min-agent 0.6.9 → 0.7.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "min-agent",
-  "version": "0.6.9",
+  "version": "0.7.1",
   "type": "module",
   "description": "Minimal AI coding agent with tool use, MCP, and skills support",
   "license": "MIT",

package/skills/self-config/SKILL.md

@@ -80,16 +80,18 @@ Instructions...
 
 - Rules: edit the files in the table above. `/reload` reloads rules only, not MCP.
 - Memory: **off** by default. Config `memory` is `on` | `off` (`true`/`enable` → on, `false`/`disable` → off). Project overlays global; writing `memory` globally also removes a project `memory` overlay. When off, memories are not injected and `memory_save` / `memory_search` / `memory_delete` are not registered (takes effect next turn after you change the file). CLI `min-agent memory on|off` / `--memory` follow the same write-vs-this-run rule as permission. `/memory on|off` writes **global** by default (and clears a project overlay); `/memory --project` writes only the project file. `/memory` lists the switch plus stored entries; `/memory <text>` still writes `memory.json` even when off. Default save scope is project when `.min-agent/` exists. Shape: `{ "content": string, "tags": string[], "created": ISO string }` array. When on, memories are injected each turn as background reference, not as work to resume. Do not store secrets or API keys. HTTP: `GET/POST /v1/memory/mode`, chat body `memory`, and `GET /v1/memory` include `memory` / `source` / `label`.
-- Permission: `accept-edits` (default) | `ask` | `allow-all` in config `permission`. CLI `min-agent permission …` / `--permission` without a message writes config and exits; with a message it is this session only. `--yes` is this session only and does not write config. `min-agent exec` (one-shot) uses a permissive default when neither `--permission` nor `--yes` is given: file edits and ordinary commands run without asking, and only genuinely destructive commands (deleting files/dirs, `drop`/`truncate`/`delete from`, `mkfs`/`dd`/raw-device writes, `shred`/`wipefs`, `git reset --hard`/`git clean -f`, `docker rm`/`prune`, `find … -delete`/`-exec rm`) still prompt. An explicit `--permission` (or `--yes`) overrides this and behaves exactly as in interactive sessions (`allow-all` runs even destructive commands silently). Confirmation prompts are coalesced: when several actions in one step need approval, a single overlay lists them all and one allow/deny decision applies to the whole batch instead of stacking separate prompts.
+- Permission: `accept-edits` (default) | `ask` | `allow-all` in config `permission`. CLI `min-agent permission …` / `--permission` without a message writes config and exits; with a message it is this session only. `--yes` is this session only and does not write config. `min-agent exec` (one-shot) uses a permissive default when neither `--permission` nor `--yes` is given: file edits and ordinary commands run without asking, and only genuinely destructive commands (deleting files/dirs, `drop`/`truncate`/`delete from`, `mkfs`/`dd`/raw-device writes, `shred`/`wipefs`, `git reset --hard`/`git clean -f`, `docker rm`/`prune`, `find … -delete`/`-exec rm`) still prompt. An explicit `--permission` (or `--yes`) overrides this and behaves exactly as in interactive sessions (`allow-all` runs even destructive commands silently). In `ask` / `accept-edits`, "dangerous commands" that still prompt do NOT include ordinary `git push`, `git stash`/`git stash pop`, `git rebase`, or `chmod` — only their harmful forms count: force pushes (`git push --force`/`-f`/`--force-with-lease`) and `git stash drop`/`git stash clear` (plus `git reset --hard`, `git clean -f`, `git checkout .`, `rm -r/-f`, `sudo`, disk/db operations, etc.). Confirmation prompts are coalesced: when several actions in one step need approval, a single overlay lists them all and one allow/deny decision applies to the whole batch instead of stacking separate prompts.
 - Thinking intensity: `off` | `low` | `medium` | `high` | `max` in config `thinking`. Omit the field to use **medium**, then clamp to levels the current model actually exposes (from the model catalog). `/think` opens an interactive picker of those English levels and writes **global** config; that also clears a project `thinking` overlay so a leftover project `off` cannot hide the new value after restart. `/think --project` writes only the project file. Typed `/think off|low|medium|high|max` still works when the model supports that value. `min-agent think …` / `--think` follow the same write-vs-this-run rule as permission. `xhigh` / `extra-high` / `none` are accepted as aliases (`xhigh` → `max`, `none` → `off`). Each request maps that intensity onto the current model and gateway (MiniMax uses `adaptive`/`disabled`; official OpenAI omits `thinking` and maps `max` to `xhigh`; an `ollama` provider uses native chat with `think` plus the configured window). Learned mappings are cached in `~/.min-agent/thinking-wire-cache.json` for 7 days. Per-model context window and supported effort values are loaded from the model catalog (`https://models.lonae.com`, override with `MIN_AGENT_MODELS_API_URL`) and cached in `~/.min-agent/model-catalog-cache.json` for 7 days after a successful lookup. When the provider host is unknown, effort levels are the majority across offerings that actually list efforts (toggle-only rows do not vote), so a single gateway cannot invent `medium`. An `ollama` provider skips that catalog and uses native `POST /api/show` instead (whether the model advertises thinking, plus the loaded window: Modelfile `num_ctx` if set, otherwise the architecture length capped at 32768). Chat completions are sent to native `POST /api/chat` so `options.num_ctx` and `think` actually apply — the OpenAI-compatible `/v1` endpoint ignores both. `/ctx` opens a picker of `2k` / `4k` / `8k` / `12k` / `16k` / `32k` / `64k` / `128k` / `256k` / `auto` and writes the active provider's `contextWindow` (global only; providers are not in project config). Typed `/ctx 8k` and CLI `min-agent ctx 8k` do the same; `auto` clears the override. The menu item is hidden unless the active provider is ollama. Results are cached in `~/.min-agent/ollama-model-cache.json` for 7 days.
 - Sandbox default is **off**. `mode`: `off` | `workspace` | `strict`. Optional `network`, `extraWriteRoots`, `extraReadRoots`. Isolation is independent of permission. `--sandbox` / `--network` without a message write config and exit.
 
 ## Providers
 
-Only in global `config.json`: `providers[]` with `name`, `type` (`openai-compatible` | `openai` | `ollama`), `baseURL`, `apiKey`, optional `defaultModel`, `contextWindow`. `activeProvider` selects one. Project config may set `activeProvider` and `defaultModel` (no keys). If `providers` is missing or empty, a built-in OpenRouter provider (`openrouter`, model `openrouter/free`) is used at runtime and is not written to disk. The preset is **locked**: while it is the active provider, `min-agent setup` rejects adding, editing, switching, or removing providers, the model list is fixed to `openrouter/free` (never fetched), and only that model can be selected (`/model`, `--model`, chat `model`). `MIN_AGENT_NO_BUILTIN_PROVIDER=1` disables the fallback — with it set (or once any user provider exists) the lock no longer applies and setup works normally.
+Only in global `config.json`: `providers[]` with `name`, `type` (`openai-compatible` | `openai` | `ollama`), `baseURL`, `apiKey`, optional `defaultModel`, `contextWindow`. `activeProvider` selects one. Project config may set `activeProvider` and `defaultModel` (no keys). If `providers` is missing or empty, a built-in OpenRouter provider (`openrouter`, model `openrouter/free`) is used at runtime and is not written to disk. While that preset is the active provider it is **locked against edits**: it cannot itself be edited, switched away from, or removed (`min-agent setup --switch/--remove` refuse it), the model list is fixed to `openrouter/free` (never fetched), and only that model can be selected (`/model`, `--model`, chat `model`). But you can **always add** your own provider — `min-agent setup --type …` and the wizard's "添加" entry work even while the preset is active, and once a usable provider exists it takes over automatically (the preset is no longer injected, so the lock lifts). `MIN_AGENT_NO_BUILTIN_PROVIDER=1` disables the fallback entirely.
 
 `/provider` opens an interactive picker and writes **global** `activeProvider`; that also clears a project `activeProvider` overlay so the choice is what later turns use. Typed `/provider <name>` still works. Adding, editing, or removing providers is `min-agent setup` (not the TUI picker).
 
-CLI: `min-agent setup` (interactive wizard or flags). Flags: `--type openai-compatible|openai|ollama`, `--url`, `--api-key`, `--name`, `--default-model`, `--switch <name>`, `--remove <name>`. `--yes` skips overwrite/delete confirmation during setup; it does not change permission. Keys only in the global file. While the preset is active the wizard only shows the locked built-in provider (test connection / done).
+CLI: `min-agent provider` (no args) prints the active provider and the available list; `min-agent provider <name>` switches the active provider (writes global `activeProvider`, clears the project overlay). Add/edit/remove go through `min-agent setup` (interactive wizard or flags): `--type openai-compatible|openai|ollama`, `--url`, `--api-key`, `--name`, `--default-model`, `--switch <name>`, `--remove <name>`. `--yes` skips overwrite/delete confirmation during setup; it does not change permission. Keys only in the global file.
+
+HTTP: `GET /v1/provider` returns `{ active, providers[] }`; `POST /v1/provider` with `{ "provider": "<name>" }` switches (writes global, clears project overlay; no `scope`, since providers are global-only). Missing/empty name → `400 invalid_provider`; unknown name → `404 provider_not_found`.
 
 After changing keys or MCP connections, tell the user if a restart is required. Do not print full secrets back in chat.