requested effort, never
+  a claim about provider cognition); the child engine passes a separate `--thinking` argument and the
+  model-suffix synthesis is gone.
+- Bounded durable terminal results: settled delegate/council/flow outcomes are saved as versioned
+  session entries with immutable `result:<UUID>` references (count/byte budgets, honest truncation
+  and storage receipts). `intercom results` lists them and `intercom result { ref, offset, limit }`
+  reads pages after reload — read-only: no respawn, no rebilling, no extra wake. The restore notice
+  now distinguishes vanished runtime work from retained terminal reports.
+
+### Fixed
+
+- Show every council/flow participant's launch model and requested effort, including auxiliary
+  judges and repeated roles with distinct inline selections. Persist the receipt for history;
+  pending model setup remains explicit. Role hints omit code and technical identifiers rather than
+  turning environment-variable names or Git refs into reviewer labels.
+- Treat failed model-availability reads as unavailable rather than advertising the whole catalog.
+  Session identity failures remain explicit and cannot reuse a previous owner or synthesize a
+  process-based identity; branch recovery restores the persisted name.
+- Admit granted bridge communication tools through Pi 1.4's plain tool allowlist, so a read-only
+  worker can still contact its supervisor. Empty grants, explicit exclusions and semantic bus denial
+  remain restrictive; sibling contact requires peer opt-in.
+- Refuse incompatible reference-flow journal versions and non-successful archived phases without
+  respawning completed work, including unapproved saved checkpoints. Retain truncation provenance
+  in resumed previews and final reports.
+- Label compact status usage as cumulative input/output tokens, distinct from context occupancy.
+- Preserve observed model identity after recovery in terminal results and completion views, while
+  launch cards retain the original selection. Requested and observed values remain distinguishable.
+- Announce a successful or stopped async run ONCE: the completion follow-up card is the single
+  settlement surface (the tree row already settles immediately); the duplicate info toast is gone.
+  Failures keep their immediate durable card/sanitized toast.
+- Pin isolated worktree exports to the starting commit, preserving worker commits together with later
+  uncommitted changes and new files in the returned patch.
+- Keep unanswered supervisor decisions/interviews unresolved instead of suggesting implicit approval.
+  Expose explicit outcomes and suppress bus activity for already-cancelled calls.
+
+### Removed
+
+- Remove the `/persona none` alias; use `/persona off` to deactivate the current persona.
+- Remove obsolete host API facades, the CJS-only Pi resolver fallback, unused session/notifier
+  options, unemitted identity-message aliases and redundant internal re-exports. Callers and test
+  fixtures now use the current Pi contracts directly.
+
+### Changed
+
+- Clarify and regression-test `/persona restore`: overwrite all bundled defaults without pruning
+  additional custom personas, agents or resources. Settings, credentials and sessions are not reset.
+- Target the latest stable Pi only (currently 1.4.0): development pins, `MIN_PI_VERSION`, docs and
+  the package-qualification gate move together, and historical host versions are rejected. A scoped
+  development override pins `undici` past known advisories inside the Pi 1.4.0 host dependency tree.
+- Align source SDK smoke checks with the canonical settings store and the current interactive vs
+  headless execution contract; settings qualification also rejects historical host versions.
 
 ## [1.17.3](https://github.com/AeonDave/pi-persona/tree/v1.17.3) - 2026-10-23
 

package/README.md

@@ -1,7 +1,7 @@
 # pi-persona
 
 <p align="center">
-  <img src="assets/banner.png" alt="pi-persona — supervised multi-agent orchestration for Pi">
+  <img src="https://raw.githubusercontent.com/AeonDave/pi-persona/v1.17.5/assets/banner.png" alt="pi-persona — supervised multi-agent orchestration for Pi">
 </p>
 
 [![CI](https://github.com/AeonDave/pi-persona/actions/workflows/test.yml/badge.svg?branch=main)](https://github.com/AeonDave/pi-persona/actions/workflows/test.yml) [![OpenSSF Scorecard](https://api.scorecard.dev/projects/github.com/AeonDave/pi-persona/badge)](https://scorecard.dev/viewer/?uri=github.com/AeonDave/pi-persona) [![npm version](https://img.shields.io/npm/v/@aeondave/pi-persona?logo=npm)](https://www.npmjs.com/package/@aeondave/pi-persona) [![License](https://img.shields.io/github/license/AeonDave/pi-persona)](LICENSE)
@@ -17,7 +17,8 @@ you can inspect workers, redirect them, or stop a run while it is in progress.
 
 ## Install
 
-Requires **Pi ≥ 1.0.0**, **Node.js ≥ 22.19**, and **Git**. Configure a model provider in Pi first.
+Requires **the latest stable Pi (currently 1.4.0)**, **Node.js ≥ 22.19**, and **Git**.
+Update Pi together with this plugin; historical Pi releases are not maintained. Configure a model provider in Pi first.
 
 Run in your terminal:
 
@@ -39,9 +40,9 @@ your customizations.
 | Install option | Command |
 |---|---|
 | This project only | `pi install -l npm:@aeondave/pi-persona` |
-| Pin this release | `pi install npm:@aeondave/pi-persona@1.17.3` |
+| Pin this release | `pi install npm:@aeondave/pi-persona@1.17.5` |
 | Update an unpinned install | `pi update npm:@aeondave/pi-persona` |
-| Git tag 1.17.3 | `pi install git:github.com/AeonDave/pi-persona@v1.17.3` |
+| Git tag 1.17.5 | `pi install git:github.com/AeonDave/pi-persona@v1.17.5` |
 
 Restart Pi after updating. For a pinned install, install the new version or tag explicitly.
 If switching from a Git install, remove that source first with
@@ -52,7 +53,8 @@ then install the npm package. Keep only one source configured to avoid loading t
 
 | Capability | What you get |
 |---|---|
-| **Async workers** | Specialists with their own roles, skills, and models; results return while the supervisor continues other work |
+| **Async workers** | Specialists with their own roles, skills, models, and thinking levels; results return while the supervisor continues other work |
+| **Retained results** | Bounded reports remain available after reload and can be read in pages without restarting workers |
 | **Live steering** | Inspect a worker, send guidance, or stop a run from the agent panel |
 | **Cross-session collaboration** | Exocom connects independent Pi sessions to exchange findings and coordinate work |
 | **Councils and flows** | Compare perspectives, run repair-and-check loops, or organize work into stages |
@@ -119,8 +121,9 @@ To enable Exocom, open two terminals in the same workspace and start each with:
 pi --exocom --persona dev
 ```
 
-Then ask one session to consult the other or agree who handles which files.
-Use `/exocom` to inspect the connection and workspace code.
+Use `/exocom` to inspect the connection and workspace code. Sessions can exchange one-way messages,
+record a voluntary task, or share a bounded evidence excerpt. Creating a task does not start work in
+the other session; a peer chooses whether to take it.
 
 A session in another workspace can join using that exact, case-sensitive code:
 
@@ -129,10 +132,11 @@ pi --exocom=Ab0T --persona researcher
 ```
 
 Replace `Ab0T` with the code shown by `/exocom`. Both sessions must run on the same machine and
-share a Pi agent directory. A peer joining from another workspace can advise and exchange results;
-it cannot claim files in the joined workspace.
+share a Pi agent directory. A peer joining from another workspace can advise, exchange results, and
+take read-only tasks; it cannot claim or take tasks that declare write paths in the joined workspace.
 
-See the [collaboration guide](docs/EXPERIENCE.md#work-with-another-pi-through-exocom) for day-to-day use.
+See the [cross-session collaboration guide](docs/COLLABORATION.md) for the task, invitation, ask and
+evidence workflows.
 
 ## Choose a persona
 
@@ -170,10 +174,11 @@ See [the reference](docs/REFERENCE.md) for an inline council example and recover
 Edit installed personas and agents in `~/.pi/agent/persona/agents/`, or add project-specific
 overrides in `.pi/agents/`. Run `/persona reload` after editing.
 
-`/persona seed` preserves existing files. **`/persona restore` replaces bundled defaults**, so use it
-only when you intend to discard customizations to those files.
-
-For optional long-term memory, add [pi-persona-mind](https://github.com/AeonDave/pi-persona-mind).
+`/persona seed` preserves existing files. **`/persona restore` overwrites all bundled defaults**
+(personas, agents, teams, flows, contracts, presets and shared prompts), discarding customizations
+to those files. It does not delete additional custom files: a persona `pippo.md` or an agent
+`pluto.md` remains untouched. A custom file using the same destination as a bundled default is
+replaced. Settings, credentials, sessions and project-local overrides are not reset.
 
 `/persona-settings` is separate from Pi's `/settings`: it edits pi-persona preferences and saved
 persona model assignments, not native Pi or compaction settings. In the TUI, `/` filters settings,
@@ -181,11 +186,20 @@ persona model assignments, not native Pi or compaction settings. In the TUI, `/`
 changes apply after restarting Pi or Pi's native `/reload`, not `/new`; `/persona reload` only
 refreshes persona definitions. Model changes apply to future runs. See [configuration and settings](docs/REFERENCE.md#configuration-and-data).
 
+## Optional memory companion
+
+[pi-persona-mind 0.8.4](https://github.com/AeonDave/pi-persona-mind/releases/tag/v0.8.4) adds durable
+project/persona memory, session notes and a visible automatic consolidation worker. It requires
+pi-persona 1.17.5 or later. Install it with `pi install npm:@aeondave/pi-persona-mind`, then restart
+Pi or run `/reload`. See its [README](https://github.com/AeonDave/pi-persona-mind#readme) for scope,
+automatic-review limits and undo.
+
 ## Documentation
 
 | Guide | What's inside |
 |---|---|
 | [Everyday use](docs/EXPERIENCE.md) | Choosing a persona, following work, and reading results |
+| [Cross-session collaboration](docs/COLLABORATION.md) | Voluntary tasks, optional offers, asks, evidence and presence between Pi sessions |
 | [Customization reference](docs/REFERENCE.md) | Tool APIs, configuration, and copyable recipes |
 | [Strategies](docs/STRATEGIES.md) | Teams, councils, flows, and orchestration options |
 | [Timers and monitors](docs/MONITORS.md) | Reminders and programs that wake the supervisor |
@@ -205,8 +219,10 @@ npm test
 ```
 
 Pi loads the TypeScript extension directly; there is no build step.
-To qualify a separately installed Pi 1.3.0 host without cloud calls or your profile, run
-`node --import tsx scripts/qualify-host.mjs <absolute-path-to-pi-coding-agent-package>`.
+Qualify the installed tarball on the current host without provider traffic or your profile with
+`node scripts/qualify-package.mjs --host <absolute-path-to-pi-coding-agent-package>`.
+The narrower source-SDK contract check is
+`node --import tsx scripts/qualify-host.mjs <absolute-path-to-pi-coding-agent-package>`; both reject historical host versions.
 The [CI workflow](https://github.com/AeonDave/pi-persona/actions/workflows/test.yml) runs strict
 typechecking, dependency auditing and the test suite on Linux and Windows. The OpenSSF badge links to the project's
 scored supply-chain checks; it is not a certification that the code is free of vulnerabilities.