monkeybot-cli 0.13.0__tar.gz → 0.13.2__tar.gz

{monkeybot_cli-0.13.0 → monkeybot_cli-0.13.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: monkeybot-cli
-Version: 0.13.0
+Version: 0.13.2
 Summary: CLI to create, configure, validate, and chat with monkeybot agents.
 Requires-Python: >=3.11
 Requires-Dist: httpx>=0.27.0

{monkeybot_cli-0.13.0 → monkeybot_cli-0.13.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "monkeybot-cli"
-version = "0.13.0"
+version = "0.13.2"
 description = "CLI to create, configure, validate, and chat with monkeybot agents."
 requires-python = ">=3.11"
 dependencies = [

{monkeybot_cli-0.13.0 → monkeybot_cli-0.13.2}/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 for `ENV_MAP` keys. `model.*` (provider, name, temperature, max_tokens, thinking_budget, reasoning_effort, 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.*`).
+**Precedence:** env vars and `.env` win over YAML for `ENV_MAP` keys. `model.*` (provider, name, temperature, max_tokens, thinking_budget, reasoning_effort, context_window, 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.*`).
 
 ---
 
@@ -34,7 +34,7 @@ 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.
+YAML-only for provider, name, sampling, context window, max turns, and cache retention. Leftover `MODEL_*` / `MAX_TURNS` env vars are ignored. History summarization and chat titles use `name`. A leftover `summarization_model` key is ignored.
 
 | Field | Default | When to change |
 |---|---|---|
@@ -48,7 +48,6 @@ YAML-only for provider, name, sampling, context window, summarization model, max
 | `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 (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`.
 

monkeybot_cli-0.13.2/src/monkeybot_cli/scaffold_defaults/goal/SKILL.md

@@ -0,0 +1,67 @@
+---
+name: goal
+description: Create one durable objective that continues across scheduled turns until evidence proves it is done.
+---
+
+# Goal
+
+Use this skill only when the user explicitly invokes `/goal` with an objective
+that may require multiple turns.
+
+A goal is complete only when current evidence proves every requirement of the
+objective. Stopping a turn, running out of time, or having a plausible answer
+does not finish it.
+
+There is no deadline that finishes the work. The goal stays active across turns
+until the end state is true, or until a budget pause or a persistent failure
+stops the ticks. A budget pause is not completion. The objective stays intact
+and the user can resume it.
+
+## 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. A webhook can also wake the goal.
+- Treat the stored objective as authoritative. Do not shrink it to work already done.
+- Make measurable progress. Verify results before you even consider completion.
+- Temporary session-busy deferrals are normal and are not goal failures.
+- Persistent execution failures stop the goal after the retry limit.
+- Using up the tick or runtime budget pauses the goal. It does not complete it.
+
+## Waiting
+
+If you are blocked on a person or an external event (review, approval, CI, a
+publish), call `update_goal` with `status="waiting"`, the goal id, and a
+`reason`. Pass `recheck_after` (for example `2h`) only when you should look
+again even if no event arrives. Do not keep waking on the timer while blocked.
+You cannot pause a goal. That is the user's control.
+
+## Complete
+
+Before `update_goal` with `status="complete"`, completion is unproven. In a
+separate step, after the evidence tool calls:
+
+1. Pull concrete requirements out of the objective and anything it points at
+   (files, plans, specs, issues, instructions). Do not shrink the original scope.
+2. For each requirement, name the evidence that would prove it, then look at
+   the current state: files, command output, tests, pull-request state, rendered
+   UI, runtime behavior.
+3. Judge each item as `proved`, `contradicted`, `incomplete`, `too_weak`, or
+   `missing`. A green test counts only if it covers that requirement. Uncertain
+   or indirect evidence is not done.
+4. The audit has to prove completion. Failing to notice leftover work is not enough.
+
+Intent, partial progress, memory of earlier turns, and a reasonable-sounding
+answer are not proof.
+
+Call `update_goal` with `status="complete"` and an `audit` array only after
+every item is `proved` and no required work remains. The call must be its own
+step so the transcript already contains the evidence. Ending the turn does not
+call `update_goal`. The goal stays active and the full objective stays intact.
+
+`status="active"` is only for resuming a goal the user paused.

{monkeybot_cli-0.13.0 → monkeybot_cli-0.13.2}/src/monkeybot_cli/scaffold_defaults/monkeybot.example.yaml

@@ -4,7 +4,7 @@
 #
 # Precedence: environment variables (and optional root `.env`) win over values here
 # except ``model.*`` (provider, name, temperature, max_tokens, thinking_budget,
-# reasoning_effort, context_window, summarization_model, max_turns, cache_retention)
+# reasoning_effort, context_window, 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
@@ -111,8 +111,6 @@ model:
   max_turns: 1000
   # Prompt-cache session hints: none | short | long (YAML-only)
   # cache_retention: short
-  # 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

monkeybot_cli-0.13.0/src/monkeybot_cli/scaffold_defaults/goal/SKILL.md

@@ -1,31 +0,0 @@
----
-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.