agent-dispatch 0.9.0__tar.gz → 0.10.0__tar.gz

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/AGENTS.md

@@ -51,7 +51,7 @@ Python ≥ 3.10 · `from __future__ import annotations` everywhere · Pydantic v
 
 ## When adding a feature, check every layer
 
-`models.py` (data shape) → `runner.py` (dispatch mechanics) → `server.py` (MCP tool) → `cli.py` (CLI flag) → tests for each → `README.md` + `agents.example.yaml` (user docs).
+`models.py` (data shape) → `config.py` (YAML round-trip + empty-collection pruning) → `runner.py` (dispatch mechanics) → `server.py` (MCP tool) → `cli.py` (CLI flag) → tests for each → `README.md` + `agents.example.yaml` (user docs).
 
 ## More detail
 

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/CHANGELOG.md

@@ -7,6 +7,34 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.10.0] - 2026-07-14
+
+`doctor` learns to check groups; three correctness fixes found in review.
+
+### Added
+- **`agent-dispatch doctor` diagnoses group health.** A new "Groups" section
+  reports each group's member count, flags dangling members (agents removed
+  from config but still referenced) as a failure, and empty groups as a
+  warning — each with a concrete remediation command.
+
+### Fixed
+- `auto_describe()`: an empty `"description"` field in `package.json` (a
+  common `npm init` placeholder) was no longer being filtered out, producing
+  malformed generated descriptions like `" | Stack: Node.js"`. Empty/blank
+  descriptions are ignored again.
+- `doctor`'s group remediation hints pointed at `group update --members`,
+  a flag that doesn't exist (`group update` only edits `description` /
+  `shared_context`; membership is set via `group add --member`). Hints now
+  point at the working `group remove` + `group add --member` recreation path.
+- `JobStore.mark_running()` now refuses to start any job that isn't
+  `pending` (previously only refused `cancelled`), closing a race where a
+  stale/duplicate worker could resurrect an already-finished or failed job.
+
+### Changed
+- Consolidated the "unknown group member" check — previously duplicated
+  across five call sites in `cli.py` and `server.py` — into a single
+  `DispatchConfig.unknown_group_members()` helper.
+
 ## [0.9.0] - 2026-06-30
 
 Coordinate a group of related projects from one session.

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-dispatch
-Version: 0.9.0
+Version: 0.10.0
 Summary: MCP server that lets Claude Code agents delegate tasks to agents in other project directories
 Project-URL: Homepage, https://github.com/ginkida/agent-dispatch
 Project-URL: Repository, https://github.com/ginkida/agent-dispatch
@@ -43,6 +43,8 @@ Description-Content-Type: text/markdown
 
 Each agent runs as a separate `claude -p` session in its own project directory — inheriting that project's MCP servers, CLAUDE.md, and tools. The calling agent just gets the result back.
 
+Related projects can be bundled into a **[group](#groups)** — a shared brief plus a member list — so one session can coordinate work across them (e.g. code repos + an `infra`/Portainer gateway + an `analytics` gateway).
+
 Works with OAuth, API key, and Claude subscription authentication.
 
 > **AI agents:** this README is the canonical doc for *using* the tool — setup: [Quick Start](#quick-start) (every step has a deterministic verify), first call: [`dispatch`](#dispatch), tool selection: [Which Tool to Use](#which-tool-to-use), failure handling: [Error Recovery](#error-recovery). Working *on* this repo instead? See [AGENTS.md](AGENTS.md).
@@ -539,6 +541,23 @@ agents:
     # disallowed_tools:     # block specific tools
     #   - Write
 
+# Optional: bundle related agents into a cross-project working set.
+# A descriptive layer — no router; the orchestrating session coordinates
+# with the normal dispatch tools. See the Groups section above.
+groups:
+  shop:
+    # ORCHESTRATOR-facing: how to coordinate the group. Surfaced by
+    # list_groups/inspect_group, NEVER injected into a member's prompt.
+    description: "After a code change: deploy via infra, then verify via analytics."
+    # MEMBER-facing facts, auto-prepended to dispatch(..., group="shop").
+    shared_context: |
+      Prod runs in Portainer stack "shop". Metrica counter 12345.
+    members:                # reference agents above (many-to-many)
+      - agent: infra
+        use_for: deploy, restart, container logs
+      # - agent: backend
+      #   use_for: orders/payments endpoints
+
 settings:
   default_timeout: 300
   # default_permission_mode: bypassPermissions  # inherited by all agents
@@ -608,7 +627,7 @@ agent-dispatch MCP server
 - **Cost visibility** — `max_budget_usd` per agent or globally; a dispatch whose cost exceeds it returns `budget_exceeded: true` + a hint (post-hoc — the `claude` CLI has no spend cap, so the overage can be flagged but not prevented).
 - **Concurrency** — `max_concurrency` (default: 5) caps parallel `claude -p` processes. Note: the sync and async dispatch paths use separate semaphores, so the worst-case total is `2 × max_concurrency`.
 - **Timeout** — per-agent or global (default: 300s). Orphaned processes are cleaned up.
-- **Caching** — identical `(agent, task, context, caller, goal, response_format)` requests return cached results, bounded by `cache.max_size` (oldest entry evicted first). Only successes are cached. Sessions and dialogues are never cached.
+- **Caching** — identical `(agent, task, context, caller, goal, response_format)` requests return cached results, bounded by `cache.max_size` (oldest entry evicted first). Only successes are cached. Sessions and dialogues are never cached. A `group=` dispatch folds the group's `shared_context` into `context`, so different groups cache separately and a plain dispatch is unaffected.
 
 See [SECURITY.md](SECURITY.md) for the full threat model (including the `bypassPermissions` escalation risk and on-disk job files).
 
@@ -621,9 +640,10 @@ See [SECURITY.md](SECURITY.md) for the full threat model (including the `bypassP
 | `agent-dispatch update <name>` | Update agent config (permissions, timeout, model, etc.) |
 | `agent-dispatch remove <name>` | Remove an agent |
 | `agent-dispatch list` | List agents with health status and permissions |
+| `agent-dispatch group <add\|list\|inspect\|update\|remove>` | Manage [groups](#groups) — cross-project working sets of agents |
 | `agent-dispatch describe <name>` | Show full configuration for one agent (tri-state tools, project files) |
 | `agent-dispatch test <name> [task] [--stream]` | Test an agent with a dispatch (`--stream` for live progress) |
-| `agent-dispatch doctor` | Diagnose installation: claude CLI, MCP registration, agent health |
+| `agent-dispatch doctor` | Diagnose installation: Claude CLI, MCP registration, agent health, and group membership |
 | `agent-dispatch jobs [--status --limit]` | List async dispatch jobs (most recent first) |
 | `agent-dispatch job <id>` | Show one job: status, progress tail, result preview |
 | `agent-dispatch cancel <id>` | Cancel a pending job (running jobs: use the `dispatch_cancel` MCP tool) |

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/README.md

@@ -13,6 +13,8 @@
 
 Each agent runs as a separate `claude -p` session in its own project directory — inheriting that project's MCP servers, CLAUDE.md, and tools. The calling agent just gets the result back.
 
+Related projects can be bundled into a **[group](#groups)** — a shared brief plus a member list — so one session can coordinate work across them (e.g. code repos + an `infra`/Portainer gateway + an `analytics` gateway).
+
 Works with OAuth, API key, and Claude subscription authentication.
 
 > **AI agents:** this README is the canonical doc for *using* the tool — setup: [Quick Start](#quick-start) (every step has a deterministic verify), first call: [`dispatch`](#dispatch), tool selection: [Which Tool to Use](#which-tool-to-use), failure handling: [Error Recovery](#error-recovery). Working *on* this repo instead? See [AGENTS.md](AGENTS.md).
@@ -509,6 +511,23 @@ agents:
     # disallowed_tools:     # block specific tools
     #   - Write
 
+# Optional: bundle related agents into a cross-project working set.
+# A descriptive layer — no router; the orchestrating session coordinates
+# with the normal dispatch tools. See the Groups section above.
+groups:
+  shop:
+    # ORCHESTRATOR-facing: how to coordinate the group. Surfaced by
+    # list_groups/inspect_group, NEVER injected into a member's prompt.
+    description: "After a code change: deploy via infra, then verify via analytics."
+    # MEMBER-facing facts, auto-prepended to dispatch(..., group="shop").
+    shared_context: |
+      Prod runs in Portainer stack "shop". Metrica counter 12345.
+    members:                # reference agents above (many-to-many)
+      - agent: infra
+        use_for: deploy, restart, container logs
+      # - agent: backend
+      #   use_for: orders/payments endpoints
+
 settings:
   default_timeout: 300
   # default_permission_mode: bypassPermissions  # inherited by all agents
@@ -578,7 +597,7 @@ agent-dispatch MCP server
 - **Cost visibility** — `max_budget_usd` per agent or globally; a dispatch whose cost exceeds it returns `budget_exceeded: true` + a hint (post-hoc — the `claude` CLI has no spend cap, so the overage can be flagged but not prevented).
 - **Concurrency** — `max_concurrency` (default: 5) caps parallel `claude -p` processes. Note: the sync and async dispatch paths use separate semaphores, so the worst-case total is `2 × max_concurrency`.
 - **Timeout** — per-agent or global (default: 300s). Orphaned processes are cleaned up.
-- **Caching** — identical `(agent, task, context, caller, goal, response_format)` requests return cached results, bounded by `cache.max_size` (oldest entry evicted first). Only successes are cached. Sessions and dialogues are never cached.
+- **Caching** — identical `(agent, task, context, caller, goal, response_format)` requests return cached results, bounded by `cache.max_size` (oldest entry evicted first). Only successes are cached. Sessions and dialogues are never cached. A `group=` dispatch folds the group's `shared_context` into `context`, so different groups cache separately and a plain dispatch is unaffected.
 
 See [SECURITY.md](SECURITY.md) for the full threat model (including the `bypassPermissions` escalation risk and on-disk job files).
 
@@ -591,9 +610,10 @@ See [SECURITY.md](SECURITY.md) for the full threat model (including the `bypassP
 | `agent-dispatch update <name>` | Update agent config (permissions, timeout, model, etc.) |
 | `agent-dispatch remove <name>` | Remove an agent |
 | `agent-dispatch list` | List agents with health status and permissions |
+| `agent-dispatch group <add\|list\|inspect\|update\|remove>` | Manage [groups](#groups) — cross-project working sets of agents |
 | `agent-dispatch describe <name>` | Show full configuration for one agent (tri-state tools, project files) |
 | `agent-dispatch test <name> [task] [--stream]` | Test an agent with a dispatch (`--stream` for live progress) |
-| `agent-dispatch doctor` | Diagnose installation: claude CLI, MCP registration, agent health |
+| `agent-dispatch doctor` | Diagnose installation: Claude CLI, MCP registration, agent health, and group membership |
 | `agent-dispatch jobs [--status --limit]` | List async dispatch jobs (most recent first) |
 | `agent-dispatch job <id>` | Show one job: status, progress tail, result preview |
 | `agent-dispatch cancel <id>` | Cancel a pending job (running jobs: use the `dispatch_cancel` MCP tool) |

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/agents.example.yaml

@@ -10,6 +10,17 @@ agents:
       - restart_services
     timeout: 300
 
+  # Analytics gateway — a browser + Yandex Metrica agent, no codebase of its own.
+  # Its value is its MCP servers + access, not its source. Shared across groups.
+  analytics:
+    directory: ~/projects/analytics
+    description: "Analytics gateway. MCP servers: browser, yandex-metrica. Pulls funnels, conversion, traffic. Read-only."
+    capabilities:
+      - funnel_report
+      - conversion_metrics
+    permission_mode: bypassPermissions  # runs non-interactively against read-only sources
+    timeout: 300
+
   # Backend agent — source code, tests, database
   backend:
     directory: ~/projects/backend
@@ -62,7 +73,21 @@ groups:
         use_for: orders/payments endpoints, migrations
       - agent: infra
         use_for: deploy, restart, container logs
-      # - agent: analytics   # a shared gateway agent could also live here
+      - agent: analytics
+        use_for: funnel + conversion verification
+
+  # A second product reusing the SHARED infra/analytics gateways. Membership is
+  # many-to-many — gateways are referenced, not owned, so one analytics/infra
+  # agent serves every product.
+  blog:
+    description: "Content site. Same deploy-then-verify loop via the shared gateways."
+    shared_context: |
+      Production runs in Portainer stack "blog". Metrica counter 67890.
+    members:
+      - agent: infra
+        use_for: deploy, logs
+      - agent: analytics
+        use_for: pageview + bounce-rate checks
 
 settings:
   default_timeout: 300

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "agent-dispatch"
-version = "0.9.0"
+version = "0.10.0"
 description = "MCP server that lets Claude Code agents delegate tasks to agents in other project directories"
 readme = "README.md"
 license = "MIT"

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/src/agent_dispatch/__init__.py

@@ -1,3 +1,3 @@
 """agent-dispatch: Delegate tasks between Claude Code agents across projects."""
 
-__version__ = "0.9.0"
+__version__ = "0.10.0"

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/src/agent_dispatch/cli.py

@@ -563,12 +563,13 @@ def group_list() -> None:
         click.echo(f"  {click.style(name, bold=True)} ({len(grp.members)} member(s))")
         if grp.description:
             click.echo(f"    desc: {grp.description}")
+        unknown_members = set(config.unknown_group_members(grp))
         rendered: list[str] = []
         for m in grp.members:
-            if m.agent in config.agents:
-                rendered.append(m.agent)
-            else:
+            if m.agent in unknown_members:
                 rendered.append(click.style(f"{m.agent}(unknown)", fg="red"))
+            else:
+                rendered.append(m.agent)
         if rendered:
             click.echo(f"    members: {', '.join(rendered)}")
         click.echo(f"    shared context: {'yes' if grp.shared_context.strip() else 'no'}")
@@ -593,8 +594,9 @@ def group_inspect(name: str) -> None:
         for line in grp.shared_context.splitlines():
             click.echo(f"    {line}")
     click.echo(f"  members ({len(grp.members)}):")
+    unknown_members = set(config.unknown_group_members(grp))
     for m in grp.members:
-        marker = "" if m.agent in config.agents else click.style(" (unknown)", fg="red")
+        marker = click.style(" (unknown)", fg="red") if m.agent in unknown_members else ""
         hint = f" — {m.use_for}" if m.use_for else ""
         click.echo(f"    - {m.agent}{marker}{hint}")
     if not grp.members:
@@ -750,6 +752,32 @@ def doctor() -> None:
             except OSError as e:
                 fail(f"{name}: directory unreadable - {e}")
 
+    section("Groups")
+    if config is None:
+        warn("Skipped (config could not be loaded)")
+    elif not config.groups:
+        ok("No groups configured")
+    else:
+        for name, group in config.groups.items():
+            unknown = config.unknown_group_members(group)
+            if unknown:
+                missing = ", ".join(unknown)
+                fail(f"{name}: unknown member(s): {missing}")
+                click.echo(
+                    f"    Fix by recreating: agent-dispatch group remove {name} && "
+                    f"agent-dispatch group add {name} --member ... (or edit agents.yaml)"
+                )
+            elif not group.members:
+                warn(f"{name}: no members configured")
+                click.echo(
+                    f"    Add members by recreating: agent-dispatch group remove {name} && "
+                    f"agent-dispatch group add {name} --member agent1 --member agent2"
+                )
+            else:
+                count = len(group.members)
+                suffix = "member" if count == 1 else "members"
+                ok(f"{name}: {count} {suffix}")
+
     section("Summary")
     issues = counters["issues"]
     warnings = counters["warnings"]

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/src/agent_dispatch/config.py

@@ -80,8 +80,13 @@ def _collect_mcp_servers(directory: Path) -> list[str]:
         if path.exists():
             try:
                 data = json.loads(path.read_text(encoding="utf-8"))
-                servers.extend(data.get("mcpServers", {}).keys())
-            except (json.JSONDecodeError, KeyError):
+                if not isinstance(data, dict):
+                    raise ValueError("top-level JSON value is not an object")
+                configured = data.get("mcpServers", {})
+                if not isinstance(configured, dict):
+                    raise ValueError("mcpServers is not an object")
+                servers.extend(str(name) for name in configured)
+            except (OSError, UnicodeDecodeError, json.JSONDecodeError, ValueError):
                 logger.debug("Failed to parse MCP config: %s", path)
     return list(dict.fromkeys(servers))  # deduplicate, preserve order
 
@@ -137,7 +142,12 @@ def auto_describe(directory: Path) -> str:
     claude_md = directory / "CLAUDE.md"
     if claude_md.exists():
         sentences: list[str] = []
-        for line in claude_md.read_text(encoding="utf-8").strip().splitlines()[:40]:
+        try:
+            lines = claude_md.read_text(encoding="utf-8").strip().splitlines()[:40]
+        except (OSError, UnicodeDecodeError):
+            logger.debug("Failed to read CLAUDE.md: %s", claude_md)
+            lines = []
+        for line in lines:
             stripped = line.strip()
             if stripped and not stripped.startswith("#") and not stripped.startswith("--"):
                 sentences.append(stripped)
@@ -150,7 +160,12 @@ def auto_describe(directory: Path) -> str:
     if not parts:
         readme = directory / "README.md"
         if readme.exists():
-            for line in readme.read_text(encoding="utf-8").strip().splitlines()[:20]:
+            try:
+                lines = readme.read_text(encoding="utf-8").strip().splitlines()[:20]
+            except (OSError, UnicodeDecodeError):
+                logger.debug("Failed to read README.md: %s", readme)
+                lines = []
+            for line in lines:
                 stripped = line.strip()
                 if (
                     stripped
@@ -165,9 +180,17 @@ def auto_describe(directory: Path) -> str:
     # pyproject.toml — project description
     pyproject = directory / "pyproject.toml"
     if pyproject.exists():
-        for line in pyproject.read_text(encoding="utf-8").splitlines():
+        try:
+            lines = pyproject.read_text(encoding="utf-8").splitlines()
+        except (OSError, UnicodeDecodeError):
+            logger.debug("Failed to read pyproject.toml: %s", pyproject)
+            lines = []
+        for line in lines:
             if line.strip().startswith("description"):
-                desc = line.split("=", 1)[1].strip().strip('"').strip("'")
+                _, separator, value = line.partition("=")
+                if not separator:
+                    continue
+                desc = value.strip().strip('"').strip("'")
                 if desc:
                     parts.append(desc)
                 break
@@ -177,9 +200,11 @@ def auto_describe(directory: Path) -> str:
     if pkg_json.exists():
         try:
             pkg = json.loads(pkg_json.read_text(encoding="utf-8"))
-            if pkg.get("description"):
-                parts.append(pkg["description"])
-        except (json.JSONDecodeError, KeyError):
+            if isinstance(pkg, dict):
+                desc = pkg.get("description")
+                if isinstance(desc, str) and desc.strip():
+                    parts.append(desc)
+        except (OSError, UnicodeDecodeError, json.JSONDecodeError):
             logger.debug("Failed to parse package.json: %s", pkg_json)
 
     # MCP servers — critical for understanding what tools this agent has

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/src/agent_dispatch/jobs.py

@@ -192,17 +192,18 @@ class JobStore:
     def mark_running(self, job_id: str) -> Job | None:
         """Mark a pending job as running.
 
-        Returns the updated job, or None if the job is missing OR has already
-        been cancelled. Refusing to run a cancelled job closes the race with
-        ``cancel()``: both take ``self._lock``, so whichever wins, the worker
-        either sees ``cancelled`` (and skips) or sets ``running`` first (and
-        cancel then refuses).
+        Returns the updated job, or None unless the job exists and is still
+        pending. Refusing every non-pending state prevents a duplicate worker
+        from resurrecting a completed/failed/cancelled job. It also closes the
+        race with ``cancel()``: both take ``self._lock``, so whichever wins,
+        the worker either sees ``cancelled`` (and skips) or sets ``running``
+        first (and cancel then refuses).
         """
         with self._lock:
             job = self.get(job_id)
             if job is None:
                 return None
-            if job.status == "cancelled":
+            if job.status != "pending":
                 return None
             job.status = "running"
             job.started_at = time.time()

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/src/agent_dispatch/models.py

@@ -158,6 +158,10 @@ class DispatchConfig(BaseModel):
             validate_agent_name(name)
         return self
 
+    def unknown_group_members(self, group: DispatchGroup) -> list[str]:
+        """Member agent names in `group` that aren't in `self.agents` (sorted, deduped)."""
+        return sorted({m.agent for m in group.members if m.agent not in self.agents})
+
 
 class DispatchResult(BaseModel):
     """Result of a dispatch call."""

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/src/agent_dispatch/server.py

@@ -500,6 +500,7 @@ async def list_groups(ctx: Context | None = None) -> str:
 
     groups = []
     for name, grp in config.groups.items():
+        unknown_members = set(config.unknown_group_members(grp))
         members = []
         for m in grp.members:
             entry: dict = {"agent": m.agent}
@@ -507,7 +508,7 @@ async def list_groups(ctx: Context | None = None) -> str:
                 entry["use_for"] = m.use_for
             # Flag dangling refs (agent removed) instead of crashing — never
             # touch config.agents[m.agent] when it's unknown.
-            if m.agent not in config.agents:
+            if m.agent in unknown_members:
                 entry["unknown"] = True
             else:
                 try:
@@ -548,12 +549,13 @@ async def inspect_group(name: str, ctx: Context | None = None) -> str:
         return err
 
     grp = config.groups[name]
+    unknown_members = set(config.unknown_group_members(grp))
     members = []
     for m in grp.members:
         entry: dict = {"agent": m.agent}
         if m.use_for:
             entry["use_for"] = m.use_for
-        if m.agent not in config.agents:
+        if m.agent in unknown_members:
             entry["unknown"] = True
         else:
             agent = config.agents[m.agent]

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/tests/test_cli.py

@@ -852,6 +852,57 @@ class TestDoctor:
         assert "CLAUDE.md" in result.output
         assert ".mcp.json" in result.output
 
+    def test_healthy_group_passes(self, tmp_path: Path, _isolated_config: Path):
+        agent_dir = tmp_path / "proj"
+        agent_dir.mkdir()
+        _isolated_config.parent.mkdir(parents=True, exist_ok=True)
+        _isolated_config.write_text(
+            f"agents:\n  proj:\n    directory: {agent_dir}\n"
+            "groups:\n  product:\n    members:\n      - agent: proj\n"
+        )
+        with (
+            patch("agent_dispatch.cli.shutil.which", side_effect=lambda x: f"/usr/bin/{x}"),
+            self._patch_claude_mcp_list(registered=True),
+        ):
+            result = runner.invoke(cli, ["doctor"])
+        assert result.exit_code == 0, result.output
+        assert "product: 1 member" in result.output
+        assert "All checks passed" in result.output
+
+    def test_dangling_group_member_fails(self, tmp_path: Path, _isolated_config: Path):
+        agent_dir = tmp_path / "proj"
+        agent_dir.mkdir()
+        _isolated_config.parent.mkdir(parents=True, exist_ok=True)
+        _isolated_config.write_text(
+            f"agents:\n  proj:\n    directory: {agent_dir}\n"
+            "groups:\n  product:\n    members:\n"
+            "      - agent: proj\n      - agent: removed_gateway\n"
+        )
+        with (
+            patch("agent_dispatch.cli.shutil.which", side_effect=lambda x: f"/usr/bin/{x}"),
+            self._patch_claude_mcp_list(registered=True),
+        ):
+            result = runner.invoke(cli, ["doctor"])
+        assert result.exit_code != 0
+        assert "product: unknown member(s): removed_gateway" in result.output
+        assert "group remove product && agent-dispatch group add product --member" in result.output
+
+    def test_empty_group_warns(self, tmp_path: Path, _isolated_config: Path):
+        agent_dir = tmp_path / "proj"
+        agent_dir.mkdir()
+        _isolated_config.parent.mkdir(parents=True, exist_ok=True)
+        _isolated_config.write_text(
+            f"agents:\n  proj:\n    directory: {agent_dir}\ngroups:\n  product:\n    members: []\n"
+        )
+        with (
+            patch("agent_dispatch.cli.shutil.which", side_effect=lambda x: f"/usr/bin/{x}"),
+            self._patch_claude_mcp_list(registered=True),
+        ):
+            result = runner.invoke(cli, ["doctor"])
+        assert result.exit_code == 0
+        assert "product: no members configured" in result.output
+        assert "1 warning" in result.output
+
     def test_summary_singular_plural(self, tmp_path: Path):
         """One issue should say 'issue' not 'issues'."""
         with patch("agent_dispatch.cli.shutil.which", return_value=None):

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/tests/test_config.py

@@ -10,7 +10,7 @@ from pathlib import Path
 import pytest
 import yaml
 
-from agent_dispatch.config import auto_describe, load_config, save_config
+from agent_dispatch.config import auto_describe, collect_mcp_servers, load_config, save_config
 from agent_dispatch.models import (
     AgentConfig,
     DispatchConfig,
@@ -176,6 +176,34 @@ def test_auto_describe_fallback(tmp_path: Path):
     assert tmp_path.name in desc
 
 
+def test_collect_mcp_servers_ignores_wrong_json_shapes(tmp_path: Path):
+    (tmp_path / ".mcp.json").write_text("[]")
+    claude_dir = tmp_path / ".claude"
+    claude_dir.mkdir()
+    (claude_dir / "settings.local.json").write_text('{"mcpServers": []}')
+
+    assert collect_mcp_servers(tmp_path) == []
+
+
+def test_auto_describe_tolerates_malformed_metadata_shapes(tmp_path: Path):
+    (tmp_path / "CLAUDE.md").write_bytes(b"\xff\xfe")
+    (tmp_path / "README.md").write_bytes(b"\xff\xfe")
+    (tmp_path / "pyproject.toml").write_text("description\n")
+    (tmp_path / "package.json").write_text("[]")
+    (tmp_path / ".mcp.json").write_text('{"mcpServers": []}')
+
+    assert auto_describe(tmp_path) == "Stack: Python, Node.js"
+
+
+def test_auto_describe_ignores_empty_package_json_description(tmp_path: Path):
+    (tmp_path / "package.json").write_text('{"description": ""}')
+
+    desc = auto_describe(tmp_path)
+
+    assert not desc.startswith(" | ")
+    assert "Stack: Node.js" == desc
+
+
 def test_save_and_load_groups_roundtrip(tmp_path: Path):
     f = tmp_path / "test.yaml"
     config = DispatchConfig(

{agent_dispatch-0.9.0 → agent_dispatch-0.10.0}/tests/test_jobs.py

@@ -315,6 +315,20 @@ class TestJobCancel:
         assert store.mark_running(job.id) is None
         assert store.get(job.id).status == "cancelled"
 
+    def test_mark_running_refuses_completed_job(self, store: JobStore):
+        job = store.create("agent", "task")
+        store.finish(job.id, DispatchResult(agent="agent", success=True, result="done"))
+
+        assert store.mark_running(job.id) is None
+        assert store.get(job.id).status == "done"
+
+    def test_mark_running_refuses_failed_job(self, store: JobStore):
+        job = store.create("agent", "task")
+        store.fail(job.id, "boom")
+
+        assert store.mark_running(job.id) is None
+        assert store.get(job.id).status == "failed"
+
 
 class TestRecoverStale:
     def test_recovers_old_running_job(self, store: JobStore):