diff --git a/bin/gstack-capy-install b/bin/gstack-capy-install index 6122d76e4..4ad259627 100755 --- a/bin/gstack-capy-install +++ b/bin/gstack-capy-install @@ -725,11 +725,13 @@ fi record_verdict "$TRAILER" "$([ "$RC" -eq 0 ] && echo 1 || echo 0)" LOADOUT_LINES="" if [ "$RC" -eq 0 ] && [ -z "$MODEL" ] && [ -n "${GSTACK_PREFERENCES_FILE:-}" ] && [ -z "${GSTACK_EVAL_DIR:-}${EVALS_RUN_ID:-}" ] && [ "$PROFILE" -eq 0 ] && [ -n "$LAUNCH_FILE" ]; then - _ag_first=$(cd "$ROOT" && bin/gstack-models resolve --role agent 2>/dev/null | head -1) + _ag_out=$(cd "$ROOT" && bin/gstack-models resolve --role agent 2>&1) && _ag_rc=0 || _ag_rc=$? + _ag_first=$(printf '%s\n' "$_ag_out" | head -1) case "$_ag_first" in *", this machine") MODEL_SOURCE=config ;; *", the preferences file") MODEL_SOURCE=preferences ;; esac + [ "$_ag_rc" -eq 0 ] || LOADOUT_LINES="LOADOUT_FALLBACK: agent_model unreadable: $(printf '%s' "$_ag_first" | tr -d '\000-\037' | cut -c1-200); serving full (docs/troubleshooting.md#loadout-fallback)" [ "$MODEL_SOURCE" = GSTACK_MODEL ] || MODEL=$(printf '%s' "$_ag_first" | sed -n 's|^agent: [a-z0-9-]*/\([A-Za-z0-9._-]*\) .*|\1|p') fi if [ "$RC" -eq 0 ] && [ -n "$MODEL" ] && [ "$PROFILE" -eq 0 ] && [ -n "$LAUNCH_FILE" ]; then diff --git a/changelog.d/gsta161-gst-982-capy-model.md b/changelog.d/gsta161-gst-982-capy-model.md index 7bbe0e299..109ccbddb 100644 --- a/changelog.d/gsta161-gst-982-capy-model.md +++ b/changelog.d/gsta161-gst-982-capy-model.md @@ -1,7 +1,7 @@ **Capy sessions get their model's loadout again without a sentence in the skill (GST-982).** The browse wave (#3858) removed the Capy skill's instruction to run the installer with `GSTACK_MODEL`, to keep `capy/skill/gstack/SKILL.md` under its context budget. After that, every Capy session installed the full skills, including Opus 5.5 sessions that should get `lite`. Now the installer finds the model by itself. ### Fixed -- **`gstack-capy-install` reads the owner's model preference.** When it gets no `--model` and no `GSTACK_MODEL`, it uses the `agent_model` in the session's `GSTACK_PREFERENCES_FILE` (the Drive skill's `preferences.yaml`, which `gstack-capy-session` already exports), resolved by `gstack-models resolve --role agent`. So `opus` means `claude-opus-5-5` today. The line reads `LOADOUT: … source=preferences` (`source=config` when this machine's `config.yaml` sets it), followed by a `LOADOUT_ASSUMED:` note that the model came from the preference and not the session. Eval runs (`GSTACK_EVAL_DIR` or `EVALS_RUN_ID` set) skip the preference. `GSTACK_MODEL` and `--model` still win, and a `host` preference or no file still serves full. The frozen bootstrapper `capy/skill/gstack/scripts/install.sh` and the skill text are unchanged. +- **`gstack-capy-install` reads the owner's model preference.** When it gets no `--model` and no `GSTACK_MODEL`, it uses the `agent_model` in the session's `GSTACK_PREFERENCES_FILE` (the Drive skill's `preferences.yaml`, which `gstack-capy-session` already exports), resolved by `gstack-models resolve --role agent`. So `opus` means `claude-opus-5-5` today. The line reads `LOADOUT: … source=preferences` (`source=config` when this machine's `config.yaml` sets it), followed by a `LOADOUT_ASSUMED:` note that the model came from the preference and not the session. Eval runs (`GSTACK_EVAL_DIR` or `EVALS_RUN_ID` set) skip the preference, and a preference `gstack-models` cannot resolve prints `LOADOUT_FALLBACK` instead of serving full silently. `GSTACK_MODEL` and `--model` still win, and a `host` preference or no file still serves full. The frozen bootstrapper `capy/skill/gstack/scripts/install.sh` and the skill text are unchanged. ### Tests -- `test/gstack-capy-install.test.ts`: an `opus` preference picks lite with `source=preferences` and its own launch file, `GSTACK_MODEL` overrides the preference, a `config.yaml` preference reads `source=config`, eval runs skip the preference, a `host` preference prints no loadout lines, and the real `gstack-models resolve --role agent` keeps the `agent: /` first line the installer reads. +- `test/gstack-capy-install.test.ts`: an `opus` preference picks lite with `source=preferences` and its own launch file, `GSTACK_MODEL` overrides the preference, a `config.yaml` preference reads `source=config`, eval runs skip the preference, an unresolvable preference prints `LOADOUT_FALLBACK`, a `host` preference prints no loadout lines, and the real `gstack-models resolve --role agent` keeps the `agent: /` first line the installer reads. diff --git a/test/gstack-capy-install.test.ts b/test/gstack-capy-install.test.ts index 52db9a11a..3a651fbbe 100644 --- a/test/gstack-capy-install.test.ts +++ b/test/gstack-capy-install.test.ts @@ -605,6 +605,7 @@ describe('gstack-capy-install: launch PATH, Bun reuse, CI pins, setup skip, verd ]); script(path.join(f.root, 'bin/gstack-models'), [ 'echo "models $* prefs=${GSTACK_PREFERENCES_FILE:-}" >> "$CAPY_LOG"', + '[ -z "${FAKE_BAD_MODEL:-}" ] || { echo "agent: agent_model $FAKE_BAD_MODEL is not a model"; exit 1; }', '[ -z "${FAKE_CONFIG_MODEL:-}" ] || { echo "agent: anthropic/$FAKE_CONFIG_MODEL (opus) - from agent_model in $HOME/.gstack/config.yaml, this machine"; exit 0; }', 'case "$(sed -n "s/^agent_model: *//p" "${GSTACK_PREFERENCES_FILE:-/dev/null}" 2>/dev/null)" in', ' opus) echo "agent: anthropic/claude-opus-5-5 (opus) - from agent_model in $GSTACK_PREFERENCES_FILE, the preferences file" ;;', @@ -634,6 +635,13 @@ describe('gstack-capy-install: launch PATH, Bun reuse, CI pins, setup skip, verd } expect(f.calls().filter(l => l.startsWith('modules ')).length).toBe(modulesBefore); + const bad = run(f, ['--for', 'ship'], { GSTACK_PREFERENCES_FILE: prefs, FAKE_BAD_MODEL: 'gpt-6.1-sol' }); + expect(bad.status, bad.stdout + bad.stderr).toBe(0); + expect(bad.stdout).toContain('LOADOUT_FALLBACK: agent_model unreadable: agent: agent_model gpt-6.1-sol is not a model; serving full (docs/troubleshooting.md#loadout-fallback)\n'); + expect(bad.stdout).not.toMatch(/^(LOADOUT|SKILL_ROOT):/m); + expect(launchOf(bad.stdout)).toBe(verdicts(f)[0].replace(/\.json$/, '.env')); + expect(f.calls().filter(l => l.startsWith('modules ')).length).toBe(modulesBefore); + const env = run(f, ['--for', 'ship'], { GSTACK_PREFERENCES_FILE: prefs, GSTACK_MODEL: 'claude-sonnet-5-5' }); expect(env.status, env.stdout + env.stderr).toBe(0); expect(f.calls().filter(l => l.startsWith('modules ')).at(-1)).toBe(`modules install --full-root ${f.home}/.claude/skills`);