diff --git a/docs/capy-install.md b/docs/capy-install.md index 22a3481b0..6cc4f4f2d 100644 --- a/docs/capy-install.md +++ b/docs/capy-install.md @@ -467,6 +467,13 @@ make writable, or set GSTACK_STATE_ROOT to a writable directory (LAUNCH_FILE_UNWRITABLE)`, and a failing run prints no `GSTACK_LAUNCH_FILE` line and removes the file an earlier passing run left beside the verdict it rewrites (a profile check that keeps a fuller ok verdict leaves that verdict's file). +With `--model `, or `GSTACK_MODEL=` in its environment (what the Capy +skill passes), an ok run other than `--for review-voice` also prints `LOADOUT: …` +and `SKILL_ROOT: ` just before `GSTACK_LAUNCH`. For a loadout other than +`full`, `GSTACK_LAUNCH_FILE` then names `.loadout--.env`, +a copy of the verdict's launch file that adds `GSTACK_LOADOUT_SKILL_ROOT`; the +verdict and its own launch file do not change, and any failure prints +`LOADOUT_FALLBACK` and serves `full` ([loadouts](loadouts.md#capy)). `. ` at the start of a shell applies them without ever printing them, which is the only way to hand them to a child agent: pass the path, never the values. None of the assignments is a secret, but during GSTA-96's unattended diff --git a/docs/loadouts.md b/docs/loadouts.md index 1013f8280..b3ba8299e 100644 --- a/docs/loadouts.md +++ b/docs/loadouts.md @@ -23,9 +23,11 @@ bin/gstack-modules render --host claude --loadout full --out-dir ~/arms/control bin/gstack-modules render --host claude \ --modules 'full,-section:office-hours/second-opinion,-section:office-hours/visual-design' \ --out-dir ~/arms/oh-lean +bin/gstack-modules resolve --model claude-opus-5-5 # the loadout an install would serve, and why +bin/gstack-modules install --full-root "$HOME/.claude/skills" --model claude-opus-5-5 # publish it and print SKILL_ROOT ``` -`render` writes the whole host tree into a staging directory beside `--out-dir`. It checks that no rendered file still points at an excluded module, writes `loadout.lock.json` last (loadout name or `adhoc`, the normalized spec and its sha256, host, model, every excluded id, and the sha256 and byte count of every file), then swaps the result into place. A failure leaves an earlier render at `--out-dir` untouched. Claude section links name `--out-dir`, so point the eval harness at that directory. Pass the same `--model`, `--install-root` and `--plan-mode` the install under test uses, so the arms differ only by the modules. Codex renders default to the host's generic `gpt` overlay, while `./setup` uses `gpt-6-astra`. +`render` writes the whole host tree into a staging directory beside `--out-dir`. It checks that no rendered file still points at an excluded module, writes `loadout.lock.json` last (loadout name or `adhoc`, the normalized spec and its sha256, host, model, every excluded id, and the sha256 and byte count of every file), then swaps the result into place. A failure leaves an earlier render at `--out-dir` untouched. Claude section links name `--out-dir`, so point the eval harness at that directory. Pass the same `--model`, `--install-root` and `--plan-mode` the install under test uses, so the arms differ only by the modules. Codex renders default to the host's generic `gpt` overlay, while `./setup` uses `gpt-6-astra`. `--bind-model --full-root ` (both or neither, on a loadout that excludes something) bakes the start lines an install for that model serves ([below](#the-start-line-carries-the-model)). `bun run gen:skill-docs --loadout --out-dir ` and `--modules --out-dir ` apply the same filter to a generation run without the staging, dangling-reference check or lock file; a selection with exclusions and no `--out-dir` is refused with `MODULE_SPEC_INVALID`, because the committed tree is always the `full` render. A non-`full` render adds `` to each SKILL.md header. @@ -55,7 +57,7 @@ A model id is lowercased, its `provider/` prefix and a trailing `[…]` are drop The Capy skill passes the thread's model id in the environment: `GSTACK_MODEL= bash scripts/install.sh --check --for `. The variable, unlike `--model`, is safe on a checkout whose installer predates loadouts: that installer ignores it instead of refusing an unknown argument. The installer prints two lines before the launch lines: ``` -LOADOUT: lite model=claude-opus-5-5 source=model-flag digest=3f2a9c01d4e7 reused=yes +LOADOUT: lite model=claude-opus-5-5 source=GSTACK_MODEL digest=3f2a9c01d4e7 reused=yes SKILL_ROOT: /home/user/.gstack/loadouts/lite-3f2a9c01d4e7 ``` diff --git a/docs/troubleshooting.md b/docs/troubleshooting.md index 69101094e..11d3b1574 100644 --- a/docs/troubleshooting.md +++ b/docs/troubleshooting.md @@ -5527,7 +5527,7 @@ QM registration does not work yet. QM's skill-pack import clones the whole repos ## Module loadouts (gstack-modules) -These codes come from `bin/gstack-modules` and `gen-skill-docs --loadout/--modules` (guide: [loadouts.md](loadouts.md)). Each one exits 2 before anything is written, and none falls back to the `full` loadout: an eval arm that silently rendered `full` would measure the control. +These codes come from `bin/gstack-modules` and `gen-skill-docs --loadout/--modules` (guide: [loadouts.md](loadouts.md)). Each one exits 2 before anything is written, and none falls back to the `full` loadout: an eval arm that silently rendered `full` would measure the control. The exceptions are the install-time notices `LOADOUT_INVALID_MODEL`, `LOADOUT_MISMATCH` and `LOADOUT_FALLBACK` (from `bin/gstack-modules install`, the Capy installer and `gstack-skill-start`): an install never fails on them and serves `full` instead. ### `LOADOUTS_INVALID: modules/loadouts.json …`