Files
gstack/hosts/define-host.ts
T
Garry TanandClaude Fable 5 60e51342b5 v1.67.2.0 feat: gpt-5.6-sol bounded-scope profile for Codex installs (#2633)
* feat: model taxonomy gains gpt-5.6-sol + per-host generation defaults

Adds 'gpt-5.6-sol' to the model taxonomy with exact-match-only resolution
(Terra/Luna/suffixed IDs deliberately fall back to generic gpt) and replaces
the hardcoded 'claude' generation default with a validated
HostConfig.defaultModel: codex renders the gpt profile when --model is
absent, every other host keeps claude. Codex ship golden regenerated
accordingly; ADDING_A_HOST documents the new field.

* feat: gpt-5.6-sol bounded-scope overlay + scope-aware resolvers

The Sol profile pins the explicit task as the lake: adjacent work is
report-only, investigation is bounded, runs terminate on one clean
verification pass, and the AskUserQuestion decision-brief format is never
trimmed. The overlay wrapper grants scope-interpretation precedence while
concrete workflow steps, gates, and skill-mandated re-verification loops
still win. Sol-specific Completeness Principle and first-run intro copy.
New SETUP_COMMAND resolver renders './setup --host <host>' for every
non-claude host so generated upgrade skills reinstall their own host.

* feat: setup reads the Codex model from config.toml

New resolve-codex-generation-model.ts reads the top-level model from
${CODEX_HOME:-~/.codex}/config.toml, validates against the model allowlist,
strips control characters from every config-derived string it surfaces,
guards against non-absolute config locations, and warns on Sol near-misses.
setup runs it on EVERY invocation (read-only TOML lookup) so a plain
./setup can never clobber a Sol user's rendered profile with the hardcoded
fallback; --model <id> overrides for one run and prints the persistence
hint. Kiro installs render the claude profile before copying (Kiro fronts
Claude-family models), rewrite the baked setup command to --host kiro, and
restore the resolved Codex profile after; the codex skills path honors
CODEX_HOME. Static pins cover the resolver wiring, fail-closed exit,
quoted argv, and the Kiro sandwich.

* feat: hermetic Codex runner hardening + Sol scope-termination E2E

The Codex E2E runner copies auth.json only (operator plugins, MCP servers,
rules, and skills no longer leak into hermetic evals), pins CODEX_HOME to
the temp dir, and supports per-run model, TOML overrides, and
--ignore-user-config. New periodic E2E installs the FULL generated
investigate skill on gpt-5.6-sol against a planted one-line bug with decoy
TODOs: the fix must land inside the boundary (untracked files counted via
git status --porcelain), decoys stay byte-identical, the regression oracle
survives unweakened, nothing gets committed, all within 30 tool calls.
The shared .agents tree is snapshotted and restored exactly in beforeAll;
fixture commits disable gpg signing. Wired into the periodic CI matrix,
paid-shard globs, eval scripts, touchfiles/E2E_TIERS
(codex-sol-scope-termination), and diff-based selection. Real-file
periodic-tier classification pins both codex E2Es out of the gate tier.
Free-tier test proves an explicit --model overrides the host default
through the real generation CLI.

* chore: bump version and changelog (v1.67.2.0)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: post-ship documentation sync for v1.67.2.0

- README: Codex skills path is CODEX_HOME-aware; state that
  --model overrides detection for one run only (persist via
  the Codex config.toml model key)
- CONTRIBUTING: add the model-overlay axis to the per-host
  config table (per-host defaultModel, override precedence)
- CLAUDE.md: eval results dir is ~/.gstack/projects/<slug>/evals/
  (legacy fallback ~/.gstack-dev/evals/), matching eval-store.ts
  and the eval:* CLI headers

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: post-ship documentation sync (v1.67.2.0)

Sol exact-match and near-miss warning documented in README; CODEX_HOME-aware
uninstall and troubleshooting paths; hermetic auth.json-only detail and the
build-clobber gotcha in CLAUDE.md; eval-store location corrected in
ARCHITECTURE.md; defaultModel row in the ADDING_A_HOST field reference;
resolver test count corrected in the CHANGELOG entry.

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-18 17:00:04 -07:00

161 lines
5.8 KiB
TypeScript

/**
* defineHost() factory — the single place the copy-paste across hosts/*.ts
* used to live.
*
* Every field a host doesn't override gets the common external-host default:
* paths derived from the host name (`.{name}/skills/gstack`), allowlist
* frontmatter (name + description), no metadata sidecar, skip the codex
* skill, the standard three-entry pathRewrite trio derived from the resolved
* paths, the shared runtimeRoot asset list, and symlink-generated install.
*
* Defaults are constructed fresh per call, so no two host configs ever share
* a mutable array/object. Optional fields that are absent today (toolRewrites,
* coAuthorTrailer, boundaryInstruction) stay absent unless a host explicitly
* sets them — the factory never default-populates optional fields.
*/
import type { HostConfig } from '../scripts/host-config';
type PathRewrite = { from: string; to: string };
/**
* Preamble resolvers that orchestrate cross-model second opinions (they shell
* out to Codex or spin up the review army). Suppressed on hosts that can't or
* shouldn't invoke other models — Codex itself (can't invoke itself) and the
* non-Claude agent runtimes (OpenClaw, Hermes, GBrain).
*/
export const CROSS_MODEL_RESOLVERS: string[] = [
'DESIGN_OUTSIDE_VOICES', // design.ts — invokes Codex for outside voices
'ADVERSARIAL_STEP', // review.ts — invokes Codex adversarially
'CODEX_SECOND_OPINION', // review.ts — invokes Codex
'CODEX_PLAN_REVIEW', // review.ts — invokes Codex
'REVIEW_ARMY', // review-army.ts — multi-model orchestration
];
/**
* Brain-aware resolvers. Suppressed by default on every host — only hosts
* that can run with a GBrain (hermes, gbrain) leave these active.
*/
export const GBRAIN_RESOLVERS: string[] = [
'GBRAIN_CONTEXT_LOAD',
'GBRAIN_SAVE_RESULTS',
];
/**
* Tool-name rewrites for OpenClaw-style agent runtimes (lowercase exec /
* read / write / edit tools, sessions_spawn for subagents). OpenClaw and
* GBrain share these byte-for-byte; spread into `toolRewrites` at the use
* site so each config owns its own copy.
*/
export const EXEC_STYLE_TOOL_REWRITES: Record<string, string> = {
'use the Bash tool': 'use the exec tool',
'use the Write tool': 'use the write tool',
'use the Read tool': 'use the read tool',
'use the Edit tool': 'use the edit tool',
'use the Agent tool': 'use sessions_spawn',
'use the Grep tool': 'search for',
'use the Glob tool': 'find files matching',
'the Bash tool': 'the exec tool',
'the Read tool': 'the read tool',
'the Write tool': 'the write tool',
'the Edit tool': 'the edit tool',
};
/**
* Host definition input: name + displayName are required, everything else is
* an override on the common external-host defaults documented above.
*
* `extraPathRewrites` appends to the derived standard trio
* (`~/.claude/skills/gstack` → `~/{globalRoot}`, `.claude/skills/gstack` →
* localSkillRoot, `.claude/skills` → `{hostSubdir}/skills`). Hosts whose
* rewrites aren't mechanically derivable (codex, factory use $GSTACK_ROOT and
* an extra review rewrite; claude has none) replace the whole list via
* `pathRewrites` instead. The two are mutually exclusive.
*/
export interface HostOverrides<N extends string = string>
extends Partial<Omit<HostConfig, 'name' | 'displayName'>> {
name: N;
displayName: string;
/** Appended after the derived pathRewrite trio. Mutually exclusive with `pathRewrites`. */
extraPathRewrites?: PathRewrite[];
}
export function defineHost<const N extends string>(overrides: HostOverrides<N>): HostConfig & { name: N } {
const {
name,
displayName,
cliCommand = name,
cliAliases = [],
defaultModel = 'claude',
globalRoot = `.${name}/skills/gstack`,
localSkillRoot = `.${name}/skills/gstack`,
hostSubdir = `.${name}`,
usesEnvVars = true, // false only for Claude (literal ~ paths, no $GSTACK_ROOT)
frontmatter = {
mode: 'allowlist',
keepFields: ['name', 'description'],
descriptionLimit: null,
},
generation = {
generateMetadata: false,
skipSkills: ['codex'], // Codex skill is a Claude wrapper around codex exec
},
pathRewrites,
extraPathRewrites,
toolRewrites,
suppressedResolvers = [...GBRAIN_RESOLVERS],
runtimeRoot = {
globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
globalFiles: {
'review': ['checklist.md', 'TODOS-format.md'],
},
},
install = {
linkingStrategy: 'symlink-generated',
},
coAuthorTrailer,
learningsMode = 'basic',
boundaryInstruction,
} = overrides;
if (pathRewrites && extraPathRewrites) {
throw new Error(
`[${name}] pathRewrites and extraPathRewrites are mutually exclusive: ` +
`pathRewrites replaces the derived trio, extraPathRewrites appends to it`
);
}
const resolvedPathRewrites: PathRewrite[] = pathRewrites ?? [
{ from: '~/.claude/skills/gstack', to: `~/${globalRoot}` },
{ from: '.claude/skills/gstack', to: localSkillRoot },
{ from: '.claude/skills', to: `${hostSubdir}/skills` },
...(extraPathRewrites ?? []),
];
// Field order below mirrors the HostConfig interface (and the original
// hand-written configs) so serialized output is stable. Optional fields are
// conditionally spread so absent overrides stay truly absent (no
// `key: undefined` entries).
return {
name,
displayName,
cliCommand,
cliAliases,
defaultModel,
globalRoot,
localSkillRoot,
hostSubdir,
usesEnvVars,
frontmatter,
generation,
pathRewrites: resolvedPathRewrites,
...(toolRewrites !== undefined ? { toolRewrites } : {}),
suppressedResolvers,
runtimeRoot,
install,
...(coAuthorTrailer !== undefined ? { coAuthorTrailer } : {}),
learningsMode,
...(boundaryInstruction !== undefined ? { boundaryInstruction } : {}),
};
}