Merge M6: named sessions - persistence and resume

Closes #22, closes #23

adapters/mock/adapter.sh

@@ -10,4 +10,7 @@ set -eu
 [ -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

@@ -12,21 +12,43 @@ set -eu
 : "${PI_PROVIDER:?pi adapter: PI_PROVIDER is required}"
 : "${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 "$MOSAIC_WORKSPACE"
+fi
+
+# Session (M6): persistent named session directory; resume the most recent
+# session in that directory when one exists (pi documented flags).
+# Default remains ephemeral (--no-session) when no session is declared.
+SESSION_FLAGS="--no-session"
+if [ -n "${MOSAIC_SESSION_DIR:-}" ]; then
+    mkdir -p "$MOSAIC_SESSION_DIR"
+    SESSION_FLAGS="--session-dir $MOSAIC_SESSION_DIR"
+    if [ -n "$(ls -A "$MOSAIC_SESSION_DIR" 2>/dev/null)" ]; then
+        SESSION_FLAGS="$SESSION_FLAGS -c"
+    fi
+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; --no-tools  this runtime needs no tools
+#   --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 \
-    --no-tools \
+    $TOOLS_FLAG \
+    $SESSION_FLAGS \
     --provider "$PI_PROVIDER" \
     --model "$PI_MODEL" \
     --system-prompt "$(cat "$MOSAIC_SYSTEM_PROMPT_FILE")" \

compose.yaml

@@ -15,6 +15,11 @@ services:
       # 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:-}
+      # Persistent named session dir (set by the task runner; M6)
+      MOSAIC_SESSION_DIR: ${MOSAIC_SESSION_DIR:-}
       # mock adapter only: verbatim response for deterministic seam tests
       MOSAIC_MOCK_RESPONSE: ${MOSAIC_MOCK_RESPONSE:-}
       # Documented container auth alternative: provider API key via

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

scripts/mosaic-task.mjs

@@ -38,6 +38,7 @@ 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`);
@@ -105,7 +106,7 @@ function validateMission(document, file) {
 
 function validateTask(document, file) {
   if (!isPlainObject(document)) fail(2, "task must be a JSON object");
-  rejectUnknownKeys(document, ["taskVersion", "id", "prompt", "mission", "expectExact", "timeoutSeconds"], "task");
+  rejectUnknownKeys(document, ["taskVersion", "id", "prompt", "mission", "expectExact", "timeoutSeconds", "workspace", "capabilities", "session"], "task");
   if (document.taskVersion !== 1) {
     fail(2, `unsupported taskVersion: ${JSON.stringify(document.taskVersion)} (supported: 1)`);
   }
@@ -144,6 +145,50 @@ function validateTask(document, file) {
     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;
+  }
+
+  // Session (M6): optional named persistent session under
+  // <dataRoot>/sessions/<name>. Distinct names never share state.
+  let session = null;
+  if (document.session !== undefined && document.session !== null) {
+    if (typeof document.session !== "string" || document.session.length === 0) {
+      fail(2, 'task "session" must be a non-empty string when present');
+    }
+    validateId(document.session, "task session");
+    session = document.session;
+  }
+
+  // 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,
@@ -153,6 +198,9 @@ function validateTask(document, file) {
     missionSnapshot,
     expectExact,
     timeoutSeconds,
+    workspace,
+    tools,
+    session,
   };
 }
 
@@ -223,6 +271,24 @@ function runTask(taskFile) {
     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(",") : "";
+
+  // Session (M6): persistent named session dir, passed as container path.
+  if (task.session) {
+    fs.mkdirSync(path.join(resolved.dataRoot, "sessions", task.session), { recursive: true });
+    spawnEnv.MOSAIC_SESSION_DIR = `/var/lib/mosaic/sessions/${task.session}`;
+  }
+
   const proc = spawnSync(
     "docker",
     ["compose", "run", "--rm", "-T", "mosaic-agent", task.prompt],
@@ -269,6 +335,9 @@ function runTask(taskFile) {
     request: task.prompt,
     response,
     expectedExact: expected,
+    workspace: task.workspace,
+    tools: task.tools,
+    session: task.session,
     exitCode: proc.status,
     signal: proc.signal ?? null,
     provider: resolved.execution.provider,

scripts/test-task.sh

@@ -146,6 +146,38 @@ 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.

tasks/session-demo-1.json

@@ -0,0 +1,8 @@
+{
+  "taskVersion": 1,
+  "id": "t-session-teach",
+  "prompt": "Remember this code word for later: mosaico. Reply with exactly: REMEMBERED",
+  "session": "demo",
+  "expectExact": "REMEMBERED",
+  "timeoutSeconds": 180
+}

tasks/session-demo-2.json

@@ -0,0 +1,7 @@
+{
+  "taskVersion": 1,
+  "id": "t-session-recall",
+  "prompt": "What code word did I ask you to remember earlier in this session? Reply with only the code word.",
+  "session": "demo",
+  "timeoutSeconds": 180
+}

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
+}