Files
gstack/hosts/define-host.ts
T
ac20ef1e13 v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)
* fix(make-pdf,design): real TOC page numbers and anchors; design models move to gpt-5.5 + gpt-image-2 (#2903, #2807)

* ci: pin every action to a SHA, Scorecard, checksummed Bun, scoped Codex CLI in the CI image, macOS named-regressions job (#1948, #1706, #1997)

* fix(cso,browse): Windows/macOS lease identity, retention skips bad runs, truthful 'not assessed' reports, env.kv false positive, Windows browse spawn fixes (#2894, #2912, #2048, #2637, #2805)

* fix(outside-voice): one Codex model precedence for probe and dispatch, bounded timeouts with KILL escalation, probe cache identity, guarded mktemp, skills hidden in nested Codex (#2776, #2914, #2787, #2881, #2847)

* feat(setup): install registry, ./setup --status, staged activation, per-scope migrations, host tiers and conformance kit, OpenCode/Hermes fixes, Copilot CLI (experimental), disabled_skills, slimmer CLAUDE.md (#1925, #2879, #2347, #2338, #2626, #2629, #2825, #2015, #393, #1206, #2096)

Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com>
Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com>
Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>

* fix(preamble): skills start in worktree-isolated Claude Code sessions — one literal skill-start line, context-recovery helper, no eval in skill blocks, $N token tripwire, honest plan-mode precedence (#2763, #2896, #2851)

* fix(setup): per-install renders for renamed, vendored and custom-config installs, space-safe alias roots, per-host /cso launcher path (#1882, #2906)

* test: free tests never write the real HOME (home-write tripwire), no orphaned browse daemons, symlinked-TMPDIR (macOS) fixes, gbrain-on-PATH isolation (#2895, #2816, #2829, #2841, #2982, #2911, #2909, #2908, #2910)

* chore: integrate wave follow-ups — regenerate all hosts, README model docs, TODOS, touchfiles, duration seeds, Bun 1.3 telemetry test fix, replay fixtures pinned to their recorded bytes

* v1.91.14.0: release metadata

* test(browse): group-kill cleanup falls back to the leader when macOS returns EPERM for a live group

* ci: Codex login steps run under bash (the CI container's default sh rejects pipefail)

* fix: full-suite repairs — private state roots for 7 real-HOME writers, truthful home-guard attribution with --attribute-home, gstack-paths shim in ship-hook fixtures, Copilot in team-init probes, test-of-test detector, cookie review fixture pinned to the approved excerpt

* fix(windows): LF for Dockerfiles, normalized home-guard exclusions, path.relative fixture containment, ship push test spawn timeouts

* test(design-detect): widen the whole-scan budget test's timing margins so a loaded macOS runner can't time out the single-batch call

* fix(evals): qa protocol names defined for the judge, async PTY judge so overlapping sessions keep their cleanup deadline, bws setup cases use the standard JUDGE_MS tier

* test(pty): the non-blocking judge case is POSIX-only (its fake judge is a shebang script, like the PTY harness it covers)

* test(evals): ship-coverage-audit names absolute skill paths, uses Read, and skips the Step 7 artifact nothing consumes (removes the mechanism behind 3 of 4 historical timeouts)

* test: deflake terminal-agent concurrent startup (write the placeholder record before spawning, like the product) and qa-evidence resumed pipe (barrier on a full high-water mark instead of a sleep)

* fix(design): daemon log stream handles open errors instead of crashing the daemon; shutdown test awaits the stubbed exit

* test(evals): skillify checks the product's resolved state root (no GSTACK_HOME bypass), negative cases check every root; tpa shims live outside the agent's cwd and answer consistently

* test(evals): coverage-audit detector splits parallel columns at │ rails and [+] groups; coverage prompts name absolute skill paths; TODOs from the gate eval census

* fix(plan-eng-review): scope gate always sends the menu (no headless 'Scope pending' exit); PTY harness ends idle turn-ends and API-error panels promptly with a precise diagnostic

* test(evals): one position-bound coverage-read rule credits read-only && chains (labels, context ranges, git displays in either order) and still rejects forged output

* fix(ship): documentation section has one saved source inserted by cat (never retyped); spawned-marker evidence is the child output; refreshed codex/factory ship goldens

* test(docsync): the byte-exact insert positive is POSIX-only (the bash-command observer refuses backslash paths by design)

* test(evals): plan-design-with-ui focus-title rule accepts the comma-less 'dimensions or focus' wording (replayed on the captured CI run, negative controls kept)

* fix(qa-callers): exploratory preflight says the scope/method Reads come after exploratory.md; design-review scan check credits an executed scan proven by one engine run over the changed files

---------

Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com>
Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com>
Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>
2026-10-03 07:54:09 -07:00

184 lines
6.7 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:
* tier 'experimental' with conservative capabilities (tool execution and
* browser, prose questions, no plan mode, no delegation, advisory safety),
* paths derived from the host name (`.{name}/skills/gstack`), allowlist
* frontmatter (name + description), no metadata sidecar, all skills enabled,
* 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 the selected outside provider or spin up the review army). Suppressed
* on the non-Claude agent runtimes that already opt out (OpenClaw, Hermes,
* GBrain). Codex keeps the outside-provider resolvers and suppresses only army.
*/
export const CROSS_MODEL_RESOLVERS: string[] = [
'DESIGN_OUTSIDE_VOICES', // design.ts — selected outside provider
'ADVERSARIAL_STEP', // review.ts — adversarial outside review
'CODEX_SECOND_OPINION', // review.ts — legacy token, selected provider
'CODEX_PLAN_REVIEW', // review.ts — legacy token, selected provider
'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',
};
/**
* Prepend a one-paragraph tool-name glossary to the preamble's STATUS rules
* (spread into `toolRewrites`). For hosts whose native tools differ from the
* Claude names the shared prose uses; test/host-config.test.ts pins the anchor.
*/
export const PREAMBLE_GLOSSARY_ANCHOR = 'Read the echoed `KEY: value` STATUS lines';
export function preambleToolGlossary(glossary: string): Record<string, string> {
return { [PREAMBLE_GLOSSARY_ANCHOR]: `${glossary}\n\n${PREAMBLE_GLOSSARY_ANCHOR}` };
}
/**
* 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 $GSTACK_ROOT and
* an extra review rewrite; claude has none) replace the whole list via
* `pathRewrites` instead. The two are mutually exclusive.
*/
export interface HostOverrides<N extends string = string>
extends Partial<Omit<HostConfig, 'name' | 'displayName'>> {
name: N;
displayName: string;
/** Appended after the derived pathRewrite trio. Mutually exclusive with `pathRewrites`. */
extraPathRewrites?: PathRewrite[];
}
export function defineHost<const N extends string>(overrides: HostOverrides<N>): HostConfig & { name: N } {
const {
name,
displayName,
cliCommand = name,
cliAliases = [],
defaultModel = 'claude',
tier = 'experimental',
capabilities = {
toolExecution: true,
questions: 'prose',
planMode: false,
delegation: false,
browser: true,
safetyHooks: 'advisory',
},
globalRoot = `.${name}/skills/gstack`,
localSkillRoot = `.${name}/skills/gstack`,
hostSubdir = `.${name}`,
usesEnvVars = true, // false only for Claude (literal ~ paths, no $GSTACK_ROOT)
frontmatter = {
mode: 'allowlist',
keepFields: ['name', 'description'],
descriptionLimit: null,
},
generation = {
generateMetadata: false,
skipSkills: [],
},
pathRewrites,
extraPathRewrites,
toolRewrites,
suppressedResolvers = [...GBRAIN_RESOLVERS],
runtimeRoot = {
globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
globalFiles: {
'review': ['checklist.md', 'TODOS-format.md'],
},
},
install = {
linkingStrategy: 'symlink-generated',
},
coAuthorTrailer,
learningsMode = 'basic',
boundaryInstruction,
} = overrides;
if (pathRewrites && extraPathRewrites) {
throw new Error(
`[${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,
tier,
capabilities,
globalRoot,
localSkillRoot,
hostSubdir,
usesEnvVars,
frontmatter,
generation,
pathRewrites: resolvedPathRewrites,
...(toolRewrites !== undefined ? { toolRewrites } : {}),
suppressedResolvers,
runtimeRoot,
install,
...(coAuthorTrailer !== undefined ? { coAuthorTrailer } : {}),
learningsMode,
...(boundaryInstruction !== undefined ? { boundaryInstruction } : {}),
};
}