@lmctl-ai/lmctl 0.1.82 → 0.1.84

package/durable-memory/model_selection.md

@@ -0,0 +1,138 @@
+# Model Selection
+
+`model=` on a `_MEMBER_` line is a provider-specific model request.
+
+For `.lmctl` teamfile compatibility mode:
+
+- `lmctl lint <teamfile>` warns when a requested model is not in the
+  tested-model catalog for `claude`, `codex`, `gemini`, `qwen`, or `agy`.
+- `opencode` model validation reads configured models from
+  `~/.config/opencode/opencode.json` and WARNS (never injects) when a
+  `model=` isn't declared there and isn't a config-free github-copilot
+  GPT/Gemini/o-series id. See the `## OpenCode` section below.
+- `copilot` accepts `model=` syntactically, but model selection is not
+  supported and lint warns that the value is ignored.
+- `lmctl seed <teamfile>` passes `model=` through to the provider seed
+  call. It does not contact provider model catalogs.
+
+The runtime also carries a built-in fallback catalog so installed
+`lmctl` can lint without requiring this source-tree document to be
+present in `dist`. Keep this document and
+`src/providers/config/model-selection-lint.ts` synchronized when adding
+or retiring tested model ids.
+
+## Claude
+
+| Configured `model=` | Evidence |
+| --- | --- |
+| `claude-opus-4-6` | Ported from lmctl0 tested-model catalog. |
+| `claude-opus-4-7` | Ported from lmctl0 tested-model catalog. |
+| `claude-opus-4-8` | Added from operator-confirmed availability on 2026-06-13; `lmctl lint` compatibility smoke accepts it. |
+| `claude-sonnet-4-6` | Ported from lmctl0 tested-model catalog. |
+| `claude-sonnet-5` | Operator-confirmed 2026-07-05 (via GitHub Copilot: `opencode --model github-copilot/claude-sonnet-5 run …` → "build · claude-sonnet-5"). Also a valid native Claude Code model id (`claude --model claude-sonnet-5`). |
+| `claude-haiku-4-5` | Ported from lmctl0 tested-model catalog. |
+| `claude-fable-5` | Session observed locally via `lmctl0 ls` on 2026-06-11; `lmctl lint` compatibility smoke accepts it. Anthropic announced on 2026-06-12 that access to Fable 5 was suspended for customers; keep the id valid for existing teamfiles, but do not use it for new work while unavailable. |
+
+## Codex
+
+| Configured `model=` | Evidence |
+| --- | --- |
+| `gpt-5.2` | Ported from lmctl0 tested-model catalog. |
+| `gpt-5.4` | Ported from lmctl0 tested-model catalog. |
+| `gpt-5.5` | Ported from lmctl0 tested-model catalog. |
+| `gpt-5.4-mini` | Ported from lmctl0 tested-model catalog. |
+| `gpt-5.3-codex` | Ported from lmctl0 tested-model catalog. |
+| `gpt-5.3-codex-spark` | Ported from lmctl0 tested-model catalog. |
+
+## Gemini
+
+| Configured `model=` | Evidence |
+| --- | --- |
+| `gemini-3.1-pro-preview` | Ported from lmctl0 tested-model catalog. |
+| `gemini-3-flash-preview` | Ported from lmctl0 tested-model catalog. |
+| `gemini-3.1-flash-lite-preview` | Ported from lmctl0 tested-model catalog. |
+| `gemini-2.5-flash` | Ported from lmctl0 tested-model catalog. |
+| `gemini-2.5-flash-lite` | Ported from lmctl0 tested-model catalog. |
+
+## Qwen
+
+| Configured `model=` | Evidence |
+| --- | --- |
+| `qwen3.5-plus` | Ported from lmctl0 tested-model catalog. |
+| `qwen3.6-plus` | Ported from lmctl0 tested-model catalog. |
+
+## Antigravity
+
+Antigravity (`agy`) is a distinct provider from Gemini even though it stores
+state under `~/.gemini/antigravity-cli`. `lmctl` supports it through native
+terminal resume plus one-shot `agy -p` turns.
+
+| Configured `model=` | Evidence |
+| --- | --- |
+| `gemini-1.5-flash` | Ported from lmctl0 tested-model catalog. |
+| `gemini-1.5-pro` | Ported from lmctl0 tested-model catalog. |
+| `gemini-3.5-flash` | Ported from lmctl0 tested-model catalog. |
+| `gemini-3.1-pro` | Ported from lmctl0 tested-model catalog. |
+| `gpt-oss-120b` | Ported from lmctl0 tested-model catalog. |
+| `gpt-4-turbo` | Ported from lmctl0 tested-model catalog. |
+| `gpt-4` | Ported from lmctl0 tested-model catalog. |
+| `gpt-3.5-turbo` | Ported from lmctl0 tested-model catalog. |
+| `claude-3-opus` | Ported from lmctl0 tested-model catalog. |
+| `claude-3-sonnet` | Ported from lmctl0 tested-model catalog. |
+| `claude-3-haiku` | Ported from lmctl0 tested-model catalog. |
+
+## OpenCode
+
+opencode model ids use `<provider>/<model>` shape. **lmctl does NOT manage opencode
+model config.** When lmctl spawns an opencode member it writes only
+`permission: "allow"` (the YOLO contract — opencode ACP has no
+`--dangerously-skip-permissions` flag) plus its own `mcp.lmctl` bridge entry into
+the member's `.opencode/opencode.json`. It never injects a provider/model catalog.
+Models resolve from **opencode's own default models.dev catalog + your
+`~/.config/opencode/opencode.json`** — you own the model config.
+
+What needs declaring:
+- **github-copilot GPT / Gemini / o-series** → served **config-free** from opencode's
+  default catalog. Just `opencode auth login github-copilot`, then
+  `model=github-copilot/gpt-5.5`, etc.
+- **github-copilot Claude** (`claude-opus-4.8`, `claude-sonnet-5`, …) → **must be
+  declared** in your `opencode.json`. Copilot proxies Claude through its own API and
+  opencode's default catalog does not route them (→ "404 page not found"); declaring
+  them under a `github-copilot` provider (`@ai-sdk/openai-compatible`,
+  `baseURL https://api.githubcopilot.com`) fixes it.
+- **Custom providers** (`deepseek/*`, `z-ai-coding/*`, `openrouter/*`,
+  `ollama-local/*`, …) → **must be declared** (not in models.dev).
+
+Copy the published sample and adjust for your account:
+
+```sh
+mkdir -p ~/.config/opencode
+cp examples/opencode.json ~/.config/opencode/opencode.json   # or: curl -sL https://lmctl.com/examples/opencode.json -o ~/.config/opencode/opencode.json
+```
+
+**Lint = detect + warn (never inject).** `lmctl lint`/`seed` warns when a
+`provider=opencode model=` is **not declared** in your `opencode.json` and isn't a
+config-free github-copilot GPT/Gemini/o id — pointing you at the sample. It also
+warns when `model=` is absent (opencode would silently pick its own default). It
+does not edit your config.
+
+`effort=`/variants: an opencode member's `effort=` maps to opencode's `--variant`
+(reasoning effort). Declare the variants on the model in your `opencode.json` (see
+the sample's Claude/GPT entries with `variants: { high, xhigh, max }`); on the ACP
+chat path lmctl sends `session/set_config_option` with `configId: "model"` and
+`configId: "effort"` before `session/prompt`.
+
+Example:
+
+```md
+_MEMBER_ alias=Reviewer provider=opencode model=github-copilot/gpt-5.4 effort=xhigh sessionid=<seeded-id>
+```
+
+`effort=` support by provider:
+
+| Provider | Status |
+| --- | --- |
+| `opencode` | Supported (via the model's declared `variants` in opencode.json). |
+| `claude` | Claude Code has native `--effort`, but lmctl has not wired `_MEMBER_ effort=` to Claude yet. |
+| `codex` | Native effort surfaces exist; lmctl has not wired `_MEMBER_ effort=` to Codex yet. |
+| `agy` | No verified effort flag; only `--model` supported. |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lmctl-ai/lmctl",
-  "version": "0.1.82",
+  "version": "0.1.84",
   "description": "A provider-agnostic control plane for teams of AI coding agents — across providers, with independent review and durable memory.",
   "type": "module",
   "homepage": "https://lmctl.com",
@@ -13,6 +13,7 @@
     "dist/cli/schema.sql",
     "dist/cli/side_effect_classifier.json",
     "dist/config/",
+    "durable-memory/model_selection.md",
     "workflows/",
     "bin/",
     "package.json",