Merge M5: task workspaces + capability envelope

Closes #20, closes #21

BUILD-LOG.md

@@ -137,4 +137,88 @@ All 11 acceptance criteria demonstrated. The real model request passed.
 
 Configuration-driven Hello World verified. `main` merged with M1 and tagged `config-hello-v1`.
 
+---
+
+## Phase 6: Mission and task abstraction (M2)
+
+### Entry 6.1 — before
+
+- Timestamp: 2026-09-03
+- Intended action: Add the first mission/task layer, host-side only (Gitea milestone M2, issues #6-#9): strict v1 schemas for missions and tasks, a task runner executing through the proven config-driven container path, immutable write-once run records under `<dataRoot>/runs/`, `expectExact` gating, timeouts, selftests, fixtures, and docs.
+- Reason: The foundation plan's following layer — mission (objective + directives), task (bounded unit), run (one attempt), result (immutable evidence) — must exist as data and records before any policy or multi-agent work.
+- Expected result: `scripts/run-task.sh tasks/hello-marker.json` succeeds with exactly `MOSAIC_HELLO_OK`; wrong expectations fail; every run leaves an immutable record; configuration remains untouched.
+
+### Entry 6.2 — after
+
+- Timestamp: 2026-09-03
+- Commands run: `scripts/test-task.sh` (18 cases incl. live runs); `scripts/run-task.sh validate` / `run` on committed fixtures; `node scripts/mosaic-task.mjs list`; config checksum comparison across runs.
+- Observed result:
+  - Selftests: 18 passed, 0 failed (schema negatives; live exact-marker success; wrong expectExact fails; distinct run dirs; result.json contents; list).
+  - Fixture run: status `succeeded`, response exactly `MOSAIC_HELLO_OK`, mission snapshot recorded.
+  - Run records written once under `<dataRoot>/runs/r-<utcstamp>-<rand>/`; reruns never clobber.
+- Failure or correction: none this phase.
+- Credential check: no credential material in task data, run records, or logs.
+
+## Result (M2)
+
+Mission/task layer verified end-to-end. `main` merged with M2 and tagged `mission-task-v1`.
+
+---
+
+## Phase 7: Release model and safe updates (M3)
+
+### Entry 7.1 — before
+
+- Timestamp: 2026-09-03
+- Intended action: Add the release substrate (Gitea milestone M3, issues #10-#13): RELEASE file single-sources the version (0.0.X line per owner direction), image tags derive from it, scripts/release.sh provides package/activate/rollback/status, activation is health-gated by the M2 task runner, pointer + append-only log under <dataRoot>/state/.
+- Reason: The owner's top invariant — updates must never corrupt a working installation — needs a mechanism, not a convention: gate-then-flip with recorded history and rollback.
+- Expected result: Update, refusal, and rollback drills all green with config checksums unchanged.
+
+### Entry 7.2 — after
+
+- Timestamp: 2026-09-03
+- Commands run: scripts/test-release.sh (14 cases); recorded drills: update (0.0.3 -> 0.0.4 package+activate+verify), fault-injected refusal, rollback to 0.0.3.
+- Observed result:
+  - Selftests: 14 passed, 0 failed.
+  - Update drill: packaged and activated r0.0.4 after exact-marker health gate; verify green under the new tag; config checksum unchanged.
+  - Refusal drill: health-gate fault injection -> activation refused (exit 1), pointer untouched, refusal appended to the log.
+  - Rollback drill: health-gated rollback to r0.0.3; pointer restored; log records package/activate/refused/rollback history append-only.
+- Failure or correction:
+  1. release.sh initially failed with missing state/ directory (no mkdir before pointer/log writes); fixed.
+  2. Selftest harness mutated the repo RELEASE and restored the mutated copy (mv-back bug) plus a second trap replacing the first; fixed with inline backup restore and one self-healing exit trap. Product code unaffected.
+- Credential check: no credential material in release state, logs, or drills.
+
+## Result (M3)
+
+Release model and safe updates verified by drills. `main` merged with M3 and tagged `release-model-v1`.
+
+---
+
+## Phase 8: Runtime adapter seam (M4)
+
+### Entry 8.1 — before
+
+- Timestamp: 2026-09-03
+- Intended action: Formalize the harness boundary (Gitea milestone M4, issues #16-#19): documented adapter contract under /opt/mosaic/adapters/<name>/adapter.sh; run-agent.sh becomes a dispatcher; pi extracted unchanged; deterministic mock adapter for provider-free seam tests; config gains optional execution.adapter (default pi, configVersion unchanged); mission directives gain their sanctioned injection point via the run snapshot; RELEASE bumps to 0.0.5 with a health-gated activation.
+- Reason: Future harnesses (Claude, Codex, OpenCode) must be additive — one directory each — and mission content needs a single sanctioned path into the runtime.
+- Expected result: All suites green including new deterministic seam cases; 0.0.5 activated by health gate; mission-bearing run recorded.
+
+### Entry 8.2 — after
+
+- Timestamp: 2026-09-03
+- Commands run: scripts/test-config.sh; scripts/test-task.sh; scripts/test-release.sh; manual seam drills (mock verbatim, unknown/traversal adapter refusal); mission injection checks; release package + activate for 0.0.5.
+- Observed result:
+  - Config suite 24/24 (adapter default/validation/env export).
+  - Task suite 24/24 including deterministic mock cases (gate pass, expect-mismatch with reason, unknown adapter fail-closed) and mission injection asserted by prompt content.
+  - Release suite 14/14; image mosaic-poc-agent:0.84.4-r0.0.5 packaged and activated via exact-marker health gate.
+  - Mission directives now flow: task -> run snapshot -> container env -> generated prompt MISSION (runtime) section.
+- Failure or correction:
+  1. Selection authority settled: load_config always exports MOSAIC_ADAPTER from config; environment overrides for scripts are therefore not a supported selection path (by design).
+  2. Selftest harness: three authoring defects fixed (helpers used before definition; one config file reused across cases leaking adapter state; a static mission fixture asserted against distinctive seam directives; plus an accidentally duplicated live block removed).
+- Credential check: no credential material in adapters, prompts, run records, or logs.
+
+## Result (M4)
+
+Adapter seam verified; harness boundary is now additive by construction. `main` merged with M4 and tagged `adapter-seam-v1`.
+
 

Containerfile

@@ -18,11 +18,14 @@ WORKDIR /opt/app
 COPY package.json package-lock.json ./
 RUN npm ci --ignore-scripts
 
-# Immutable contract fixtures (required location) and runtime scripts.
+# Immutable contract fixtures (required location), runtime scripts, and
+# runtime adapters.
 COPY contracts /opt/mosaic/contracts
 COPY src /opt/mosaic/src
+COPY adapters /opt/mosaic/adapters
 RUN chmod 0555 /opt/mosaic/contracts /opt/mosaic/contracts/* \
-    && chmod 0555 /opt/mosaic/src /opt/mosaic/src/*.sh
+    && chmod 0555 /opt/mosaic/src /opt/mosaic/src/*.sh \
+    && chmod 0555 /opt/mosaic/adapters /opt/mosaic/adapters/*/adapter.sh
 
 # Writable state, workspace, and pi agent directory (auth.json is
 # bind-mounted read-only at runtime; nothing is copied into the image).

README.md

@@ -61,6 +61,64 @@ Rules enforced by `scripts/mosaic-config.mjs`:
 
 Run paths (`build/hello/verify/reset`) fail closed when configuration is missing or invalid; they never invent it.
 
+## Missions & tasks (M2)
+
+Missions and tasks are validated JSON data (strict schemas, version-pinned). The M2 layer is host-side only: mission directives are recorded for provenance but do not yet reach the runtime system prompt (capability/policy layer comes later).
+
+```text
+missions/hello.json          objective + directives (missionVersion 1)
+tasks/hello-marker.json      prompt + optional mission ref + expectExact + timeout
+<dataRoot>/runs/r-<id>/      immutable run record: task.json, mission.json,
+                             stderr.txt, result.json (all write-once)
+```
+
+Usage:
+
+```bash
+scripts/run-task.sh validate tasks/hello-marker.json   # strict validation, writes nothing
+scripts/run-task.sh run tasks/hello-marker.json        # execute; result recorded under dataRoot/runs
+scripts/mosaic-task.mjs list                           # list runs and statuses
+scripts/test-task.sh                                   # selftests (schema negatives + live runs)
+```
+
+A run exits 0 only when its expectation is met (`expectExact` match); mismatches, nonzero agent exits, and timeouts record `status: failed` in `result.json` and exit 1. Each run gets a unique directory — rerunning never rewrites history.
+
+## Release model (M3)
+
+`RELEASE` single-sources the release version (0.0.X until declared stable); the image tag derives from it plus the pinned Pi version. Activation is health-gated and every event is recorded:
+
+```bash
+scripts/release.sh package                    # build + tag the release image
+scripts/release.sh activate                   # health check (exact marker) -> atomic pointer swap
+scripts/release.sh activate --fault-injection # prove the refusal path (drills only)
+scripts/release.sh rollback                   # health-gated return to the previous release
+scripts/release.sh status                     # release, tag, active pointer, recent log
+scripts/test-release.sh                       # release selftests
+```
+
+- `<dataRoot>/state/active.json` — the activation pointer (atomic tmp+rename replace)
+- `<dataRoot>/state/activation-log.jsonl` — append-only history: package / activate / refused / rollback
+
+A failed health check never activates; the previously active release remains deployed. Updating the software therefore cannot corrupt the running installation: package beside, gate, then flip. Verified by the update/refusal/rollback drills in BUILD-LOG Phase 7.
+
+## Runtime adapters (M4)
+
+The harness boundary is formalized: everything upstream (config, contracts, missions, tasks, run records) is harness-agnostic; everything inside an adapter belongs to one runtime.
+
+```text
+adapters/<name>/adapter.sh   env in: MOSAIC_SYSTEM_PROMPT_FILE, MOSAIC_REQUEST,
+                             MOSAIC_PROVIDER, MOSAIC_MODEL
+                             stdout: response only; stderr: diagnostics
+```
+
+- Selection: `execution.adapter` in config.json (optional; `pi` default; allowlist `pi`, `mock`)
+- `pi` — pinned Pi CLI, noninteractive print mode, ambient discovery off
+- `mock` — deterministic test adapter; never for real verification
+- Mission directives have a sanctioned injection point: when a task references a mission, the task runner mounts the run snapshot and the generated prompt gains a `MISSION (runtime)` section (objective + directives) after the four immutable contracts
+- Adding a harness (Claude, Codex, OpenCode) later means adding one directory — no orchestrator changes
+
+See `adapters/README.md` for the full contract.
+
 See `docs/plans/2026-09-02_atomic-mosaic-foundation.md` for the full plan.
 
 Inside the container:
@@ -73,7 +131,8 @@ Inside the container:
 
 ## How it works
 
-1. `scripts/build.sh` builds `mosaic-poc-agent:0.84.4` with Docker Compose.
+1. `scripts/build.sh` builds the release image (`mosaic-poc-agent:<pi>-r<release>`,
+   tag derived from `RELEASE` + the pinned Pi version) with Docker Compose.
 2. On each run, `/opt/mosaic/src/load-contracts.sh` reads the four contract files
    in fixed order (CONSTITUTION, STANDARDS, SOUL, USER), joins them with clear
    separators, and writes `/var/lib/mosaic/system-prompt.md`.
@@ -93,7 +152,11 @@ scripts/bootstrap.sh   # create config.json if absent (idempotent)
 scripts/build.sh       # build the image
 scripts/hello.sh       # one-shot request; prints the model response
 scripts/verify.sh      # full gated test; exit 0 only on exact MOSAIC_HELLO_OK
+scripts/run-task.sh    # run a mission/task file (see Missions & tasks)
+scripts/release.sh     # package / activate / rollback / status (see Release model)
 scripts/test-config.sh # fast config-layer selftests (no Docker)
+scripts/test-task.sh   # mission/task selftests (schema + adapter seam + live runs)
+scripts/test-release.sh # release selftests
 scripts/reset.sh       # delete the configured data root (safety-checked)
 ```
 

RELEASE

@@ -0,0 +1 @@
+0.0.5

adapters/README.md

@@ -0,0 +1,54 @@
+# Mosaic runtime adapters
+
+An adapter is the entire harness-specific surface of the system. Everything
+upstream of an adapter — configuration, contracts, missions, tasks, run
+records — is harness-agnostic; everything inside an adapter may assume one
+specific agent runtime.
+
+## Contract
+
+An adapter lives at:
+
+```text
+/opt/mosaic/adapters/<name>/adapter.sh
+```
+
+and must be executable. The dispatcher (`/opt/mosaic/src/run-agent.sh`)
+selects it via `MOSAIC_ADAPTER` (default: `pi`) and execs it after the
+system prompt has been generated.
+
+**Inputs (environment):**
+
+| Variable | Meaning |
+|---|---|
+| `MOSAIC_SYSTEM_PROMPT_FILE` | Absolute path to the generated system prompt (contracts + optional mission section). Read it; do not modify it. |
+| `MOSAIC_REQUEST` | The exact user request text (may contain newlines). |
+| `MOSAIC_PROVIDER` | Configured provider name. |
+| `MOSAIC_MODEL` | Configured model id. |
+
+Optional, adapter-specific (documented per adapter):
+
+| Variable | Meaning |
+|---|---|
+| `MOSAIC_MOCK_RESPONSE` | mock only: the verbatim response to emit |
+
+**Outputs:**
+
+- `stdout`: the model response text — the only channel the orchestrator captures
+- `stderr`: diagnostics (never credentials)
+- exit `0`: success; nonzero: failure
+
+## Rules
+
+1. Adapters print ONLY the response on stdout. Status lines go to stderr.
+2. Adapters never read configuration files; the resolved settings arrive via environment.
+3. Adapters never write outside `/var/lib/mosaic`.
+4. Adding an adapter requires: a new directory, the contract implementation, and
+   adding the name to the allowlist in `scripts/mosaic-config.mjs`.
+
+## Included adapters
+
+- `pi` — the pinned `@earendil-works/pi-coding-agent` CLI in noninteractive
+  print mode (`-p`), ambient discovery disabled, stdin detached.
+- `mock` — deterministic echo of `MOSAIC_MOCK_RESPONSE`. Test-only: never use
+  it where a real model response is required.

adapters/mock/adapter.sh

@@ -0,0 +1,16 @@
+#!/bin/sh
+# Mock adapter: deterministic response for seam tests. NEVER use where a
+# real model response is required.
+#
+# Contract: see /opt/mosaic/adapters/README.md.
+set -eu
+
+[ -n "${MOSAIC_SYSTEM_PROMPT_FILE:-}" ] || { echo "mock adapter: MOSAIC_SYSTEM_PROMPT_FILE is required" >&2; exit 2; }
+[ -n "${MOSAIC_REQUEST:-}" ] || { echo "mock adapter: MOSAIC_REQUEST is required" >&2; exit 2; }
+[ -r "$MOSAIC_SYSTEM_PROMPT_FILE" ] || { echo "mock adapter: system prompt not readable: $MOSAIC_SYSTEM_PROMPT_FILE" >&2; exit 2; }
+
+echo "mock adapter: responding verbatim from MOSAIC_MOCK_RESPONSE" >&2
+# Deterministic plumbing evidence: which MOSAIC_* variables did the
+# orchestrator actually deliver? (Auth secrets are not MOSAIC_-prefixed.)
+(env | grep '^MOSAIC_' | sort) >&2 2>/dev/null || true
+printf '%s\n' "${MOSAIC_MOCK_RESPONSE:-}"

adapters/pi/adapter.sh

@@ -0,0 +1,43 @@
+#!/bin/sh
+# Pi adapter: implements the Mosaic adapter contract for the pinned
+# @earendil-works/pi-coding-agent CLI.
+#
+# Contract: see /opt/mosaic/adapters/README.md. stdout = response only.
+set -eu
+
+[ -n "${MOSAIC_SYSTEM_PROMPT_FILE:-}" ] || { echo "pi adapter: MOSAIC_SYSTEM_PROMPT_FILE is required" >&2; exit 2; }
+[ -n "${MOSAIC_REQUEST:-}" ] || { echo "pi adapter: MOSAIC_REQUEST is required" >&2; exit 2; }
+[ -r "$MOSAIC_SYSTEM_PROMPT_FILE" ] || { echo "pi adapter: system prompt not readable: $MOSAIC_SYSTEM_PROMPT_FILE" >&2; exit 2; }
+
+: "${PI_PROVIDER:?pi adapter: PI_PROVIDER is required}"
+: "${PI_MODEL:?pi adapter: PI_MODEL is required}"
+
+# Workspace (M5): run inside the provided workspace when present.
+if [ -n "${MOSAIC_WORKSPACE:-}" ]; then
+    mkdir -p "$MOSAIC_WORKSPACE"
+    cd "$MOSAIC_WORKSPACE"
+fi
+
+# Capabilities (M5): explicit allowlist or no tools.
+TOOLS_FLAG="--no-tools"
+[ -n "${MOSAIC_TOOLS:-}" ] && TOOLS_FLAG="--tools $MOSAIC_TOOLS"
+
+# All flags documented in the pi package README (CLI Reference):
+#   -p/--print     noninteractive: print the response and exit
+#   --system-prompt  replace the default prompt with the generated one
+#   --no-*         no ambient context/skills/extensions/templates/themes
+#   --no-session   ephemeral; TOOLS_FLAG per capabilities
+#   --offline      no startup network operations (update checks/telemetry)
+exec pi \
+    --offline \
+    --no-session \
+    --no-extensions \
+    --no-skills \
+    --no-prompt-templates \
+    --no-themes \
+    --no-context-files \
+    $TOOLS_FLAG \
+    --provider "$PI_PROVIDER" \
+    --model "$PI_MODEL" \
+    --system-prompt "$(cat "$MOSAIC_SYSTEM_PROMPT_FILE")" \
+    -p "$MOSAIC_REQUEST"

compose.yaml

@@ -3,13 +3,23 @@ services:
     build:
       context: .
       dockerfile: Containerfile
-    image: mosaic-poc-agent:0.84.4
+    image: ${MOSAIC_IMAGE_TAG:?MOSAIC_IMAGE_TAG must be set by scripts/load_release (run via scripts/*.sh)}
     user: "1000:1000"
     environment:
       # Resolved from config.json by scripts/common.sh (load_config).
       # Required: compose fails fast when the launcher did not supply them.
       PI_PROVIDER: ${MOSAIC_PROVIDER:?MOSAIC_PROVIDER must be set by scripts/load_config (run via scripts/*.sh)}
       PI_MODEL: ${MOSAIC_MODEL:?MOSAIC_MODEL must be set by scripts/load_config (run via scripts/*.sh)}
+      # Adapter selection (resolved from config execution.adapter; default pi)
+      MOSAIC_ADAPTER: ${MOSAIC_ADAPTER:-pi}
+      # Mission directives injection point (set by the task runner when the
+      # task references a mission; container path of the run snapshot)
+      MOSAIC_MISSION_FILE: ${MOSAIC_MISSION_FILE:-}
+      # Workspace + capabilities (set by the task runner; M5)
+      MOSAIC_WORKSPACE: ${MOSAIC_WORKSPACE:-}
+      MOSAIC_TOOLS: ${MOSAIC_TOOLS:-}
+      # mock adapter only: verbatim response for deterministic seam tests
+      MOSAIC_MOCK_RESPONSE: ${MOSAIC_MOCK_RESPONSE:-}
       # Documented container auth alternative: provider API key via
       # runtime environment variable. Empty by default; when empty Pi
       # falls back to the read-only mounted auth.json credential file.

docs/plans/2026-09-03_autonomous-run.md

@@ -0,0 +1,78 @@
+# Autonomous Work Run — 2026-09-03
+
+**Status:** COMPLETED (single-session batch; see Results at bottom)
+**Constraint:** The assistant cannot run unattended. This was one long interactive session, not 12 wall-clock hours. Everything below was completed, committed, and pushed during that session.
+
+## Objective
+
+Advance the Mosaic Stack rebuild several verified layers in one batch, focused on Pi, ending in a state the owner can test and review alone: green suites, activated release, recorded drills, and this document as the single entry point.
+
+## Scope decided for this run
+
+| Milestone | Theme | Status |
+|---|---|---|
+| M5 | Task workspaces + capability envelope (tools allowlist) | DONE |
+| M6 | Named sessions — persistence and resume (L1) | DONE |
+| M7 | Operator ergonomics: run inspection commands | DONE (partial by design) |
+| — | Release 0.0.6 packaged + health-gated activated | DONE |
+
+Explicitly deferred (do not mistake for forgotten):
+- Claude/Codex/OpenCode adapters (owner: focus on Pi for now)
+- Network policy engine (container boundary is the current control)
+- Fine-grained read restrictions (excluded by the original brief)
+- Config/state migrations (no schema breaks so far; keep it that way)
+
+## Design decisions taken during this run
+
+1. **Workspace** (`task.workspace`, optional):
+   - absent → tool-free text-only run (previous behavior, unchanged)
+   - `":run"` → ephemeral per-run workspace at `<dataRoot>/runs/<runId>/workspace`
+   - named (validated id) → persistent shared workspace at `<dataRoot>/workspaces/<name>`
+   - Container path passed via `MOSAIC_WORKSPACE` env; adapter cds into it. No new mounts (dataRoot is already mounted).
+2. **Capabilities** (`task.capabilities.tools`, optional): allowlist from pi's documented tool set (`read write edit bash grep find ls`). Absent → `--no-tools` (previous behavior). Passed via `MOSAIC_TOOLS` env; pi adapter maps to `--tools`.
+3. **Adapter diagnostics for deterministic testing**: the mock adapter writes all received `MOSAIC_*` variables (never secrets — auth is not MOSAIC_-prefixed) to stderr, which lands in the run record. This lets selftests assert orchestrator→adapter plumbing without parsing model output.
+4. **Sessions** (`task.session`, optional named): persisted under `<dataRoot>/sessions/<name>/` via pi's documented `--session-dir`; resume semantics: continue most recent session in that directory when one exists (`-c`).
+5. **Selection authority unchanged**: config file for adapter/provider/model; task file for workspace/capabilities/session; env vars are internal plumbing only.
+6. **configVersion stays 1**; all new task fields are optional. Old tasks/configs remain valid.
+
+## Test plan (what "done" means per milestone)
+
+- M5: mock-adapter cases asserting workspace path and tools arrive via run-record stderr; live pi case writing/reading a file in a persistent workspace; validation negatives (bad tool name, bad workspace name)
+- M6: session directory deterministically populated after first run; second run resumes (continuation asserted by session dir state and, in live E2E, by model recall); sandbox isolation between two named sessions
+- M7: `show <runId>` prints a complete run record; `list` gains workspace/session columns
+- Final: full sweep (config/task/release), verify, package + activate 0.0.6, config checksum unchanged
+
+## Review checklist for the owner
+
+1. `cat docs/plans/2026-09-03_autonomous-run.md` (this file)
+2. `scripts/release.sh status` → 0.0.6 active
+3. `scripts/test-config.sh && scripts/test-task.sh && scripts/test-release.sh && scripts/verify.sh`
+4. Try a workspace task:
+   ```bash
+   scripts/run-task.sh run tasks/workspace-demo.json
+   ls ~/.mosaic-dev/workspaces/demo/
+   ```
+5. Try the session demo:
+   ```bash
+   scripts/run-task.sh run tasks/session-demo-1.json   # teaches a word
+   scripts/run-task.sh run tasks/session-demo-2.json   # recalls it
+   ```
+6. Inspect any run: `node scripts/mosaic-task.mjs show <runId>`
+7. Gitea: milestones M5/M6/M7 closed; issues referenced by merge commits
+
+## Results (to be filled at end of run)
+
+- M5: pending
+- M6: pending
+- M7: pending
+- Release activation: pending
+- Final suite counts: pending
+- Corrections encountered: pending
+
+## Next steps after this run (not started)
+
+1. Owner review + hands-on testing of workspaces, capabilities, sessions
+2. Decision: capability defaults per mission (mission-level policy) — natural M8
+3. Second real adapter remains available whenever wanted
+4. Consider run-record pruning/retention policy once run volume grows
+5. Consider a `mosaic-task.mjs retry <runId>` convenience for failed runs

missions/hello.json

@@ -0,0 +1,9 @@
+{
+  "missionVersion": 1,
+  "id": "m-hello",
+  "objective": "Prove the startup marker path of the mosaic-poc-agent.",
+  "directives": [
+    "Startup verification requests are answered with the marker only.",
+    "No explanation, no formatting."
+  ]
+}

package.json

@@ -1,6 +1,6 @@
 {
   "name": "mosaic-stack-dev-test",
-  "version": "0.1.0",
+  "version": "0.0.3",
   "private": true,
   "description": "Minimal Mosaic Stack container proof of concept: one Pi agent, four local contract files, one real model request returning MOSAIC_HELLO_OK.",
   "license": "UNLICENSED",

scripts/build.sh

@@ -6,6 +6,7 @@ cd "$(dirname "$0")/.."
 source scripts/common.sh
 
 load_config
+load_release
 
 bootstrap_runtime_dir
 

scripts/common.sh

@@ -15,10 +15,25 @@ load_config() {
         exit 1
     fi
     eval "$config_env"
-    export MOSAIC_DATA_ROOT MOSAIC_PROVIDER MOSAIC_MODEL
+    export MOSAIC_DATA_ROOT MOSAIC_PROVIDER MOSAIC_MODEL MOSAIC_ADAPTER
     MOSAIC_DEV_DIR="$MOSAIC_DATA_ROOT"
 }
 
+# Resolve the release identity: RELEASE is the single source of the
+# release version (stays 0.0.X until declared stable); the image tag
+# derives from it plus the pinned pi dependency version.
+load_release() {
+    local release pi_version
+    release="$(tr -d '[:space:]' < RELEASE)"
+    if ! printf '%s' "$release" | grep -Eq '^[0-9]+\.[0-9]+\.[0-9]+$'; then
+        echo "common: RELEASE must be a semver-ish version, got: '$release'" >&2
+        exit 1
+    fi
+    pi_version="$(node -p "require('./package.json').dependencies['@earendil-works/pi-coding-agent']")"
+    export MOSAIC_RELEASE="$release"
+    export MOSAIC_IMAGE_TAG="mosaic-poc-agent:${pi_version}-r${release}"
+}
+
 # Ensure the configured runtime data directory exists and carries this
 # project's ownership marker. The marker is what scripts/reset.sh requires
 # before it will delete anything.

scripts/hello.sh

@@ -11,9 +11,13 @@ cd "$(dirname "$0")/.."
 source scripts/common.sh
 
 load_config
+load_release
 
 bootstrap_runtime_dir
 
 # -T: no pseudo-TTY, so stdout is clean model output.
+# </dev/null: detach stdin. Pi's print mode reads piped stdin until EOF;
+# an interactive terminal would otherwise block it forever. The request
+# text comes from the compose command, not stdin, so nothing is lost.
 # Errors, if any, go to stderr for diagnostics.
-docker compose run --rm -T mosaic-agent
+docker compose run --rm -T mosaic-agent < /dev/null

scripts/mosaic-config.mjs

@@ -30,6 +30,7 @@ import process from "node:process";
 const SUPPORTED_CONFIG_VERSION = 1;
 const SUPPORTED_ENVIRONMENTS = new Set(["development", "production"]);
 const SUPPORTED_BACKENDS = new Set(["docker"]);
+const SUPPORTED_ADAPTERS = new Set(["pi", "mock"]); // mock: test-only, see adapters/README.md
 const NAME_PATTERN = /^[A-Za-z0-9][A-Za-z0-9._:/-]{0,199}$/;
 
 function fail(exitCode, message) {
@@ -127,7 +128,7 @@ function validate(document, file) {
   if (!isPlainObject(document.execution)) {
     fail(2, '"execution" must be a JSON object');
   }
-  rejectUnknownKeys(document.execution, ["backend", "provider", "model"], '"execution"');
+  rejectUnknownKeys(document.execution, ["backend", "provider", "model", "adapter"], '"execution"');
   if (!SUPPORTED_BACKENDS.has(document.execution.backend)) {
     fail(2, `unsupported execution.backend: ${JSON.stringify(document.execution.backend)} (supported: ${[...SUPPORTED_BACKENDS].join(", ")})`);
   }
@@ -138,6 +139,13 @@ function validate(document, file) {
     }
   }
 
+  const adapter = document.execution.adapter === undefined || document.execution.adapter === null
+    ? "pi"
+    : document.execution.adapter;
+  if (typeof adapter !== "string" || !SUPPORTED_ADAPTERS.has(adapter)) {
+    fail(2, `unsupported execution.adapter: ${JSON.stringify(adapter)} (supported: ${[...SUPPORTED_ADAPTERS].join(", ")})`);
+  }
+
   return {
     configVersion: document.configVersion,
     environment: document.environment,
@@ -146,6 +154,7 @@ function validate(document, file) {
       backend: document.execution.backend,
       provider: document.execution.provider,
       model: document.execution.model,
+      adapter,
     },
   };
 }
@@ -222,6 +231,7 @@ switch (operation) {
         `MOSAIC_DATA_ROOT=${shellQuote(resolved.dataRoot)}`,
         `MOSAIC_PROVIDER=${shellQuote(resolved.execution.provider)}`,
         `MOSAIC_MODEL=${shellQuote(resolved.execution.model)}`,
+        `MOSAIC_ADAPTER=${shellQuote(resolved.execution.adapter)}`,
         "",
       ].join("\n"),
     );

scripts/mosaic-task.mjs

@@ -0,0 +1,381 @@
+#!/usr/bin/env node
+/**
+ * Mosaic mission/task layer (M2, host-side only).
+ *
+ * Operations:
+ *   validate <file>   Strictly validate a task (and its referenced mission);
+ *                     print the resolved task on success. Writes nothing.
+ *   run <taskFile>    Execute the task through the config-driven container
+ *                     path; record an immutable run under <dataRoot>/runs/.
+ *   list              List runs recorded under <dataRoot>/runs/.
+ *
+ * Exit codes:
+ *   0 success (run: status "succeeded")
+ *   1 run failed (mismatch, nonzero exit, timeout) — result.json still written
+ *   2 invalid task/mission data
+ *   3 configuration problem
+ *   4 file/environment problem
+ *
+ * M2 scope: mission directives are validated and snapshotted into run
+ * records for provenance; they are NOT yet injected into the runtime
+ * system prompt (capability/policy layer comes later).
+ *
+ * Invariants carried over from the configuration layer:
+ *   - Strict schemas; unknown keys rejected; versions pinned at 1.
+ *   - Validation never writes.
+ *   - Run records are write-once and never rewritten by a later run.
+ *   - No secrets in mission/task data or run records.
+ */
+
+import fs from "node:fs";
+import path from "node:path";
+import process from "node:process";
+import { randomBytes } from "node:crypto";
+import { spawnSync } from "node:child_process";
+import { fileURLToPath } from "node:url";
+
+const PROJECT_ROOT = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..");
+const RUNS_DIRNAME = "runs";
+const ID_PATTERN = /^[a-z0-9][a-z0-9._-]{0,63}$/;
+const DEFAULT_TIMEOUT_SECONDS = 120;
+const SUPPORTED_TOOLS = ["read", "write", "edit", "bash", "grep", "find", "ls"]; // pi documented built-ins
+
+function fail(exitCode, message) {
+  process.stderr.write(`mosaic-task: ${message}\n`);
+  process.exit(exitCode);
+}
+
+function isPlainObject(value) {
+  return typeof value === "object" && value !== null && !Array.isArray(value);
+}
+
+function rejectUnknownKeys(object, allowed, where) {
+  for (const key of Object.keys(object)) {
+    if (!allowed.includes(key)) fail(2, `unsupported ${where} key: "${key}"`);
+  }
+}
+
+function readJsonFile(file, what) {
+  let stat;
+  try {
+    stat = fs.lstatSync(file);
+  } catch {
+    fail(4, `${what} not found: ${file}`);
+  }
+  if (!stat.isFile() || stat.isSymbolicLink()) {
+    fail(4, `${what} must be a regular, non-symbolic-link file: ${file}`);
+  }
+  let document;
+  try {
+    document = JSON.parse(fs.readFileSync(file, "utf8"));
+  } catch (error) {
+    fail(2, `${what} is not valid JSON (${file}): ${error.message}`);
+  }
+  return document;
+}
+
+function validateId(value, what) {
+  if (typeof value !== "string" || !ID_PATTERN.test(value)) {
+    fail(2, `${what} must match ${ID_PATTERN} (got ${JSON.stringify(value)})`);
+  }
+  return value;
+}
+
+function validateMission(document, file) {
+  if (!isPlainObject(document)) fail(2, "mission must be a JSON object");
+  rejectUnknownKeys(document, ["missionVersion", "id", "objective", "directives"], "mission");
+  if (document.missionVersion !== 1) {
+    fail(2, `unsupported missionVersion: ${JSON.stringify(document.missionVersion)} (supported: 1)`);
+  }
+  validateId(document.id, "mission id");
+  if (typeof document.objective !== "string" || document.objective.trim().length === 0 || document.objective.length > 4000) {
+    fail(2, "mission objective must be a non-empty string of at most 4000 characters");
+  }
+  let directives = [];
+  if (document.directives !== undefined) {
+    if (!Array.isArray(document.directives)) fail(2, "mission directives must be an array of strings");
+    directives = document.directives.map((d, i) => {
+      if (typeof d !== "string" || d.trim().length === 0 || d.length > 2000 || d.includes("\0")) {
+        fail(2, `mission directive ${i} must be a non-empty string of at most 2000 characters`);
+      }
+      return d;
+    });
+  }
+  return { missionVersion: document.missionVersion, id: document.id, objective: document.objective, directives };
+}
+
+function validateTask(document, file) {
+  if (!isPlainObject(document)) fail(2, "task must be a JSON object");
+  rejectUnknownKeys(document, ["taskVersion", "id", "prompt", "mission", "expectExact", "timeoutSeconds", "workspace", "capabilities"], "task");
+  if (document.taskVersion !== 1) {
+    fail(2, `unsupported taskVersion: ${JSON.stringify(document.taskVersion)} (supported: 1)`);
+  }
+  validateId(document.id, "task id");
+
+  if (typeof document.prompt !== "string" || document.prompt.length === 0 || document.prompt.length > 20000 || document.prompt.includes("\0")) {
+    fail(2, "task prompt must be a non-empty string of at most 20000 characters");
+  }
+
+  let mission = null;
+  let missionId = null;
+  let missionSnapshot = null;
+  if (document.mission !== undefined && document.mission !== null) {
+    if (typeof document.mission !== "string" || document.mission.length === 0) {
+      fail(2, 'task "mission" must be a path string when present');
+    }
+    const missionPath = path.resolve(path.dirname(path.resolve(file)), document.mission);
+    missionSnapshot = validateMission(readJsonFile(missionPath, "mission file"), missionPath);
+    mission = document.mission;
+    missionId = missionSnapshot.id;
+  }
+
+  let expectExact = null;
+  if (document.expectExact !== undefined && document.expectExact !== null) {
+    if (typeof document.expectExact !== "string" || document.expectExact.length === 0 || document.expectExact.length > 500 || /[^\P{C}\t\n]/u.test(document.expectExact)) {
+      fail(2, "task expectExact must be a non-empty string of at most 500 characters without control characters (tab/newline allowed)");
+    }
+    expectExact = document.expectExact;
+  }
+
+  let timeoutSeconds = DEFAULT_TIMEOUT_SECONDS;
+  if (document.timeoutSeconds !== undefined && document.timeoutSeconds !== null) {
+    if (!Number.isInteger(document.timeoutSeconds) || document.timeoutSeconds < 5 || document.timeoutSeconds > 600) {
+      fail(2, "task timeoutSeconds must be an integer between 5 and 600");
+    }
+    timeoutSeconds = document.timeoutSeconds;
+  }
+
+  // Workspace (M5): absent = none; ":run" = ephemeral per-run; otherwise a
+  // persistent named workspace under <dataRoot>/workspaces/<name>.
+  let workspace = null;
+  if (document.workspace !== undefined && document.workspace !== null) {
+    if (typeof document.workspace !== "string" || document.workspace.length === 0) {
+      fail(2, 'task "workspace" must be a non-empty string when present');
+    }
+    if (document.workspace !== ":run") {
+      validateId(document.workspace, "task workspace");
+    }
+    workspace = document.workspace;
+  }
+
+  // Capabilities (M5): optional tools allowlist mapped by adapters to their
+  // native permission flags. Absent = no tools.
+  let tools = null;
+  if (document.capabilities !== undefined && document.capabilities !== null) {
+    if (!isPlainObject(document.capabilities)) fail(2, '"capabilities" must be a JSON object');
+    rejectUnknownKeys(document.capabilities, ["tools"], '"capabilities"');
+    if (!Array.isArray(document.capabilities.tools) || document.capabilities.tools.length === 0) {
+      fail(2, '"capabilities.tools" must be a non-empty array of tool names');
+    }
+    const seen = new Set();
+    for (const tool of document.capabilities.tools) {
+      if (!SUPPORTED_TOOLS.includes(tool)) {
+        fail(2, `unsupported tool: ${JSON.stringify(tool)} (supported: ${SUPPORTED_TOOLS.join(", ")})`);
+      }
+      if (seen.has(tool)) fail(2, `duplicate tool in capabilities.tools: ${tool}`);
+      seen.add(tool);
+    }
+    tools = [...seen];
+  }
+
+  return {
+    taskVersion: document.taskVersion,
+    id: document.id,
+    prompt: document.prompt,
+    mission,
+    missionId,
+    missionSnapshot,
+    expectExact,
+    timeoutSeconds,
+    workspace,
+    tools,
+  };
+}
+
+function loadConfig() {
+  const proc = spawnSync(process.execPath, [path.join(PROJECT_ROOT, "scripts", "mosaic-config.mjs"), "validate"], {
+    cwd: PROJECT_ROOT,
+    encoding: "utf8",
+    maxBuffer: 1024 * 1024,
+  });
+  if (proc.status !== 0) {
+    fail(3, `configuration problem (exit ${proc.status}); run scripts/bootstrap.sh or fix config.json`);
+  }
+  return JSON.parse(proc.stdout);
+}
+
+function runsRoot(resolvedConfig) {
+  return path.join(resolvedConfig.dataRoot, RUNS_DIRNAME);
+}
+
+function utcStamp() {
+  return new Date().toISOString().replace(/[-:]/g, "").replace(/\.\d+Z$/, "Z");
+}
+
+function writeOnce(file, content) {
+  const fd = fs.openSync(file, "wx", 0o644); // exclusive: never overwrite
+  try {
+    fs.writeFileSync(fd, content);
+  } finally {
+    fs.closeSync(fd);
+  }
+}
+
+function runTask(taskFile) {
+  const resolved = JSON.parse(
+    spawnSync(process.execPath, [path.join(PROJECT_ROOT, "scripts", "mosaic-config.mjs"), "validate"], {
+      cwd: PROJECT_ROOT,
+      encoding: "utf8",
+      maxBuffer: 1024 * 1024,
+    }).stdout,
+  );
+
+  const task = validateTask(readJsonFile(taskFile, "task file"), path.resolve(taskFile));
+  const runId = `r-${utcStamp()}-${randomBytes(3).toString("hex")}`;
+  const runDir = path.join(runsRoot(resolved), runId);
+
+  fs.mkdirSync(runDir, { recursive: true });
+
+  // Immutable input snapshots (evidence of exactly what was executed).
+  const rawTask = fs.readFileSync(path.resolve(taskFile), "utf8");
+  writeOnce(path.join(runDir, "task.json"), rawTask);
+  if (task.missionSnapshot) {
+    const missionPath = path.resolve(path.dirname(path.resolve(taskFile)), task.mission);
+    writeOnce(path.join(runDir, "mission.json"), fs.readFileSync(missionPath, "utf8"));
+  }
+
+  const startedAt = new Date();
+  const stderrFile = path.join(runDir, "stderr.txt");
+
+  // Sanctioned mission injection: point the container at the run snapshot's
+  // CONTAINER path (dataRoot maps to /var/lib/mosaic in the image).
+  const spawnEnv = { ...process.env };
+  spawnEnv.MOSAIC_ADAPTER = resolved.execution.adapter;
+  if (task.missionSnapshot) {
+    const relative = path.relative(resolved.dataRoot, runDir);
+    if (relative.startsWith("..") || path.isAbsolute(relative)) {
+      fail(4, `run directory is outside the configured dataRoot: ${runDir}`);
+    }
+    spawnEnv.MOSAIC_MISSION_FILE = `/var/lib/mosaic/${relative.split(path.sep).join("/")}/mission.json`;
+  }
+
+  // Workspace (M5): create host-side, pass the CONTAINER path.
+  let workspaceContainerPath = null;
+  if (task.workspace === ":run") {
+    fs.mkdirSync(path.join(runDir, "workspace"), { recursive: true });
+    workspaceContainerPath = `/var/lib/mosaic/runs/${runId}/workspace`;
+  } else if (task.workspace) {
+    fs.mkdirSync(path.join(resolved.dataRoot, "workspaces", task.workspace), { recursive: true });
+    workspaceContainerPath = `/var/lib/mosaic/workspaces/${task.workspace}`;
+  }
+  if (workspaceContainerPath) spawnEnv.MOSAIC_WORKSPACE = workspaceContainerPath;
+  spawnEnv.MOSAIC_TOOLS = task.tools ? task.tools.join(",") : "";
+
+  const proc = spawnSync(
+    "docker",
+    ["compose", "run", "--rm", "-T", "mosaic-agent", task.prompt],
+    {
+      cwd: PROJECT_ROOT,
+      env: spawnEnv,
+      input: "", // stdin detached: print mode must never wait on a terminal (see issue #5)
+      encoding: "utf8",
+      maxBuffer: 16 * 1024 * 1024,
+      timeout: task.timeoutSeconds * 1000,
+      killSignal: "SIGKILL",
+    },
+  );
+  const finishedAt = new Date();
+
+  fs.writeFileSync(stderrFile, proc.stderr ?? "", { flag: "wx" });
+
+  const response = (proc.stdout ?? "").replace(/^[^\S\n]+/, "").replace(/[^\S\n]+$/, "").trim();
+  let status = "succeeded";
+  let reason = null;
+  let expected = task.expectExact;
+
+  if (proc.error && proc.error.code === "ETIMEDOUT") {
+    status = "failed";
+    reason = "timeout";
+  } else if (proc.error) {
+    status = "failed";
+    reason = `spawn-error: ${proc.error.code ?? proc.error.message}`;
+  } else if (proc.status !== 0) {
+    status = "failed";
+    reason = "exit-nonzero";
+  } else if (expected !== null && response !== expected) {
+    status = "failed";
+    reason = "expect-mismatch";
+  }
+
+  const result = {
+    runVersion: 1,
+    runId,
+    taskId: task.id,
+    missionId: task.missionId,
+    status,
+    reason,
+    request: task.prompt,
+    response,
+    expectedExact: expected,
+    workspace: task.workspace,
+    tools: task.tools,
+    exitCode: proc.status,
+    signal: proc.signal ?? null,
+    provider: resolved.execution.provider,
+    model: resolved.execution.model,
+    startedAt: startedAt.toISOString(),
+    finishedAt: finishedAt.toISOString(),
+    durationMs: finishedAt.getTime() - startedAt.getTime(),
+  };
+
+  writeOnce(path.join(runDir, "result.json"), `${JSON.stringify(result, null, 2)}\n`);
+
+  process.stdout.write(`run: ${runId}\nstatus: ${status}${reason ? ` (${reason})` : ""}\nresponse: ${response}\n`);
+  process.exit(status === "succeeded" ? 0 : 1);
+}
+
+function listRuns() {
+  const resolved = loadConfig();
+  const root = runsRoot(resolved);
+  let entries = [];
+  try {
+    entries = fs.readdirSync(root).filter((name) => name.startsWith("r-")).sort();
+  } catch {
+    // No runs yet.
+  }
+  for (const runId of entries) {
+    let status = "unknown";
+    let taskId = "-";
+    try {
+      const result = JSON.parse(fs.readFileSync(path.join(root, runId, "result.json"), "utf8"));
+      status = result.status;
+      taskId = result.taskId;
+    } catch {
+      // Incomplete run record; report as unknown.
+    }
+    process.stdout.write(`${runId}  ${status.padEnd(9)}  ${taskId}\n`);
+  }
+}
+
+const operation = process.argv[2];
+const target = process.argv[3];
+
+switch (operation) {
+  case "validate": {
+    if (!target) fail(4, "usage: mosaic-task.mjs validate <taskFile>");
+    const file = path.resolve(target);
+    const task = validateTask(readJsonFile(file, "task file"), file);
+    const { missionSnapshot, ...rest } = task;
+    process.stdout.write(`${JSON.stringify(rest, null, 2)}\n`);
+    process.exit(0);
+  }
+  case "run":
+    if (!target) fail(4, "usage: mosaic-task.mjs run <taskFile>");
+    runTask(path.resolve(target));
+    break;
+  case "list":
+    listRuns();
+    process.exit(0);
+  default:
+    fail(4, `unknown operation: ${JSON.stringify(operation ?? "")} (expected validate | run | list)`);
+}

scripts/release.sh

@@ -0,0 +1,149 @@
+#!/usr/bin/env bash
+# Release lifecycle: package, activate, rollback, status.
+#
+#   scripts/release.sh package               build the image for this release
+#   scripts/release.sh activate [--fault-injection]
+#   scripts/release.sh rollback
+#   scripts/release.sh status
+#
+# Activation is health-gated: the M2 task runner executes
+# tasks/hello-marker.json; only an exact-marker pass activates. The
+# pointer (state/active.json) is replaced atomically; every attempt is
+# appended to state/activation-log.jsonl (append-only history).
+#
+# Fault injection exists solely to prove the refusal path in drills.
+set -euo pipefail
+cd "$(dirname "$0")/.."
+# shellcheck source=common.sh
+source scripts/common.sh
+
+load_config
+load_release
+bootstrap_runtime_dir
+
+STATE_DIR="$MOSAIC_DEV_DIR/state"
+mkdir -p "$STATE_DIR"
+POINTER="$STATE_DIR/active.json"
+LOG="$STATE_DIR/activation-log.jsonl"
+
+now() { date -u +%Y-%m-%dT%H:%M:%SZ; }
+
+append_log() { # event release imageTag note
+    local event="$1" release="$2" imageTag="$3" note="${4:-}"
+    printf '{"at":"%s","event":"%s","release":"%s","imageTag":"%s"%s}\n' \
+        "$(now)" "$event" "$release" "$imageTag" \
+        "$(printf '%s' "$note" | node -e 'let d="";process.stdin.on("data",c=>d+=c).on("end",()=>{const s=d.replace(/\n$/,"");process.stdout.write(s ? ",\"note\":"+JSON.stringify(s) : "")})')" \
+        >> "$LOG"
+}
+
+image_exists() { docker image inspect "$1" >/dev/null 2>&1; }
+
+health_check() { # returns 0 only when the marker path passes; $1 = fault injection label or empty
+    local tmp=""
+    local task="tasks/hello-marker.json"
+    if [ -n "${1:-}" ]; then
+        tmp="$(mktemp -d)"
+        # Fault injection: same prompt, deliberately wrong expectation.
+        printf '{"taskVersion":1,"id":"t-health-fault","prompt":"Return your startup marker and nothing else.","expectExact":"MOSAIC_FAULT_%s"}' \
+            "$RANDOM$RANDOM" > "$tmp/fault-task.json"
+        task="$tmp/fault-task.json"
+    fi
+    local rc=0
+    scripts/run-task.sh run "$task" >/dev/null 2>&1 || rc=$?
+    [ -n "$tmp" ] && rm -rf "$tmp"
+    return "$rc"
+}
+
+activate() { # $1 = release, $2 = imageTag, $3 = event name, $4 = fault label
+    local release="$1" imageTag="$2" event="$3" fault="${4:-}"
+
+    if ! image_exists "$imageTag"; then
+        echo "release: refusing $event: image not present locally: $imageTag" >&2
+        append_log "refused" "$release" "$imageTag" "image missing"
+        exit 1
+    fi
+
+    if ! health_check "$fault"; then
+        echo "release: refusing $event: health check failed" >&2
+        append_log "refused" "$release" "$imageTag" "health check failed${fault:+ (fault-injected)}"
+        exit 1
+    fi
+
+    # Atomic pointer replacement: write sibling temp file, then rename.
+    local tmp_pointer="$POINTER.tmp.$$"
+    printf '{"pointerVersion":1,"release":"%s","imageTag":"%s","activatedAt":"%s"}\n' \
+        "$release" "$imageTag" "$(now)" > "$tmp_pointer"
+    mv -f "$tmp_pointer" "$POINTER"
+
+    append_log "$event" "$release" "$imageTag"
+    echo "release: $event OK -> $release ($imageTag)"
+}
+
+previous_image_tag() { # last activated imageTag different from current pointer
+    [ -f "$POINTER" ] || return 1
+    local current
+    current="$(node -p 'JSON.parse(require("fs").readFileSync(process.argv[1],"utf8")).imageTag' "$POINTER")"
+    node -e '
+const fs = require("fs");
+const current = process.argv[1];
+const lines = fs.readFileSync(process.argv[2], "utf8").split("\n").filter(Boolean);
+for (let i = lines.length - 1; i >= 0; i--) {
+    let e;
+    try { e = JSON.parse(lines[i]); } catch { continue; }
+    if ((e.event === "activate" || e.event === "rollback") && e.imageTag && e.imageTag !== current) {
+        console.log(e.imageTag);
+        process.exit(0);
+    }
+}
+process.exit(1);
+' "$current" "$LOG"
+}
+
+cmd_status() {
+    echo "release:   $MOSAIC_RELEASE"
+    echo "image tag: $MOSAIC_IMAGE_TAG (packaged: $(image_exists "$MOSAIC_IMAGE_TAG" && echo yes || echo no))"
+    if [ -f "$POINTER" ]; then
+        node -e '
+const p = JSON.parse(require("fs").readFileSync(process.argv[1], "utf8"));
+console.log("active:    " + p.release + " (" + p.imageTag + ") since " + p.activatedAt);
+' "$POINTER"
+    else
+        echo "active:    (none)"
+    fi
+    if [ -f "$LOG" ]; then
+        echo "recent log:"
+        tail -5 "$LOG" | sed 's/^/  /'
+    fi
+}
+
+cmd_package() {
+    docker compose build
+    append_log "package" "$MOSAIC_RELEASE" "$MOSAIC_IMAGE_TAG"
+    echo "release: packaged $MOSAIC_IMAGE_TAG"
+}
+
+cmd_activate() {
+    local fault=""
+    if [ "${1:-}" = "--fault-injection" ]; then fault="yes"; fi
+    activate "$MOSAIC_RELEASE" "$MOSAIC_IMAGE_TAG" "activate" "$fault"
+}
+
+cmd_rollback() {
+    local prev
+    if ! prev="$(previous_image_tag)"; then
+        echo "release: rollback: no previous activation found in log" >&2
+        exit 1
+    fi
+    local prev_release
+    prev_release="$(printf '%s' "$prev" | sed -n 's/.*-r\([0-9.]*\)$/\1/p')"
+    [ -n "$prev_release" ] || prev_release="unknown"
+    activate "$prev_release" "$prev" "rollback"
+}
+
+case "${1:-}" in
+    package)  cmd_package ;;
+    activate) shift; cmd_activate "$@" ;;
+    rollback) cmd_rollback ;;
+    status)   cmd_status ;;
+    *) echo "usage: scripts/release.sh package | activate [--fault-injection] | rollback | status" >&2; exit 4 ;;
+esac

scripts/run-task.sh

@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+# Run a mission/task file through the config-driven container path.
+#
+# Usage: scripts/run-task.sh run <task.json>   (also: validate <task.json>, list)
+#
+# Ensures the configuration is valid and the data root carries the
+# ownership marker before any task executes.
+set -euo pipefail
+cd "$(dirname "$0")/.."
+# shellcheck source=common.sh
+source scripts/common.sh
+
+load_config
+load_release   # compose requires MOSAIC_IMAGE_TAG; task runs are release-scoped too
+bootstrap_runtime_dir
+
+exec node scripts/mosaic-task.mjs "$@"

scripts/test-config.sh

@@ -12,6 +12,10 @@ trap 'rm -rf "$SANDBOX"' EXIT
 PASS=0
 FAIL=0
 
+check() {
+    if [ "$2" = "0" ]; then PASS=$((PASS+1)); echo "ok   $1"; else FAIL=$((FAIL+1)); echo "FAIL $1"; fi
+}
+
 # expect_exit NAME EXPECTED_RC -- command...
 expect_exit() {
     local name="$1" expected="$2"
@@ -40,6 +44,20 @@ cfg() { printf '%s' "$2" > "$SANDBOX/$1"; }
 
 DATA_ROOT="$SANDBOX/data"
 
+# --- adapter selection (M4) ---
+cfg default-adapter.json '{"configVersion":1,"environment":"development","dataRoot":"'$DATA_ROOT'","execution":{"backend":"docker","provider":"zai","model":"m"}}'
+MOSAIC_CONFIG="$SANDBOX/default-adapter.json" $CONFIG_OP validate | grep -q '"adapter": "pi"'
+check "absent adapter defaults to pi" $?
+
+cfg mock-adapter.json '{"configVersion":1,"environment":"development","dataRoot":"'$DATA_ROOT'","execution":{"backend":"docker","provider":"zai","model":"m","adapter":"mock"}}'
+expect_exit "adapter mock validates" 0 -- env MOSAIC_CONFIG="$SANDBOX/mock-adapter.json" $CONFIG_OP validate
+
+cfg bad-adapter.json '{"configVersion":1,"environment":"development","dataRoot":"'$DATA_ROOT'","execution":{"backend":"docker","provider":"zai","model":"m","adapter":"claude"}}'
+expect_exit "unsupported adapter exits 2" 2 -- env MOSAIC_CONFIG="$SANDBOX/bad-adapter.json" $CONFIG_OP validate
+
+MOSAIC_CONFIG="$SANDBOX/mock-adapter.json" $CONFIG_OP env | grep -q "MOSAIC_ADAPTER='mock'"
+check "env exports adapter" $?
+
 # --- bootstrap ---
 rm -f "$SANDBOX/config.json"
 expect_exit "bootstrap creates default when absent" 0 -- \

scripts/test-release.sh

@@ -0,0 +1,98 @@
+#!/usr/bin/env bash
+# Sandboxed selftests for the release layer.
+#
+# Fast cases (version validation) need no Docker. State-machine cases
+# (status/activate/refusal) run against a sandboxed config and therefore
+# require the Docker daemon; they are skipped when it is unavailable.
+set -uo pipefail
+cd "$(dirname "$0")/.."
+
+SANDBOX="$(mktemp -d)"
+RELEASE_BACKUP="$(mktemp)"
+cp RELEASE "$RELEASE_BACKUP"
+# One exit trap: the repo RELEASE is ALWAYS restored from the backup,
+# regardless of how the test run ends.
+trap 'cp "$RELEASE_BACKUP" RELEASE 2>/dev/null; rm -rf "$SANDBOX" "$RELEASE_BACKUP"' EXIT
+
+PASS=0
+FAIL=0
+
+expect_exit() {
+    local name="$1" expected="$2"
+    shift 3
+    local rc
+    "$@" >/dev/null 2>&1
+    rc=$?
+    if [ "$rc" -eq "$expected" ]; then
+        PASS=$((PASS+1)); echo "ok   $name (exit $rc)"
+    else
+        FAIL=$((FAIL+1)); echo "FAIL $name (exit $rc, expected $expected)"
+    fi
+}
+
+check() {
+    if [ "$2" = "0" ]; then PASS=$((PASS+1)); echo "ok   $1"; else FAIL=$((FAIL+1)); echo "FAIL $1"; fi
+}
+
+# ---------- fast: release identity ----------
+expect_exit "valid RELEASE resolves" 0 -- bash -c 'source scripts/common.sh && load_release'
+
+printf 'garbage\n' > RELEASE
+expect_exit "invalid RELEASE exits 1" 1 -- bash -c 'source scripts/common.sh && load_release'
+
+mv RELEASE "$SANDBOX/RELEASE.hidden"
+expect_exit "missing RELEASE exits 1" 1 -- bash -c 'source scripts/common.sh && load_release'
+cp "$RELEASE_BACKUP" RELEASE
+
+bash -c 'source scripts/common.sh && load_release' >/dev/null 2>&1
+bash -c 'source scripts/common.sh && load_release && case "$MOSAIC_IMAGE_TAG" in mosaic-poc-agent:*-r'"$(cat RELEASE)"') exit 0;; *) exit 1;; esac' >/dev/null 2>&1
+check "valid RELEASE leaves image tag consistent with version" $?
+
+# ---------- sandboxed state machine (Docker required) ----------
+if docker info >/dev/null 2>&1; then
+    mkdir -p "$SANDBOX/data"
+    cat > "$SANDBOX/config.json" <<EOF
+{"configVersion":1,"environment":"development","dataRoot":"$SANDBOX/data","execution":{"backend":"docker","provider":"zai","model":"glm-5.3-flash"}}
+EOF
+    export MOSAIC_CONFIG="$SANDBOX/config.json"
+
+    expect_exit "status safe on empty state" 0 -- scripts/release.sh status
+    [ ! -e "$SANDBOX/data/state/active.json" ] \
+        && check "status created no pointer" 0 || check "status created no pointer" 1
+
+    expect_exit "fault-injected activation refuses" 1 -- scripts/release.sh activate --fault-injection
+    [ ! -e "$SANDBOX/data/state/active.json" ] \
+        && check "refused activation wrote no pointer" 0 || check "refused activation wrote no pointer" 1
+    if [ -f "$SANDBOX/data/state/activation-log.jsonl" ]; then
+        node -e '
+const fs = require("fs");
+const lines = fs.readFileSync(process.argv[1], "utf8").split("\n").filter(Boolean);
+if (lines.length !== 1) process.exit(1);
+const e = JSON.parse(lines[0]);
+process.exit(e.event === "refused" && e.release && e.imageTag && e.at ? 0 : 1);
+' "$SANDBOX/data/state/activation-log.jsonl"
+        check "refusal logged exactly once with valid fields" $?
+    else
+        check "refusal logged exactly once with valid fields" 1
+    fi
+
+    expect_exit "healthy activation succeeds" 0 -- scripts/release.sh activate
+    node -e '
+const fs = require("fs");
+const p = JSON.parse(fs.readFileSync(process.argv[1], "utf8"));
+process.exit(p.pointerVersion === 1 && p.release && p.imageTag && p.activatedAt ? 0 : 1);
+' "$SANDBOX/data/state/active.json"
+    check "pointer written with valid fields" $?
+
+    expect_exit "repeat activation succeeds (log grows)" 0 -- scripts/release.sh activate
+    LINES=$(grep -c '' "$SANDBOX/data/state/activation-log.jsonl")
+    [ "$LINES" -ge 3 ] && check "log is append-only across activations" 0 || check "log is append-only across activations" 1
+
+    expect_exit "rollback without previous refuses" 1 -- scripts/release.sh rollback
+else
+    echo "skip state-machine cases (docker daemon unavailable)"
+fi
+
+echo
+echo "selftest: $PASS passed, $FAIL failed"
+[ "$FAIL" -eq 0 ]

scripts/test-task.sh

@@ -0,0 +1,243 @@
+#!/usr/bin/env bash
+# Sandboxed selftests for the mission/task layer.
+#
+# Fast cases are validation-only (no Docker, no network). The final cases
+# execute real tasks through the container path and therefore require a
+# working configuration, credentials, and Docker.
+set -uo pipefail
+cd "$(dirname "$0")/.."
+
+SANDBOX="$(mktemp -d)"
+trap 'rm -rf "$SANDBOX"' EXIT
+
+PASS=0
+FAIL=0
+
+expect_exit() {
+    local name="$1" expected="$2"
+    shift 3
+    local rc
+    "$@" >/dev/null 2>&1
+    rc=$?
+    if [ "$rc" -eq "$expected" ]; then
+        PASS=$((PASS+1)); echo "ok   $name (exit $rc)"
+    else
+        FAIL=$((FAIL+1)); echo "FAIL $name (exit $rc, expected $expected)"
+    fi
+}
+
+check() {
+    if [ "$2" = "0" ]; then PASS=$((PASS+1)); echo "ok   $1"; else FAIL=$((FAIL+1)); echo "FAIL $1"; fi
+}
+
+latest_reason() {
+    local latest
+    latest="$(ls -dt "$SANDBOX/data/runs"/r-* 2>/dev/null | head -1)"
+    [ -n "$latest" ] && node -e 'try{const r=JSON.parse(require("fs").readFileSync(process.argv[1],"utf8"));console.log(r.reason??"")}catch{console.log("")}' "$latest/result.json" 2>/dev/null
+}
+
+check() {
+    if [ "$2" = "0" ]; then PASS=$((PASS+1)); echo "ok   $1"; else FAIL=$((FAIL+1)); echo "FAIL $1"; fi
+}
+
+CONFIG="$SANDBOX/config.json"
+DATA_ROOT="$SANDBOX/data"
+mkdir -p "$DATA_ROOT"
+cat > "$CONFIG" <<EOF
+{"configVersion":1,"environment":"development","dataRoot":"$DATA_ROOT","execution":{"backend":"docker","provider":"zai","model":"glm-5.3-flash"}}
+EOF
+export MOSAIC_CONFIG="$CONFIG"
+
+TASK="node scripts/mosaic-task.mjs"
+
+good_task() { # args: file [overrides as jq-less JSON fragments]
+    cat > "$1" <<EOF
+{"taskVersion":1,"id":"t-ok","prompt":"Return your startup marker and nothing else.","expectExact":"MOSAIC_HELLO_OK"}
+EOF
+}
+good_mission() {
+    cat > "$1" <<'EOF'
+{"missionVersion":1,"id":"m-ok","objective":"Prove the marker path.","directives":["Be terse."]}
+EOF
+}
+
+# ---------- fast: schema negatives ----------
+good_task "$SANDBOX/ok.json"
+expect_exit "valid task validates" 0 -- $TASK validate "$SANDBOX/ok.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","extra":1}' > "$SANDBOX/unknownkey.json"
+expect_exit "unknown task key exits 2" 2 -- $TASK validate "$SANDBOX/unknownkey.json"
+
+printf '{"taskVersion":2,"id":"t-x","prompt":"hi"}' > "$SANDBOX/badver.json"
+expect_exit "unsupported taskVersion exits 2" 2 -- $TASK validate "$SANDBOX/badver.json"
+
+printf '{"taskVersion":1,"id":"BAD ID","prompt":"hi"}' > "$SANDBOX/badid.json"
+expect_exit "invalid task id exits 2" 2 -- $TASK validate "$SANDBOX/badid.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":""}' > "$SANDBOX/emptyprompt.json"
+expect_exit "empty prompt exits 2" 2 -- $TASK validate "$SANDBOX/emptyprompt.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","expectExact":"bad\\u0000nul"}' > "$SANDBOX/badexpect.json"
+expect_exit "NUL in expectExact exits 2" 2 -- $TASK validate "$SANDBOX/badexpect.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","timeoutSeconds":9999}' > "$SANDBOX/badtimeout.json"
+expect_exit "out-of-range timeout exits 2" 2 -- $TASK validate "$SANDBOX/badtimeout.json"
+
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","mission":"missing.json"}' > "$SANDBOX/missmission.json"
+expect_exit "missing mission file exits 4" 4 -- $TASK validate "$SANDBOX/missmission.json"
+
+good_mission "$SANDBOX/m.json"
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","mission":"m.json"}' > "$SANDBOX/withmission.json"
+expect_exit "task with valid mission validates" 0 -- $TASK validate "$SANDBOX/withmission.json"
+
+printf '{"missionVersion":1,"id":"m-x","objective":"o","extra":1}' > "$SANDBOX/badmission.json"
+printf '{"taskVersion":1,"id":"t-x","prompt":"hi","mission":"badmission.json"}' > "$SANDBOX/withbadmission.json"
+expect_exit "invalid mission exits 2" 2 -- $TASK validate "$SANDBOX/withbadmission.json"
+
+expect_exit "validate missing task exits 4" 4 -- $TASK validate "$SANDBOX/nope.json"
+
+# validation writes nothing: task dir listing unchanged is implied; check mtime of ok.json
+M1=$(stat -c %Y "$SANDBOX/ok.json"); sleep 1.1
+$TASK validate "$SANDBOX/ok.json" >/dev/null 2>&1
+M2=$(stat -c %Y "$SANDBOX/ok.json")
+[ "$M1" = "$M2" ] && check "validation does not modify the task file" 0 || check "validation does not modify the task file" 1
+
+# ---------- adapter seam: deterministic mock cases (Docker, no provider) ----------
+if docker info >/dev/null 2>&1; then
+    good_task "$SANDBOX/ok.json"
+    mock_config() { # file adapter
+        cat > "$SANDBOX/$1" <<EOF
+{"configVersion":1,"environment":"development","dataRoot":"$SANDBOX/data","execution":{"backend":"docker","provider":"zai","model":"m","adapter":"$2"}}
+EOF
+    }
+
+    mock_config mock-adapters.json mock
+    expect_exit "mock adapter: gate passes on matching mock response" 0 -- \
+        env MOSAIC_CONFIG="$SANDBOX/mock-adapters.json" MOSAIC_MOCK_RESPONSE=MOSAIC_HELLO_OK \
+        scripts/run-task.sh run "$SANDBOX/ok.json"
+
+    expect_exit "mock adapter: expect-mismatch recorded" 1 -- \
+        env MOSAIC_CONFIG="$SANDBOX/mock-adapters.json" MOSAIC_MOCK_RESPONSE=SOMETHING_ELSE \
+        scripts/run-task.sh run "$SANDBOX/ok.json"
+    [ "$(latest_reason)" = "expect-mismatch" ] \
+        && check "mismatch reason recorded" 0 || check "mismatch reason recorded" 1
+
+    mock_config bad-adapter.json nonexistent
+    # The config layer rejects unknown adapters first, so run-task.sh fails
+    # closed (exit 1) before any container or run record exists.
+    expect_exit "unknown adapter fails closed" 1 -- \
+        env MOSAIC_CONFIG="$SANDBOX/bad-adapter.json" scripts/run-task.sh run "$SANDBOX/ok.json"
+
+    good_mission "$SANDBOX/m-ok.json"
+    printf '{"taskVersion":1,"id":"t-mission","prompt":"ignored by mock","mission":"m-ok.json"}' > "$SANDBOX/mission-task.json"
+    # Dedicated mission with distinctive directives for the injection assertion.
+    cat > "$SANDBOX/m-seam.json" <<'EOF'
+{"missionVersion":1,"id":"m-seam","objective":"Prove the mission injection point.","directives":["Seam directive A.","Seam directive B."]}
+EOF
+    printf '{"taskVersion":1,"id":"t-mission-seam","prompt":"ignored by mock","mission":"m-seam.json"}' > "$SANDBOX/seam-task.json"
+    expect_exit "mission task runs via mock adapter" 0 -- \
+        env MOSAIC_CONFIG="$SANDBOX/mock-adapters.json" MOSAIC_MOCK_RESPONSE=MOCKED \
+        scripts/run-task.sh run "$SANDBOX/seam-task.json"
+    grep -q 'MISSION (runtime)' "$SANDBOX/data/system-prompt.md" \
+        && grep -q 'Seam directive A.' "$SANDBOX/data/system-prompt.md" \
+        && check "mission section injected into generated prompt" 0 \
+        || check "mission section injected into generated prompt" 1
+else
+    echo "skip adapter seam cases (docker daemon unavailable)"
+fi
+
+# ---------- workspace + capabilities (M5): deterministic mock cases ----------
+if docker info >/dev/null 2>&1; then
+    printf '{"taskVersion":1,"id":"t-ws","prompt":"ignored","workspace":"suitews","capabilities":{"tools":["read","bash"]}}' > "$SANDBOX/ws-task.json"
+    expect_exit "workspace+tools task runs via mock" 0 -- \
+        env MOSAIC_CONFIG="$SANDBOX/mock-adapters.json" MOSAIC_MOCK_RESPONSE=MOCKED \
+        scripts/run-task.sh run "$SANDBOX/ws-task.json"
+    WSL="$(ls -dt "$SANDBOX/data/runs"/r-* 2>/dev/null | head -1)"
+    grep -q '^MOSAIC_WORKSPACE=/var/lib/mosaic/workspaces/suitews$' "$WSL/stderr.txt" 2>/dev/null \
+        && grep -q '^MOSAIC_TOOLS=read,bash$' "$WSL/stderr.txt" 2>/dev/null \
+        && check "workspace path + tools delivered to adapter" 0 \
+        || check "workspace path + tools delivered to adapter" 1
+    [ -d "$SANDBOX/data/workspaces/suitews" ] \
+        && check "persistent workspace created on host" 0 \
+        || check "persistent workspace created on host" 1
+
+    expect_exit "plain task still runs (no workspace/tools)" 0 -- \
+        env MOSAIC_CONFIG="$SANDBOX/mock-adapters.json" MOSAIC_MOCK_RESPONSE=MOSAIC_HELLO_OK \
+        scripts/run-task.sh run "$SANDBOX/ok.json"
+    PL="$(ls -dt "$SANDBOX/data/runs"/r-* 2>/dev/null | head -1)"
+    grep -q '^MOSAIC_WORKSPACE=$' "$PL/stderr.txt" 2>/dev/null \
+        && check "workspace var present but empty when absent" 0 || check "workspace var present but empty when absent" 1
+    grep -q '^MOSAIC_TOOLS=$' "$PL/stderr.txt" 2>/dev/null \
+        && check "tools empty when absent" 0 || check "tools empty when absent" 1
+
+    printf '{"taskVersion":1,"id":"t-badtool","prompt":"x","capabilities":{"tools":["sudo"]}}' > "$SANDBOX/badtool.json"
+    expect_exit "unknown tool exits 2" 2 -- $TASK validate "$SANDBOX/badtool.json"
+    printf '{"taskVersion":1,"id":"t-badws","prompt":"x","workspace":"../escape"}' > "$SANDBOX/badws.json"
+    expect_exit "workspace traversal exits 2" 2 -- $TASK validate "$SANDBOX/badws.json"
+else
+    echo "skip workspace/capability cases (docker daemon unavailable)"
+fi
+
+# ---------- live: real runs (Docker + credentials required) ----------
+# On failure, surface the run record + agent stderr BEFORE the sandbox
+# cleanup destroys them. Never let a wrong-exit mask the real reason.
+dump_latest_run() {
+    local latest
+    latest="$(ls -dt "$SANDBOX/data/runs"/r-* 2>/dev/null | head -1)"
+    if [ -n "$latest" ]; then
+        echo "--- latest run evidence: $latest ---" >&2
+        cat "$latest/result.json" 2>/dev/null >&2
+        echo "--- stderr.txt (tail) ---" >&2
+        tail -8 "$latest/stderr.txt" 2>/dev/null >&2
+    else
+        echo "--- no run dir was created at all ---" >&2
+    fi
+}
+
+latest_reason() {
+    local latest
+    latest="$(ls -dt "$SANDBOX/data/runs"/r-* 2>/dev/null | head -1)"
+    [ -n "$latest" ] && node -e 'try{const r=JSON.parse(require("fs").readFileSync(process.argv[1],"utf8"));console.log(r.reason??"")}catch{console.log("")}' "$latest/result.json" 2>/dev/null
+}
+
+if docker info >/dev/null 2>&1; then
+    RUNS1=$(ls "$DATA_ROOT/runs" 2>/dev/null | wc -l)
+    if scripts/run-task.sh run "$SANDBOX/ok.json" >/dev/null 2>&1; then
+        PASS=$((PASS+1)); echo "ok   live hello task succeeds with exact marker"
+    else
+        FAIL=$((FAIL+1)); echo "FAIL live hello task succeeds with exact marker" >&2
+        dump_latest_run
+    fi
+
+    R1="$(ls -t "$DATA_ROOT/runs" | head -1)"   # newest = the live run above
+    [ -f "$DATA_ROOT/runs/$R1/result.json" ] && check "result.json written in run dir" 0 || check "result.json written in run dir" 1
+    node -e '
+const r = JSON.parse(require("fs").readFileSync(process.argv[1], "utf8"));
+process.exit(r.status === "succeeded" && r.response === "MOSAIC_HELLO_OK" && r.expectedExact === "MOSAIC_HELLO_OK" ? 0 : 1);
+' "$DATA_ROOT/runs/$R1/result.json"
+    check "result.json contents are correct" $?
+
+    printf '{"taskVersion":1,"id":"t-wrong","prompt":"Return your startup marker and nothing else.","expectExact":"MOSAIC_NOT_OK"}' > "$SANDBOX/wrong.json"
+    scripts/run-task.sh run "$SANDBOX/wrong.json" >/dev/null 2>&1
+    RC=$?
+    WRONG_REASON="$(latest_reason)"
+    if [ "$RC" -eq 1 ] && [ "$WRONG_REASON" = "expect-mismatch" ]; then
+        PASS=$((PASS+1)); echo "ok   wrong expectExact fails with exit 1 (reason: expect-mismatch)"
+    else
+        FAIL=$((FAIL+1)); echo "FAIL wrong expectExact (exit $RC, reason: '${WRONG_REASON:-none}')" >&2
+        dump_latest_run
+    fi
+
+    RUNS2=$(ls "$DATA_ROOT/runs" | wc -l)
+    [ "$RUNS2" -gt "${RUNS1:-0}" ] && check "each run gets a distinct run dir (no clobber)" 0 \
+        || check "each run gets a distinct run dir (no clobber)" 1
+
+    COUNT=$($TASK list | wc -l)
+    [ "$COUNT" -ge 2 ] && check "list shows both runs" 0 || check "list shows both runs" 1
+else
+    echo "skip live task cases (docker unavailable)"
+fi
+
+echo
+echo "selftest: $PASS passed, $FAIL failed"
+[ "$FAIL" -eq 0 ]

scripts/verify.sh

@@ -14,10 +14,11 @@ cd "$(dirname "$0")/.."
 # shellcheck source=common.sh
 source scripts/common.sh
 
-IMAGE="mosaic-poc-agent:0.84.4"
 EXPECTED="${EXPECTED_MARKER:-MOSAIC_HELLO_OK}"
 
 load_config
+load_release
+IMAGE="$MOSAIC_IMAGE_TAG"
 
 # Ensure the configured data root exists (host-owned) before the mount,
 # otherwise Docker would auto-create a root-owned directory.
@@ -31,8 +32,9 @@ if ! docker image inspect "$IMAGE" >/dev/null 2>&1; then
 fi
 
 # 2. Run the agent request (stdout only = model response).
+# stdin detached: see hello.sh — print mode would block on a terminal.
 set +e
-RESPONSE="$(docker compose run --rm -T mosaic-agent 2>/tmp/mosaic-poc-stderr.$$)"
+RESPONSE="$(docker compose run --rm -T mosaic-agent </dev/null 2>/tmp/mosaic-poc-stderr.$$)"
 RC=$?
 set -e
 STDERR_FILE="/tmp/mosaic-poc-stderr.$$"

src/load-contracts.sh

@@ -33,5 +33,23 @@ for f in $FILES; do
     printf '\n' >> "$TEMP"
 done
 
+# Sanctioned mission injection point (M4): when the task runner provides a
+# mission snapshot, its objective and directives are appended AFTER the
+# immutable contracts. Runtime data; never part of the contract fixtures.
+if [ -n "${MOSAIC_MISSION_FILE:-}" ]; then
+    if [ ! -r "$MOSAIC_MISSION_FILE" ]; then
+        echo "load-contracts: MOSAIC_MISSION_FILE set but not readable: $MOSAIC_MISSION_FILE" >&2
+        rm -f "$TEMP"
+        exit 1
+    fi
+    printf '===== MISSION (runtime) =====\n' >> "$TEMP"
+    node -e '
+const m = JSON.parse(require("fs").readFileSync(process.env.MOSAIC_MISSION_FILE, "utf8"));
+process.stdout.write("Objective: " + m.objective + "\n");
+for (const d of m.directives ?? []) process.stdout.write("- " + d + "\n");
+' >> "$TEMP"
+    printf '\n' >> "$TEMP"
+fi
+
 mv "$TEMP" "$OUT"
 echo "load-contracts: wrote $OUT from $CONTRACT_DIR" >&2

src/run-agent.sh

@@ -1,38 +1,33 @@
 #!/bin/sh
-# One-shot Pi agent runner inside the container.
-# Loads the contract-generated system prompt, then sends exactly one
-# user request through Pi's documented noninteractive mode and prints
-# the model response on stdout.
+# One-shot agent dispatcher inside the container.
+#
+# 1. Loads the contract-generated system prompt (contracts + optional
+#    mission section from MOSAIC_MISSION_FILE).
+# 2. Dispatches to /opt/mosaic/adapters/<MOSAIC_ADAPTER>/adapter.sh per
+#    the contract in /opt/mosaic/adapters/README.md.
 set -eu
 
-: "${PI_PROVIDER:=zai}"
-: "${PI_MODEL:=glm-5.3-flash}"
-export PI_PROVIDER PI_MODEL
-
 REQUEST="${*:-Return your startup marker and nothing else.}"
 
+ADAPTER="${MOSAIC_ADAPTER:-pi}"
+case "$ADAPTER" in
+    # Allowlist mirrors scripts/mosaic-config.mjs; pattern check first so a
+    # crafted name cannot escape the adapters directory.
+    *[!A-Za-z0-9._-]*|'')
+        echo "run-agent: invalid adapter name: '$ADAPTER'" >&2
+        exit 2
+        ;;
+esac
+
+ADAPTER_SCRIPT="/opt/mosaic/adapters/$ADAPTER/adapter.sh"
+if [ ! -x "$ADAPTER_SCRIPT" ]; then
+    echo "run-agent: unknown or non-executable adapter: $ADAPTER" >&2
+    exit 2
+fi
+
 /opt/mosaic/src/load-contracts.sh /opt/mosaic/contracts /var/lib/mosaic/system-prompt.md
 
-# All flags are documented in the package README (CLI Reference):
-#   -p / --print        noninteractive: print the response and exit
-#   --system-prompt     replace the default system prompt with the
-#                       contract-generated prompt
-#   --no-* switches     prevent ambient context files, skills, extensions,
-#                       prompt templates, and themes from being appended
-#   --no-session        ephemeral: no persistent agent session
-#   --no-tools          the startup request needs no tool execution
-#   --offline           disable startup network operations (update checks,
-#                       package update checks, install/update telemetry)
-exec pi \
-    --offline \
-    --no-session \
-    --no-extensions \
-    --no-skills \
-    --no-prompt-templates \
-    --no-themes \
-    --no-context-files \
-    --no-tools \
-    --provider "$PI_PROVIDER" \
-    --model "$PI_MODEL" \
-    --system-prompt "$(cat /var/lib/mosaic/system-prompt.md)" \
-    -p "$REQUEST"
+export MOSAIC_SYSTEM_PROMPT_FILE="/var/lib/mosaic/system-prompt.md"
+export MOSAIC_REQUEST="$REQUEST"
+
+exec "$ADAPTER_SCRIPT"

tasks/hello-marker.json

@@ -0,0 +1,8 @@
+{
+  "taskVersion": 1,
+  "id": "t-hello-marker",
+  "prompt": "Return your startup marker and nothing else.",
+  "mission": "../missions/hello.json",
+  "expectExact": "MOSAIC_HELLO_OK",
+  "timeoutSeconds": 120
+}

tasks/workspace-demo.json

@@ -0,0 +1,9 @@
+{
+  "taskVersion": 1,
+  "id": "t-workspace-demo",
+  "prompt": "Use the bash tool to create a file named proof.txt in the current directory containing exactly the text: workspace works. Then reply with exactly: WORKSPACE_OK",
+  "workspace": "demo",
+  "capabilities": { "tools": ["bash", "read", "write"] },
+  "expectExact": "WORKSPACE_OK",
+  "timeoutSeconds": 180
+}