monkeybot-cli 0.5.1__tar.gz → 0.7.0__tar.gz

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.5
 Name: monkeybot-cli
-Version: 0.5.1
+Version: 0.7.0
 Summary: CLI to create, configure, validate, and chat with monkeybot agents.
 Requires-Python: >=3.11
 Requires-Dist: httpx>=0.27.0
-Requires-Dist: monkeybot-browser-mcp<1,>=0.2.0
-Requires-Dist: monkeybot[cli]<4,>=3.0.0
+Requires-Dist: monkeybot-browser-mcp<1,>=0.5.0
+Requires-Dist: monkeybot[cli]<4,>=3.1.0
 Requires-Dist: python-dotenv>=1.0.0
 Requires-Dist: pyyaml>=6.0.2
 Requires-Dist: textual>=8.2.8

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/pyproject.toml

@@ -4,14 +4,14 @@ build-backend = "hatchling.build"
 
 [project]
 name = "monkeybot-cli"
-version = "0.5.1"
+version = "0.7.0"
 description = "CLI to create, configure, validate, and chat with monkeybot agents."
 requires-python = ">=3.11"
 dependencies = [
     # `cli` pulls realtime + typer so `monkeybot talk` works out of the box (text mode).
     # Audio mic/PTT needs the agent (or this env) to also install monkeybot[cli-realtime].
-    "monkeybot[cli]>=3.0.0,<4",
-    "monkeybot-browser-mcp>=0.2.0,<1",
+    "monkeybot[cli]>=3.1.0,<4",
+    "monkeybot-browser-mcp>=0.5.0,<1",
     "httpx>=0.27.0",
     "pyyaml>=6.0.2",
     "python-dotenv>=1.0.0",

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/skills/monkeybot/SKILL.md

@@ -56,7 +56,7 @@ npx skills add human-plus-machine/monkeybot --skill monkeybot
   - `monkeybot_config/monkeybot.yaml` — non-secret settings (model, paths, gateway, behavior).
   - `.env` — secrets and machine-local paths (API keys, GCP project, DB URL).
   - sidecars: `monkeybot_config/AGENT.md` (system prompt), `mcp.json` (MCP servers), `command_allowlist.yaml`.
-- **Precedence — important:** environment variables and `.env` win over `monkeybot.yaml`. If a user edits YAML but nothing changes, suspect a stale `.env` shadowing it (the YAML→env mapping lives in `runtime_env.py:ENV_MAP`).
+- **Precedence — important:** environment variables and `.env` win over `monkeybot.yaml` except `model.*` (provider, name, sampling, context window, summarization model, max turns, cache retention), which is YAML-only. If a user edits YAML but nothing changes, suspect a stale `.env` shadowing it (the YAML→env mapping lives in `runtime_env.py:ENV_MAP`).
 - **Defaults are fine on day one.** Most first-time users only touch `model`, `.env` credentials, and `AGENT.md`.
 
 ## Running CLI commands
@@ -112,7 +112,7 @@ uv sync
 | `aws_bedrock` | `AWS_ACCESS_KEY_ID` / `AWS_PROFILE` + `AWS_REGION` | `monkeybot[bedrock]` |
 | `huggingface` | `HF_TOKEN` (or `HUGGINGFACE_API_KEY`) | `monkeybot[huggingface]` |
 | `ollama-cloud` | `OLLAMA_API_KEY` | `monkeybot[ollama]` |
-| `ollama-local` | None required — `OLLAMA_BASE_URL` (default `http://localhost:11434`) | `monkeybot[ollama]` |
+| `ollama-local` | None required — `OLLAMA_BASE_URL` (default `http://localhost:11434`). Requests send `keep_alive` 24h so prefix KV cache survives idle. | `monkeybot[ollama]` |
 | `ollama` | Legacy auto-route (key + blank URL = cloud; explicit URL wins) | `monkeybot[ollama]` |
 
 **Agent-first dependencies.** The CLI is thin — it does **not** install provider/storage extras globally. `monkeybot new` scaffolds a `pyproject.toml` with the selected provider (and any `--with` extras). Run plain `uv sync` in the agent directory. `monkeybot run` / `chat` spawn the gateway from that project's interpreter (`.venv/bin/python`, else `uv run python`), and `doctor` checks extras in that same interpreter. For a config-only tree (just `monkeybot_config/`, no `pyproject.toml`) the gateway uses the CLI's interpreter when it already has MonkeyBot 3.x (and MemPalace if memory is on). If memory is enabled and that interpreter cannot import MemPalace, `run` / `chat` provision a cached CLI-managed venv under `~/.cache/monkeybot/runtimes/` holding `monkeybot[memory]` pinned to the running core (never rewrites a `pyproject.toml`). `doctor` reuses that cache when it is already present. Otherwise extras must be installed in the CLI env (`uv tool install --with 'monkeybot[<extra>]' monkeybot-cli`).
@@ -160,7 +160,7 @@ Decision → config map:
 | "Run untrusted code" | `sandbox.enabled` + `SANDBOX_API_KEY` |
 | "Use specialist agents" | `subagents.personas` + `monkeybot_config/agents/*.md` |
 | "Connect external tools" | `mcp.json` (`mcpServers` object), then `validate --check-mcp` |
-| "Control cost / context size" | `model.*`, `context_curation.*` |
+| "Control cost / context size" | `model.*` |
 | "Restrict dangerous commands" | `tools.denied_patterns`, `command_allowlist.yaml` |
 | "Multiple environments" | top-level `includes:` fragments |
 

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/skills/monkeybot/references/config-sections.md

@@ -2,7 +2,7 @@
 
 Deep reference for every `monkeybot.yaml` section. Load this only when a user needs to customize beyond Tier 1. The canonical, fully-commented template lives at `cli/src/monkeybot_cli/scaffold_defaults/monkeybot.example.yaml` in the monkeybot repo (copied to `monkeybot_config/monkeybot.example.yaml` when you scaffold); this file adds the **"when would I change this?"** context the comments don't.
 
-**Precedence:** env vars and `.env` win over YAML. The YAML→env mapping is `ENV_MAP` in `src/monkeybot/core/config/runtime_env.py`. If a YAML edit has no effect, check for a shadowing env var.
+**Precedence:** env vars and `.env` win over YAML for `ENV_MAP` keys. `model.*` (provider, name, temperature, max_tokens, thinking_budget, context_window, summarization_model, max_turns, cache_retention) is YAML-only — leftover `MODEL_*` env vars are ignored. The YAML→env mapping is `ENV_MAP` in `src/monkeybot/core/config/runtime_env.py`. If a YAML edit has no effect, check for a shadowing env var (except `model.*`).
 
 ---
 
@@ -34,6 +34,8 @@ Validate check ids: `paths.agent_md.exists`, `paths.skills_path.exists`, `paths.
 
 ## `model`
 
+YAML-only for provider, name, sampling, context window, summarization model, max turns, and cache retention. Leftover `MODEL_*` / `MAX_TURNS` / `CONTEXT_SUMMARIZATION_MODEL` env vars are ignored.
+
 | Field | Default | When to change |
 |---|---|---|
 | `provider` | `gemini` | Switch LLM vendor (see provider table in SKILL.md) |
@@ -41,9 +43,11 @@ Validate check ids: `paths.agent_md.exists`, `paths.skills_path.exists`, `paths.
 | `temperature` | `0.7` | Lower for deterministic output, higher for creative |
 | `max_tokens` | `60000` | Cap per-response length |
 | `thinking_budget` | `-1` | Gemini: `-1` model default, `0` off, `N` token budget. Ollama reasoning models: `-1` server default, `0` off (`reasoning_effort: none`) |
-| `context_window` | `1000000` | Summarization trigger (tokens); also drives soft-spill / `read_file` char budgets |
+| `context_window` | `1000000` | Summarization trigger (tokens); also drives soft-spill / `read_file` char budgets. **Not** Ollama `num_ctx` |
+| `keep_alive` | `24h` (ollama-local only) | How long local Ollama keeps the model (and KV prefix cache) loaded. YAML only. Set `"0"` to omit. See `docs/ollama-local.md` |
+| `num_ctx` | (unset) | Optional pinned Ollama `num_ctx`. YAML only. Omit = server default. Do not copy `context_window` |
 | `max_turns` | `1000` | Hard cap on turns per run |
-| `summarization_model` | (main model) | Cheaper model for history summarization (env `CONTEXT_SUMMARIZATION_MODEL`) |
+| `summarization_model` | (main model) | Cheaper model for history summarization (YAML-only)
 
 Validate check ids: `model.provider.supported`, `model.name.present`. Supported YAML providers: `gemini`/`vertex`, `openai`, `anthropic`, `vertex-claude`, `huggingface`, `ollama-cloud`, `ollama-local`, `ollama`, `aws_bedrock`, `fake`.
 
@@ -71,22 +75,6 @@ Required when `memory_storage_uri` is `gcs://…` or `provider: vertex-claude` (
 | `graceful_shutdown_timeout_sec` | `5` | Allow longer drain on shutdown |
 | `cors_allow_origins` | `http://localhost:5173` | **Custom web UI** — set its origin, or `"*"` for any |
 
-## `context_curation`
-
-Trims memory injected into context. `enabled: true` by default.
-
-Recent window by default; LLM curator only when the index is token-heavy. On curator failure, falls back to the window.
-
-| Field | Default | Notes |
-|---|---|---|
-| `memory_window_lines` | `12` | Recent index lines injected; also caps curator-selected lines |
-| `memory_index_cap` | `200` | Organizer keeps this many INDEX.md entries; older rows move to `INDEX.archive.md` |
-| `memory_token_threshold` | `2000` | Call curator when estimated index tokens exceed this |
-| `curator_model` | `gemini-3-flash` | Separate small model; empty = main model |
-| `timeout_sec` | `10` | Curator call timeout |
-
-When the prompt shows fewer entries than exist, a structural confidence score triggers a `search_memory` nudge. Skill names are always shown in full in the prompt; use `list_skills` to get the skills root path.
-
 ## `memory`
 
 MemPalace capture, wake-up, and search teaching are on by default. Turn them off with `memory.enabled: false` or `MONKEYBOT_MEMORY_HOOK_ENABLED=0`. The vector stack is the optional `monkeybot[memory]` extra — omit it (and set `enabled: false`) when you do not want chromadb/onnxruntime.
@@ -176,4 +164,4 @@ Validate check: `config.includes.resolve`.
 
 ## `fake_provider`
 
-Test-only. `events_json` feeds `MODEL_PROVIDER=fake` scripted runs (env `MONKEYBOT_FAKE_PROVIDER_EVENTS`). Not for production.
+Test-only. `events_json` feeds `model.provider: fake` scripted runs (env `MONKEYBOT_FAKE_PROVIDER_EVENTS`). Not for production.

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/src/monkeybot_cli/chat_session.py

@@ -229,7 +229,7 @@ class ChatSessionController:
         self.usage = UsageStore()
         self.session_id: str | None = None
         self.stream_error = False
-        self.transcript_report_dir: str | None = None
+        self.transcript_dir: str | None = None
         self._client: httpx.AsyncClient | None = None
         self._event_queue: asyncio.Queue[str | None] = asyncio.Queue()
         self._stream_task: asyncio.Task[None] | None = None
@@ -924,9 +924,9 @@ class ChatSessionController:
                 resp = await self._client.delete(f"{self.base}/sessions/{self.session_id}")
                 if resp.status_code == 200:
                     data = resp.json()
-                    report = data.get("transcript_report_dir") if isinstance(data, dict) else None
+                    report = data.get("transcript_dir") if isinstance(data, dict) else None
                     if isinstance(report, str) and report.strip():
-                        self.transcript_report_dir = report.strip()
+                        self.transcript_dir = report.strip()
             except Exception:
                 logger.warning(
                     "session DELETE on close failed session_id=%s",

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/src/monkeybot_cli/chat_tui.py

@@ -1680,8 +1680,8 @@ class ChatApp(App[int]):
         src = session_dir / "transcript.ndjson"
         if not src.is_file():
             self._mount_system(
-                "No trace file found — enable transcript capture on the gateway and restart "
-                "(external gateways need MONKEYBOT_TRANSCRIPT_ENABLED=1)",
+                "No trace file found — set runtime.transcript_enabled: true in monkeybot.yaml "
+                "and restart the gateway",
                 error=True,
             )
             return
@@ -1829,10 +1829,10 @@ class ChatApp(App[int]):
     async def _close_session_and_exit(self) -> None:
         # Must not be named `_shutdown` — that shadows Textual.App._shutdown.
         await self._controller.close()
-        report_dir = getattr(self._controller, "transcript_report_dir", None)
+        report_dir = getattr(self._controller, "transcript_dir", None)
         if isinstance(report_dir, str) and report_dir:
-            self._mount_system(f"Transcript report → {report_dir}")
-            print(f"Transcript report → {report_dir}", flush=True)
+            self._mount_system(f"Transcript → {report_dir}")
+            print(f"Transcript → {report_dir}", flush=True)
         self._exit_code = 1 if self._controller.stream_error else self._exit_code
         self.exit(self._exit_code)
 

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/src/monkeybot_cli/commands/chat.py

@@ -626,9 +626,9 @@ async def _plain_chat_session(
             await controller.submit(user_line)
     finally:
         await controller.close()
-        if controller.transcript_report_dir:
+        if controller.transcript_dir:
             print(
-                f"{_DIM}Transcript report → {controller.transcript_report_dir}{_RESET}",
+                f"{_DIM}Transcript → {controller.transcript_dir}{_RESET}",
                 flush=True,
             )
         await renderer.stop_io_worker()
@@ -678,7 +678,6 @@ def _spawn_gateway(config_path: Path | None, agent_root: Path, port: int) -> _Sp
         env["MONKEYBOT_CONFIG"] = str(config_path)
     env["PORT"] = str(port)
     env.setdefault("LOG_LEVEL", "error")
-    env.setdefault("MONKEYBOT_TRANSCRIPT_ENABLED", "1")
     log_file = tempfile.NamedTemporaryFile(
         mode="w+",
         prefix="monkeybot-gateway-",

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/src/monkeybot_cli/commands/doctor.py

@@ -192,6 +192,146 @@ def _add_layout_checks(report: CommandReport, layout: AgentLayout) -> None:
     )
 
 
+_OLLAMA_LOCAL_DOCS = "docs/ollama-local.md"
+_OLLAMA_NUM_CTX_LARGE = 32_768
+_OLLAMA_REASONING_TAGS = ("qwen3", "gemma4", "gemma-4", "deepseek-r1", "qwq", "magistral")
+
+
+def _is_local_ollama_provider(provider: str) -> bool:
+    """True for ollama-local and legacy ``ollama`` (not ollama-cloud)."""
+    key = provider.strip().lower().replace("_", "-")
+    return key in {"ollama-local", "ollama"}
+
+
+def _looks_like_reasoning_model(model_name: str) -> bool:
+    name = model_name.lower()
+    return any(tag in name for tag in _OLLAMA_REASONING_TAGS)
+
+
+def _parse_int(raw: object) -> int | None:
+    if raw is None or raw == "":
+        return None
+    try:
+        return int(raw)
+    except (TypeError, ValueError):
+        return None
+
+
+def _strict_positive_int(raw: object) -> tuple[int | None, bool]:
+    """Return ``(value, invalid)``. Unset is ``(None, False)``; garbage or ``<1`` is invalid."""
+    if raw is None or raw == "":
+        return None, False
+    if isinstance(raw, bool) or not isinstance(raw, int):
+        return None, True
+    if raw < 1:
+        return None, True
+    return raw, False
+
+
+def _add_ollama_local_checks(
+    report: CommandReport,
+    *,
+    provider: str,
+    model_name: str,
+    thinking_budget: object,
+    num_ctx: object,
+) -> None:
+    """Warn on local-Ollama prefix-cache traps. Always emit the four check ids."""
+    local = _is_local_ollama_provider(provider)
+    mlx = "-mlx" in model_name.lower()
+    check(
+        report,
+        id="ollama.local.mlx_runner",
+        category="provider",
+        severity="warning",
+        passed=not mlx,
+        skip=not local,
+        message=(
+            f"model.name {model_name!r} looks like an MLX pack; prefix KV cache "
+            "often does not reuse between agent steps"
+            if mlx
+            else "model.name is not an MLX pack"
+        ),
+        field="model.name",
+        value=model_name or None,
+        remediation=(
+            f"Prefer a GGUF tag for tool-calling loops. See {_OLLAMA_LOCAL_DOCS}." if mlx else None
+        ),
+        docs=_OLLAMA_LOCAL_DOCS,
+    )
+    budget = _parse_int(thinking_budget)
+    if budget is None:
+        budget = -1
+    reasoning = _looks_like_reasoning_model(model_name)
+    thinking_on_default = budget == -1
+    check(
+        report,
+        id="ollama.local.thinking_default",
+        category="provider",
+        severity="warning",
+        passed=not thinking_on_default,
+        skip=not local or not reasoning,
+        message=(
+            "thinking_budget is -1 (server default); reasoning models generate "
+            "thinking tokens before the first visible reply"
+            if thinking_on_default
+            else f"thinking_budget is {budget}"
+        ),
+        field="model.thinking_budget",
+        value=budget,
+        remediation=(
+            f"Set thinking_budget: 0 to send reasoning_effort: none. See {_OLLAMA_LOCAL_DOCS}."
+            if thinking_on_default
+            else None
+        ),
+        docs=_OLLAMA_LOCAL_DOCS,
+    )
+    ctx, ctx_invalid = _strict_positive_int(num_ctx)
+    check(
+        report,
+        id="ollama.local.num_ctx_invalid",
+        category="provider",
+        severity="error",
+        passed=not ctx_invalid,
+        skip=not local or (ctx is None and not ctx_invalid),
+        message=(
+            f"num_ctx must be a positive integer, got {num_ctx!r}"
+            if ctx_invalid
+            else (f"num_ctx is {ctx}" if ctx is not None else "num_ctx is unset")
+        ),
+        field="model.num_ctx",
+        value=num_ctx,
+        remediation=(
+            f"Set a positive integer num_ctx (e.g. 8192), or omit it. See {_OLLAMA_LOCAL_DOCS}."
+            if ctx_invalid
+            else None
+        ),
+        docs=_OLLAMA_LOCAL_DOCS,
+    )
+    large = ctx is not None and ctx > _OLLAMA_NUM_CTX_LARGE
+    check(
+        report,
+        id="ollama.local.num_ctx_large",
+        category="provider",
+        severity="warning",
+        passed=not large,
+        skip=not local or ctx is None or ctx_invalid,
+        message=(
+            f"num_ctx {ctx} is large for a local runner; prefill will be slow"
+            if large
+            else (f"num_ctx is {ctx}" if ctx is not None else "num_ctx is unset")
+        ),
+        field="model.num_ctx",
+        value=ctx,
+        remediation=(
+            f"Pin a modest num_ctx (e.g. 8192). Do not copy context_window. See {_OLLAMA_LOCAL_DOCS}."
+            if large
+            else None
+        ),
+        docs=_OLLAMA_LOCAL_DOCS,
+    )
+
+
 def run_doctor(args: argparse.Namespace) -> int:
     cwd = Path(args.cwd).expanduser().resolve() if args.cwd else None
     config_path = resolve_config(args.config, cwd=cwd)
@@ -324,6 +464,19 @@ def run_doctor(args: argparse.Namespace) -> int:
             skip=True,
         )
 
+    thinking_raw = model.get("thinking_budget") if isinstance(model, dict) else None
+    if thinking_raw is None:
+        thinking_raw = "-1"
+    num_ctx_raw = model.get("num_ctx") if isinstance(model, dict) else None
+    model_name = str(model.get("name", "")).strip() if isinstance(model, dict) else ""
+    _add_ollama_local_checks(
+        report,
+        provider=provider,
+        model_name=model_name,
+        thinking_budget=thinking_raw,
+        num_ctx=num_ctx_raw,
+    )
+
     runtime_cfg = doc.get("runtime") if isinstance(doc.get("runtime"), dict) else {}
     port = int(runtime_cfg.get("port", 8080)) if isinstance(runtime_cfg, dict) else 8080
     free = _port_free(port)

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/src/monkeybot_cli/commands/validate.py

@@ -17,7 +17,7 @@ from monkeybot.core.config import (
     validate_monkeybot_yaml_doc,
     validate_provider_env,
 )
-from monkeybot.core.config.runtime_env import ENV_MAP
+from monkeybot.core.config.runtime_env import _flatten_config
 from monkeybot.core.config.settings import ConfigError, normalize_model_provider
 from monkeybot.core.config.yaml_loader import load_monkeybot_yaml_dict
 from monkeybot.core.layout import resolve_agent_root
@@ -35,18 +35,7 @@ def _resolve_path(base: Path, rel: str) -> Path:
 
 
 def _flatten_to_env(doc: dict[str, Any]) -> dict[str, str]:
-    out: dict[str, str] = {}
-    for (section, key), env_name in ENV_MAP.items():
-        sec = doc.get(section)
-        if not isinstance(sec, dict) or key not in sec:
-            continue
-        raw = sec[key]
-        if raw is None:
-            continue
-        if isinstance(raw, bool):
-            out[env_name] = "true" if raw else "false"
-        else:
-            out[env_name] = str(raw)
+    out = _flatten_config(doc)
     gcp = doc.get("gcp") if isinstance(doc.get("gcp"), dict) else {}
     if isinstance(gcp, dict) and gcp.get("project_id"):
         out["GCP_PROJECT_ID"] = str(gcp["project_id"])

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/src/monkeybot_cli/realtime/talk_ui.py

@@ -78,7 +78,6 @@ def _spawn_combined_gateway(
         env["MONKEYBOT_CONFIG"] = str(config_path)
     env["PORT"] = str(port)
     env.setdefault("LOG_LEVEL", "error")
-    env.setdefault("MONKEYBOT_TRANSCRIPT_ENABLED", "1")
     log_file = tempfile.NamedTemporaryFile(
         mode="w+",
         prefix="monkeybot-gateway-",

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/src/monkeybot_cli/scaffold.py

@@ -176,6 +176,13 @@ def install_loop_skill(dest: Path, *, force: bool) -> str:
     return _install_file(target, resources.files(_DEFAULTS_PKG) / "loop" / "SKILL.md", force=force)
 
 
+def install_goal_skill(dest: Path, *, force: bool) -> str:
+    """Install the bundled native-goal procedure into ``skills/goal``."""
+    target = dest / "skills" / "goal" / "SKILL.md"
+    target.parent.mkdir(parents=True, exist_ok=True)
+    return _install_file(target, resources.files(_DEFAULTS_PKG) / "goal" / "SKILL.md", force=force)
+
+
 def install_env_example(dest: Path, *, force: bool) -> str:
     env_example = dest / ".env.example"
     if env_example.exists() and not force:
@@ -399,6 +406,7 @@ def run_refresh(*, dest: Path) -> list[str]:
     report.append(refresh_permissions_if_default(cfg_dir))
     report.append(refresh_monkeybot_yaml(cfg_dir))
     report.extend(ensure_memory(dest, force=False))
+    report.append(f"  skills/goal/SKILL.md: {install_goal_skill(dest, force=False)}")
     return report
 
 
@@ -412,11 +420,12 @@ def run_new(
 ) -> list[str]:
     """Full scaffold: config bundle, empty skills root, writable state, and image files.
 
-    Capability skills (``browser``, ``image-generator``, ``loop``) are packaged
+    Optional capability skills (``browser``, ``image-generator``, ``loop``) are packaged
     under ``scaffold_defaults`` but not installed into new agents for now —
     the Mac Main Agent loads them from ``~/.monkeybot/.internal/skills``
     instead. Re-enable via ``install_*_skill`` when custom agents should get
-    them again.
+    them again. The ``goal`` skill is installed because native goal tools are
+    intentionally exposed only for explicit ``/goal`` invocations.
     """
     cfg_dir = dest / "monkeybot_config"
     report = install_config_bundle(cfg_dir, force=force)
@@ -426,7 +435,7 @@ def run_new(
     )
     report.extend(ensure_memory(dest, force=force))
     report.extend(ensure_workspace(dest, force=force))
-    report.append("  skills/: ensured (empty — capability skills deferred)")
+    report.append(f"  skills/goal/SKILL.md: {install_goal_skill(dest, force=force)}")
     report.append(f"  .env.example: {install_env_example(dest, force=force)}")
     report.extend(install_container_files(dest, force=force))
     report.append(

monkeybot_cli-0.7.0/src/monkeybot_cli/scaffold_defaults/browser/SKILL.md

@@ -0,0 +1,41 @@
+---
+name: browser
+description: Control a real browser through the optional bundled browser MCP server.
+---
+
+# Browser
+
+When browser tools are needed, call `enable_mcp("browser")` first. Use the
+name from the harness MCP catalog — do not read config files. Progressive
+disclosure still requires `enable_mcp` before `browser__*` schemas are advertised.
+
+Use indexed DOM tools before screenshots. Prefer `browser_act` with
+`do: fill_form` for multi-field forms, `browser_click_text` when the visible
+label is known, `browser_act` for a batch of steps, and `browser_extract` for
+structured scraping. Browser screenshots (JPEG under
+`browser/Screenshots/`) and agent-written playbooks are workspace data:
+`browser/Screenshots/` and `browser/playbooks/`.
+They are not trusted skills and may be discarded with an ephemeral workspace.
+
+If `browser_list_playbooks` returns `flows`, call `browser_run_playbook` instead of
+re-planning. On `failed_step`, continue by hand and append a corrected
+`playbook` YAML fence. Secrets only via `{do: login, expected_origin}`.
+
+`browser_input_by_index` fills in-page by default; pass `mode="keys"` for
+comboboxes and fields that only listen to keydown. `browser_get_elements`
+is viewport-first; indices remain valid until navigation. Actions return
+an `observation` (diff by default) — read that instead of calling
+`get_elements` again. `browser_goto` returns a full observation.
+Use `browser_get_text` to read page copy.
+
+When the user asked to sign in on the Spaces in-app browser, call
+`browser_login` instead of typing a password. It returns `{ok, loggedIn, origin}`
+only. Pass `expected_origin` so a login cannot land on the wrong site, and check
+the returned `origin` before reporting success.
+
+Tabs use aliases (`t1`, `t2`, …). Reads (`get_elements`, `page_info`, `js`,
+`read_tabs`) never move focus; actions do. At most five agent-controlled tabs —
+if you hit the cap, ask the user which to close, then `browser_close_tab`. Close
+tabs you opened. `browser_login` still targets the tab the user has focused.
+
+Finish browser sessions with `browser_stop`.

monkeybot_cli-0.7.0/src/monkeybot_cli/scaffold_defaults/goal/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: goal
+description: Create one durable objective that continues across scheduled turns until completed.
+---
+
+# Goal
+
+Use this skill only when the user explicitly invokes `/goal` with an objective
+that may require multiple turns.
+
+## Start
+
+1. Preserve the user's complete objective without narrowing its scope.
+2. Call `create_goal` exactly once with that objective.
+3. Do the first concrete increment of work in the same turn.
+4. Keep the returned goal id; every `update_goal` call must include it.
+
+## Continue
+
+- Goal continuations are scheduled automatically.
+- Treat the stored objective as authoritative.
+- Make measurable progress and verify results before declaring completion.
+- Temporary session-busy deferrals are normal and are not goal failures.
+- Persistent execution failures stop the goal after the retry limit so it
+  cannot consume resources indefinitely.
+
+## Complete
+
+Call `update_goal` with the returned `goal_id` and `status="complete"` only
+after evidence proves every requirement is satisfied. Otherwise leave the goal
+active. Use the `/goals` control plane to pause, resume, or stop it manually.

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/src/monkeybot_cli/scaffold_defaults/monkeybot.example.yaml

@@ -2,7 +2,9 @@
 #
 #   cp monkeybot_config/monkeybot.example.yaml monkeybot_config/monkeybot.yaml
 #
-# Precedence: environment variables (and optional root `.env`) win over values here.
+# Precedence: environment variables (and optional root `.env`) win over values here
+# except ``model.*`` (provider, name, temperature, max_tokens, thinking_budget,
+# context_window, summarization_model, max_turns, cache_retention) which are YAML-only.
 #
 # Secrets are not committed here. Create a `.env` in the repo root when you need keys or
 # machine-local paths, for example:
@@ -29,7 +31,7 @@ runtime:
   # Internal debugging only (not agent-visible): write every AgentEvent and raw
   # provider request/response for each session to
   # {workspace_root}/.monkeybot/transcripts/{UTC}_{session_id}/transcript.ndjson.
-  # (env: MONKEYBOT_TRANSCRIPT_ENABLED)
+  # YAML-only (not overridable via environment).
   transcript_enabled: true
 
 # Required: choose the conversational harness for this deployment.
@@ -45,7 +47,7 @@ realtime:
   # Optional model override for the realtime session. Live-only models (e.g.
   # gemini-3.1-flash-live-preview) cannot be used for turn-based work, so the
   # realtime session can point to a different model than model.name. When omitted,
-  # the realtime session falls back to model.name and MODEL_PROVIDER.
+  # the realtime session falls back to model.name and model.provider.
   # model:
   #   name: gemini-3.1-flash-live-preview
   #   provider: google_genai
@@ -98,10 +100,16 @@ model:
   # Summarisation trigger (tokens). Also drives soft-spill / read_file char budgets.
   context_window: 1000000
   max_turns: 1000
-  # Prompt-cache session hints: none | short | long (env: MODEL_CACHE_RETENTION)
+  # Prompt-cache session hints: none | short | long (YAML-only)
   # cache_retention: short
-  # Optional cheaper model for sync history summarization (env: CONTEXT_SUMMARIZATION_MODEL); omit = main model
+  # Optional cheaper model for sync history summarization; omit = main model
   # summarization_model: gemini-3-flash
+  # Ollama-local only (YAML). Default 24h so the KV prefix cache survives idle.
+  # Set "0" to omit. Distinct from the Ollama daemon env OLLAMA_KEEP_ALIVE.
+  # keep_alive: 24h
+  # Ollama-local only (YAML). Pin llama num_ctx; omit = server default.
+  # Do NOT copy context_window here — that budget is summarization/spill, often 1M.
+  # num_ctx: 8192
 
 # Non-secret GCP identifiers (prefer .env for secrets / ADC path).
 # gcp:
@@ -127,8 +135,6 @@ memory:
   backend: chroma
   embedding_model: embeddinggemma-300m
 
-# context_curation is unused after MemPalace wake-up replaced INDEX.md + curator.
-
 emission:
   # Terse emission-style guidance injected into the cached harness prefix.
   # Two named modes:
@@ -247,7 +253,18 @@ scheduler:
   # Env override: MONKEYBOT_SCHEDULER_ENABLED (1 | true | yes | on).
   enabled: false
 
-# Optional JSON for MODEL_PROVIDER=fake tests (env: MONKEYBOT_FAKE_PROVIDER_EVENTS)
+# Background verifier (YAML-only). Off by default: ledger costs one model call
+# per human message. `enabled: true` turns on omitted ledger/tracker flags;
+# omitted judge.enabled turns on only when the tracker is on. Explicit
+# `enabled: false` still opts a nested section out. Omitted ledger.model /
+# judge.model inherit model.name (same fallback as the agent). The live
+# worker is session-bound ProviderJudge. Realtime loops ignore this block.
+# verifier:
+#   enabled: true
+#   escalation:
+#     max_severity: nudge
+
+# Optional JSON for model.provider: fake tests (env: MONKEYBOT_FAKE_PROVIDER_EVENTS)
 # fake_provider:
 #   events_json: '[[]]'
 

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/tests/test_chat_e2e.py

@@ -25,6 +25,11 @@ def _free_port() -> int:
 def test_chat_repl_round_trip_with_fake_gateway(tmp_path: Path) -> None:
     port = _free_port()
     base = f"http://127.0.0.1:{port}"
+    (tmp_path / "monkeybot_config").mkdir()
+    (tmp_path / "monkeybot_config" / "monkeybot.yaml").write_text(
+        "model:\n  provider: fake\n  name: fake\n",
+        encoding="utf-8",
+    )
     agent = tmp_path / "AGENT.md"
     agent.write_text("# Test agent\nYou are a test assistant.\n", encoding="utf-8")
     policy = tmp_path / "command_allowlist.yaml"
@@ -40,7 +45,6 @@ def test_chat_repl_round_trip_with_fake_gateway(tmp_path: Path) -> None:
             "DB_URL": f"sqlite:///{tmp_path / 'mb.db'}",
             "MCP_CONFIG": str(tmp_path / "no_mcp.json"),
             "MEMORY_PATH": str(tmp_path / "memory"),
-            "MODEL_PROVIDER": "fake",
             "PORT": str(port),
             "SKILLS_PATH": str(tmp_path / "skills"),
             "MONKEYBOT_CHAT_PLAIN": "1",

{monkeybot_cli-0.5.1 → monkeybot_cli-0.7.0}/tests/test_chat_session.py

@@ -430,7 +430,7 @@ def test_close_deletes_session_and_captures_report_dir() -> None:
                 200,
                 json={
                     "deleted": True,
-                    "transcript_report_dir": "/tmp/ws/.monkeybot/transcripts/20260714T150000Z_sess-close",
+                    "transcript_dir": "/tmp/ws/.monkeybot/transcripts/20260714T150000Z_sess-close",
                 },
                 request=request,
             )
@@ -441,7 +441,7 @@ def test_close_deletes_session_and_captures_report_dir() -> None:
         await controller.close()
         client.delete.assert_awaited_once_with("http://localhost:8080/sessions/sess-close")
         assert (
-            controller.transcript_report_dir
+            controller.transcript_dir
             == "/tmp/ws/.monkeybot/transcripts/20260714T150000Z_sess-close"
         )
         client.aclose.assert_awaited_once()