* test(#3897): failing-first coverage for §8.3 rungs 2-4 ADR-3473 §8.3 has four rungs; #3883/PR #3896 shipped the first. This pins the other three RED before any fix. Rung 2 — the install marker has four readers and resolveRuntime is not one. resolveRuntime resolves GSD_RUNTIME > config.runtime > 'claude' and reads no marker at all, while bin/install.js writes one (#2297) and FOUR hand-rolled readInstallRuntimeMarker copies exist: src/model-resolver.cts:65 (cached, with test seams), hooks/gsd-agent-isolation-guard.js:112, and TWICE in hooks/gsd-cursor-subagent-start.js at :346 and :355. Four copies of one rule. Fixtures and seam names mined from PR #3382 rather than re-derived; it implemented this rung and was closed "not on the merits". Rung 3 — the sandbox map, and the fallback that was the real defect. Measured across all 35 files in agents/, deriving workspace-write iff tools: declares Write or Edit: - all 11 CODEX_AGENT_SANDBOX entries derive to their mapped value exactly, zero disagreements — the map carries nothing the contract does not - 24 roles fall through `|| 'read-only'`, of which 16 declare Write or Edit So the map is redundant and the silent fallback is the defect. The maintainer chose to derive but hold those 16 at read-only pending the question of whether Codex enforces sandbox_mode or merely advises; HALT.md records it. T20 asserts the emitted sandbox_mode PER ROLE against a captured baseline, not in aggregate — an aggregate passes while one role silently widens, which is the proxy-instead-of-identity shape this repo names. T24 and T25 fail on a stale hold, so the hold list cannot rot into the subset map being deleted. Rung 4 — shortFormToId, recovered rather than invented. I nearly reported this as another wrong §8.3 claim: `git log -S shortFormToId` returns only documentation commits. That was the wrong instrument. Direct inspection of sdk/src/query/phase.ts at 11918dcc3^ shows five occurrences, and the tests match that code rather than a guess at its semantics — including first-write-wins on a duplicate short form. T43 asserts at the consumer's output: the emitted `waves` map from the real CLI, which pre-fix collapses to {"1":[...]} because every short-form edge is dropped. A unit assertion on resolveDependencyId would have passed throughout this defect's life. Observed RED, this tree: rung 2 11/11 fail — no marker rung, no seams rung 3 T23,T24,T25,T26,T30 fail; T28 fails (validate agents passes a TOML whose sandbox_mode disagrees — it checks presence only) rung 4 T42,T44 fail; T43,T49 fail with waves collapsed to a single wave 1 Green and staying green: T20/T21/T22/T27 as captured baselines, #3885's unresolvable-token warning and wave-verdict suppression, and #3785's display-mapping passthrough. If the third tier over-reaches, those go red — that is their job. Disclosed weakness: T45 (a canonical id with no dash is not short-form indexed) cannot be isolated behaviorally, because planMap always masks it. It is a non-crash boundary pin, weaker than the other rows, and is recorded as such rather than presented as equivalent. Design: .gsd/phase/feat-3897-adr3473-83-rungs/40-design.md Test matrix: .gsd/phase/feat-3897-adr3473-83-rungs/50-test-matrix.md Decision: .gsd/phase/feat-3897-adr3473-83-rungs/HALT.md Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * enhance(#3897): §8.3 rungs 2-4 — one marker reader, a derived sandbox, the third depends_on tier ADR-3473 §8.3 has four rungs. #3883/PR #3896 shipped the first. These are the other three. Rung 2 — the install marker had four readers, and resolveRuntime was not one. resolveRuntime resolved GSD_RUNTIME > config.runtime > 'claude' and read no marker, while bin/install.js writes one (#2297) and four hand-rolled readInstallRuntimeMarker copies existed: src/model-resolver.cts (cached, with seams), hooks/gsd-agent-isolation-guard.js, and twice in hooks/gsd-cursor-subagent-start.js. model-resolver's was already the house idiom, so it was promoted rather than replaced: src/runtime-slash.cts now owns it, and model-resolver plus both hooks delegate. The hooks reach it through ensureRuntimeBuild(), the seam lint-hooks-runtime-build-seam enforces. No import cycle existed - checked both directions before moving anything. The marker is the THIRD rung: env > project config > marker > 'claude'. N1 was checked rather than assumed, and my first reading of it was wrong. A marker holding an unknown name comes back essentially verbatim, which looked like a validation gap. Measured against the env rung with the same inputs - including "../../etc/passwd" and "claude;rm -rf /" - the two are identical, because they share resolveRuntimeNameFromCandidates. N1 asks for exactly that, and it is met. The residual (the shared normalizer normalizes shape, it does not validate against the known-runtime set) is pre-existing on the env rung and plausibly deliberate, since a new runtime should not need a code change. The marker also does not widen the trust boundary in any real sense: it lives inside the install tree beside the code, so anyone who can write it can write runtime-slash.cjs itself. Rung 3 — the map was redundant; the silent fallback was the defect. Measured across all 35 files in agents/, deriving workspace-write iff tools: declares Write or Edit: all 11 CODEX_AGENT_SANDBOX entries derive to their mapped value exactly, zero disagreements. The map carried nothing the contract did not already have, so it is DELETED rather than reconciled. What was actually broken is `|| 'read-only'`, which silently under-granted 24 of 35 roles. 16 of those 24 declare Write or Edit and would widen under derivation. Per the maintainer's decision (HALT.md), they are held at read-only pending the question of whether Codex enforces sandbox_mode or merely advises. Emitted TOML is therefore byte-identical for all 35 roles - asserted per role, not in aggregate, because an aggregate passes while one role silently widens. The hold list self-invalidates. A hold whose role no longer derives broader fails, and so does a hold naming a role with no agents/<name>.md. Without that it would rot into exactly the hand-maintained subset map being deleted, and this commit's own ledger claim would become false over time. Both cases were proved by injecting them and watching them throw. Two committed tests asserted the deleted map's existence and contents. They were pinning the thing being removed, so the tests moved rather than the production code: the 11 role-value pairs survive as a test-local PRE_3897_CODEX_AGENT_SANDBOX baseline, and the assertions now drive the real derivation against real agents/*.md. The coverage is preserved; only its source moved out of production code. validate agents gains checkCodexSandboxPosture, mirroring the existing checkCodexModelPosture: each installed TOML's sandbox_mode must equal the role's expected value, failing with role, expected and found. It previously checked file presence and manifest completeness only, so a TOML whose sandbox_mode disagreed passed. Rung 4 — shortFormToId, recovered rather than invented. I nearly reported this as another wrong §8.3 claim: git log -S returns only documentation commits. Wrong instrument. sdk/src/query/phase.ts at 11918dcc3^ carries five occurrences, and the implementation here matches that code rather than a guess at its semantics - including first-write-wins on a duplicate short form, deterministic from the sorted plan order. It resolves the bare plan number: depends_on: ["01"] now reaches 26-01-auth-hardening. That is a control-flow change, not a diagnostic one - plans that silently collapsed into a single wave 1 now execute in their declared waves, and execute-phase.md consumes those wave values. In-phase only, by construction: the map is built from this phase's rawPlans, so a same-named short form in another phase does not resolve. #3785's display-mapping passthrough and #3885's unresolvable-token warning and wave-verdict suppression are untouched and stay green. If the third tier had over-reached, those are what would have caught it. Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(#3897): close a fail-open I introduced, and wire the posture check to its command Two blockers from review. Both are mine, and one is a security regression my own change created. 1. A held role could escape its hold by editing its own frontmatter. The Codex install loop set the sandbox identity from the agent's frontmatter `name:` field rather than from its filename, so the hold lookup keyed off a value the file itself declares: deriveCodexSandboxMode('gsd-doc-writer', <real file>) -> read-only deriveCodexSandboxMode('gsd-doc-writer-x', <same file, name: edited>) -> workspace-write deriveCodexSandboxMode('GSD-Doc-Writer', <same file, name: recased>) -> workspace-write What makes this a blocker rather than a nit is the DIRECTION. The deleted CODEX_AGENT_SANDBOX map had the identical lookup-key quirk, but it was an allowlist: an unmatched key fell back to read-only, which is safe. The new scheme derives workspace-write from the tool contract and uses the hold as a subtraction, so the same mismatch fails OPEN. I converted a fail-closed quirk into a fail-open one and did not notice; the isolated reviewer proved it by execution. Neither safety net caught it. validateCodexSandboxHolds only checks that <key>.md exists, never that a file's derived identity matches its key. checkCodexSandboxPosture looks the canonical source up by the installed TOML's filename, finds nothing for a renamed agent, and treats it as a custom non-roster agent — silently no violation. The identity is now the FILENAME STEM, which is what validateCodexSandboxHolds already validates and what an attacker editing frontmatter cannot change without renaming the file — at which point the existing validator catches it. The lookup is case-insensitive so a recase does not slip past either. The frontmatter name still drives the TOML body and filename, unchanged; only the sandbox identity moved. All 35 roster files were checked: name matches filename stem everywhere, so a stricter "they must agree or throw" invariant would have been safe against real content. It is deliberately NOT added — it would abort an install on a tampered file where emitting a correctly-derived read-only TOML is the safer outcome. Recorded as a fork rather than decided silently. 2. checkCodexSandboxPosture was exported and never called. cmdValidateAgents (src/verify.cts) called checkAgentsInstalled and checkCodexModelPosture only; grep for the sandbox check in that file returned nothing. So criterion 3 — "validate agents fails on semantic drift, not only on missing files" — was unmet, and `validate agents` behaved exactly as before. That is ADR-3473 Decision 2's named shape: a declared policy with no executor. It also meant the T28 test asserted at the helper's return value while the COMMAND stayed broken — the ADR-3180 Decision 4(b) failure this epic exists to close, committed by me while enforcing it elsewhere in the same epic. Now wired as an additive `sandbox_posture` field beside `codex_posture`, following the sibling precedent exactly. Drift is report-only, not a non-zero exit, because that is what checkCodexModelPosture does — two sibling posture checks disagreeing about whether a violation is fatal would be its own defect. The choice is recorded in a comment rather than left implicit. A consumer-output test now drives the real CLI and asserts on the emitted JSON, and was shown failing before the wiring and passing after. Also corrected a stale artifact: the design's Known limit L1 still claimed rung 3 was not in this deliverable, written while it was halted and false once the maintainer unblocked it. Verified after both fixes: the three bypass probes all return read-only, the per-role table is 35/35 byte-identical, and both hold self-invalidation cases still throw. Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * docs(#3897): the marker rung, the derived sandbox, and the bare plan-number depends_on Reference: the runtime precedence ladder in docs/CLI-TOOLS.md gains the install marker rung; docs/COMMANDS.md documents validate agents' new sandbox_posture field; docs/reference/plan-md.md documents that depends_on accepts the bare plan number. Explanation: a docs/features fragment keyed id 3897, so it cannot collide with a concurrent PR hand-allocating a section number, regenerated into FEATURES.md. ADR-3473 §8.3 gains an ANSWER blockquote in the document's own correction style, recording what was measured and built against the section's 2026-08-26 correction - including the qualification that checkAgentsInstalled itself still checks presence only, and the semantic assertion lives in a sibling wired into validate agents rather than folded into it. No how-to. Both user-visible changes are zero-step: a non-Claude install resolving its own runtime, and plans executing in their declared waves, both happen without the user doing anything. docs/how-to/control-the-reported-host-runtime.md covers a DIFFERENT ladder (resolveReportedRuntime / agent_runtime) that this change does not touch, and was deliberately left alone rather than edited by association. No tutorial - nothing multi-step to walk through. docs/AGENTS.md unchanged: it documents Claude-side tools frontmatter, never Codex sandbox_mode, and the emitted tools contract did not change. The prompt layer documents depends_on only by example, not by schema, so nothing there needed editing - and few-shot-examples/plan-checker.md already showed depends_on: ['01'], which now actually resolves. Translated copies of plan-md.md are untouched; the project treats translations as community-maintained. Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(#3897): move the sandbox derivation out of the installer, off the install path, and off a third parser The full suite came back with 26 failures across four files. Three distinct causes, mapped individually rather than assuming the first explained the rest. A. Requiring bin/install.js printed the GSD banner to stdout and corrupted `validate agents` JSON. Unexpected token '', "[36m ██"... is not valid JSON checkCodexSandboxPosture reached deriveCodexSandboxMode by lazily requiring bin/install.js, whose module load prints the ASCII banner. So the command emitted banner bytes before its JSON and every JSON consumer broke, including ten tests that predate this branch. src/ reaching into bin/ was backwards layering that happened to also be loud. The derivation now lives in src/codex-agent-toml.cts - the existing Codex TOML domain module, no new module and no six-gate ripple - and both bin/install.js and src/agent-install-check.cts import it. One owner, which is §8.3's rule applied to the fix for §8.3. B. The stale-hold throw fired on a legitimate partial source dir, and masked a security assertion. validateCodexSandboxHolds treated "this hold's .md is absent from the install SOURCE dir" as a stale hold and threw. A test fixture, or any partial install source, legitimately contains a couple of agents. Worse, it threw BEFORE the path-escape check, so a test asserting that a `../../evil` frontmatter name is rejected got my unrelated error instead of the traversal rejection it was written for. A fail-closed check of mine was hiding a real security check. The "no stale holds, shrink-only" invariant is a property of the repo's canonical agents/ roster, not of whatever directory an install happens to read. It is off the runtime path and enforced where it belongs, in the tests that already existed for it. A partial source dir now installs cleanly, and the evil-name case throws with its own escapes-configHome message again. C. T8 depended on ambient process.env state. The marker/env parity assertion round-tripped through live process.env. It now compares against resolveExplicitRuntime's already-exported dependency-injection parameter - deterministic and hermetic, same claim. Proven still falsifiable rather than assumed: with the marker rung's normalization temporarily bypassed the two rungs diverge ("codex\n../../etc/passwd" vs "codex-../../etc/passwd") and the assertion fails, then passes again once reverted. One correction folded in along the way. The first version of the move added private _extractFrontmatterAndBody/_extractFrontmatterField helpers to codex-agent-toml.cts - a THIRD copy of frontmatter extraction, where the graph already shows two (bin/install.js:2348, runtime-artifact-conversion.cts:893). Adding a third inside the epic whose thesis is one implementation per rule is not defensible. deriveCodexSandboxMode no longer parses anything: it takes (identity, toolsValue) and each caller supplies the tools value using the extractor it already has. Both helpers are deleted. The identity argument is still the filename stem, so the fail-open fix is untouched. Verified after all three: `validate agents --raw` emits parseable JSON with no banner and both posture fields; the four hold-bypass probes still return read-only; the per-role table is 35/35 byte-identical at 26 read-only / 9 workspace-write; the hold list is still 16. Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(#3897): drop a dev-only transitive dep, make the derivation total, retire a stale fallback test Suite down to 7 failures from 26. Three more causes, mapped individually. A. My extractor import dragged in a script that does not exist in an installed tree. Cannot find module '../../../scripts/fix-slash-commands.cjs' Chain: src/agent-install-check.cts imported runtime-artifact-conversion.cjs, which requires command-roster.cjs, whose line 36 requires ../../../scripts/fix-slash-commands.cjs. That path exists in the repo and not in an install, so every test exercising a synthetic install dir died at module load. I picked that extractor for convenience without checking what it pulls in - the same mistake that produced the banner bug, one layer further out. agent-install-check now uses a single-purpose extractToolsLine on codex-agent-toml.cts. That is deliberately NOT a general frontmatter parser: we deleted those helpers a commit ago for good reason, and this reads one line. Verified from outside the repo root that requiring either module prints nothing and does not throw. B. A test pinned the deleted name-based fallback. 'defaults unknown agents to read-only' called generateCodexAgentToml with a fixture declaring tools: Read, Write, Edit. Under derivation an unknown agent with a writing contract correctly derives workspace-write - design row S6, a new writing role gets the contract, not the pin. The behavior it asserted was the silent fallback this rung deleted; identity no longer decides the sandbox. Replaced with two rows rather than a flipped string: no tools declared -> read-only (absence is not a grant), and Write/Edit declared -> workspace-write. Strictly more coverage than the row it replaces. C. The stale-hold check still threw per derivation call. Last commit took the roster-existence check off the install path, but deriveCodexSandboxMode itself still threw when a hold's role did not derive broader FOR THE CONTENT IT WAS HANDED - so it fired on any synthetic fixture for a held role. The throw is gone, and it cost nothing: if a held role's content does not derive broader, the hold pins read-only and derivation returns read-only anyway, so the hold is a no-op and there is nothing to fail about. The staleness invariant is a property of the real agents/ roster, and validateCodexSandboxHolds still enforces it there - confirmed against the real roster after the change, not assumed. deriveCodexSandboxMode is now total: every (identity, toolsValue) including undefined and null returns read-only or workspace-write, never throws. Verified: validate agents emits parseable JSON; the four hold-bypass probes return read-only; the per-role table is 35/35 at 26 read-only / 9 workspace-write. Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * docs(#3897): put the rung-3 decision in the shipped docs instead of pointing at an ignored path The ADR entry and the feature fragment both ended their rung-3 explanation with "see .gsd/phase/feat-3897-adr3473-83-rungs/45-decision-rung3-sandbox.md". That directory is gitignored (.gitignore:55), so the rationale for holding 16 roles at read-only was reachable only from the machine that produced it. A reader of the ADR got a pointer to nothing. Both now carry the reasoning inline: the criterion asks both that the sandbox derive from the declared tool contract and that no role gain a broader sandbox, and those cannot both hold, because a faithful derivation widens 16 roles the deleted map never listed and that fell through its silent read-only default. The resolution is derive-and-hold - the derivation owns the rule now, each hold is released as its enforcement question is answered, and a hold is reversible where a widened sandbox that turns out to be enforced is not. Checked before assuming this was a defect class: CONTEXT.md cites .gsd/phase/<slug>/40-design.md as its standard Design: provenance line in eight module entries, and four other shipped docs do the same. Citing a phase artifact is an established convention here, so those are left alone. What was wrong was specific to these two: they put load-bearing rationale behind the pointer instead of provenance. docs/FEATURES.md regenerated from the fragment via scripts/gen-features.cjs rather than hand-edited. Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * fix(#3897): close a fail-open, stop a silent mis-resolution, and read a declaration as a declaration Two orthogonal reviews on the shipped sha. Three of the findings are the same failure class this epic exists to close, committed inside it. 1. BLOCKER - the sandbox was decided for one identity and applied to another. bin/install.js derived sandbox_mode for the filename stem and then wrote the result to `${name}.toml`, where name comes from the file's own frontmatter. Make the two disagree and a HELD role's artifact goes wide: rename gsd-doc-writer.md -> gsd-doc-writer-v2.md, keep name: gsd-doc-writer -> stem is unheld, derives workspace-write, lands on gsd-doc-writer.toml add any gsd-*.md whose frontmatter name: is a held role -> clobbers that role's toml with workspace-write Both emit read-only on origin/next, because the deleted map was an allowlist and a miss fell back safe. This is a regression my change introduced. The previous review round moved the HOLD KEY off frontmatter to the filename stem and left the OUTPUT PATH on frontmatter; my own comment at install.js:6985 calls that value attacker-editable, four lines above the line that uses it as the filename. The decision is now made over BOTH candidate identities, most-restrictive wins: if either the stem or the emitted name is held, the mode is read-only. 2. MAJOR - hold matching was toLowerCase() only, so confusables escaped. Turkish dotted/dotless i, fullwidth, NFD, trailing space/NBSP/dot/newline, ./ and ../agents/ all slipped the hold and emitted workspace-write. Identities are now basenamed, trimmed of NBSP/zero-width/control characters, NFKC-normalized and lowercased - and anything still carrying a character outside [a-z0-9._-] is treated as suspicious and derives read-only. We do not enumerate confusables; every shipped roster file is ASCII, so refusing to widen on an identity we cannot recognize is fail-closed with no false positives on real content. 3. MAJOR - the short-form depends_on tier mis-resolved SILENTLY. shortFormToId keyed on the last dash-segment of any canonical id with no constraint that it is a plan number, so a phase holding 09-FIX-auth-PLAN.md made depends_on: ["auth"] bind at wave 2 with zero warnings. This is the worst shape in the epic: the unresolvable-token warning fires on a DROPPED token, so a MIS-RESOLVED one is invisible and the tool reports a confident wave assignment built from a wrong edge. A wrong edge is worse than a missing one. The segment must now match /^\d+$/, which is exactly the contract docs/reference/plan-md.md already documents. This tier was recovered verbatim from the retired SDK lineage, which carried the same defect; we are deliberately NOT preserving it bug-for-bug, and the comment says so, so the next reader does not "restore" it. 4. MAJOR - the derivation was reading a declaration as an absence. extractToolsLine read one line, so a YAML list-form tools: block returned only its first item. Two roster files use list form, and gsd-nyquist-auditor declares Write and Edit there - parsed as "- Read", found no write tool, and emitted read-only. Rung 3's headline claim is that sandbox_mode derives from the declared tool contract; that claim was false for 2 of 35 roles and materially wrong for 1. Reading a declaration as an absence is the silent-drop class this epic exists to close. Renamed extractToolsValue and taught it both shapes. gsd-nyquist-auditor now derives workspace-write and joins CODEX_SANDBOX_HOLDS as its 17th entry, per the standing derive-and-hold decision - so emitted TOML stays byte-identical at 26 read-only / 9 workspace-write while the hold list finally records every role that would widen. A previous pass declined this fix because it moved the count; that inverts the priority. Byte-identity is preserved THROUGH the hold, not by leaving a parser broken. Divergence check, because this is where that bug hides: both paths feeding sandbox derivation - install.js's emitter and checkCodexSandboxPosture - now route through the one extractor. The tools readers in runtime-artifact-conversion and install.js's other frontmatter call sites serve Claude-side emission and do not feed sandbox derivation. Also fixed, each real: the posture check's `found` used a naive whole-file regex where its own sibling uses the block-aware scanner, so prose inside developer_instructions produced a false violation; `found` skipped truncatePostureValue and leaked a 300-char value into validate agents output; deriveCodexSandboxMode's absolute never-throws claim was false for an object with a throwing toString; T49 could not falsify cross-phase leakage (its target phase had its own 01, so a globally-scoped map passed too); T20/N6 iterated a hardcoded table and pinned the FIXTURE size, so a 36th agent would be silently unchecked; three tests reimplemented the code they were testing instead of importing it; and T2-T4 deleted GSD_RUNTIME without restoring it. Verified: hold list 17, gsd-nyquist-auditor derives workspace-write unheld and emits read-only held, roster 35/35 at 26/9, depends_on ["auth"] no longer resolves while ["01"] still does, both identity-bypass cases and every confusable vector emit read-only. Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * docs(#3897): the hold list is 17, and the reason the 17th was missing The count read 16 because the derivation could not read the declaration it claimed to derive from: the tools reader was single-line, so a YAML list-form tools: block returned only its first item and gsd-nyquist-auditor's declared Write and Edit were read as an absence. Both the ADR entry and the feature fragment now carry the corrected count and the reason for it, rather than a silently updated number. Deriving from a declaration you cannot parse is not deriving, and a flattering count is worse than a wrong one because it looks settled. docs/FEATURES.md regenerated from the fragment. Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * chore(#3897): backfill changeset pr number Refs #3897 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> --------- Co-authored-by: sim <sim@local> Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
611 lines
26 KiB
TypeScript
611 lines
26 KiB
TypeScript
/**
|
|
* Agent Install Check — moved from core.cts (ADR-857 T0 #1268 phase rehome-core-squatters).
|
|
*
|
|
* Owns:
|
|
* - getAgentsDir(runtime?, projectRoot?): string
|
|
* - checkAgentsInstalled(runtime?, projectRoot?): AgentsInstalledResult
|
|
*
|
|
* The core.cjs re-export spine was retired in epic #1267; callers import
|
|
* these symbols from agent-install-check.cjs directly.
|
|
*/
|
|
|
|
import fs from 'node:fs';
|
|
import path from 'node:path';
|
|
// eslint-disable-next-line @typescript-eslint/no-require-imports
|
|
import modelProfiles = require('./model-profiles.cjs');
|
|
const { MODEL_PROFILES } = modelProfiles;
|
|
import { getGlobalConfigDir } from './runtime-homes.cjs';
|
|
import { getDirName, NO_LOCAL_CONFIG_DIR_SENTINEL } from './runtime-name-policy.cjs';
|
|
// #3242 — model-catalog is a genuine leaf (only node:path + its own JSON), which is
|
|
// exactly why Phase 1 (#3241) moved isAnthropicFlavoredModel there: this module can
|
|
// consume it without dragging model-resolver's config-loader chain into a
|
|
// pure read/verify surface.
|
|
import { isAnthropicFlavoredModel } from './model-catalog.cjs';
|
|
// #3243 — the Codex `.toml` block-range/BOM/scan primitives moved into the typed
|
|
// IR module (Phase 3), which this reader now imports rather than defining
|
|
// locally. Behavior is unchanged: scanTomlLines/stripBOM here are the exact
|
|
// same lenient functions that used to live in this file — see
|
|
// codex-agent-toml.cts's module header for the reader/writer reconciliation.
|
|
// #3897 CAUSE A fix: `deriveCodexSandboxMode` needs the resolved `tools:`
|
|
// frontmatter VALUE, not raw content — this module used to reach that via
|
|
// `runtime-artifact-conversion.cjs`'s general-purpose
|
|
// `extractFrontmatterAndBody`/`extractFrontmatterField`, but that module's
|
|
// dependency chain (`command-roster.cjs` -> `scripts/fix-slash-commands.cjs`,
|
|
// a dev-only repo script) does not resolve from an installed tree — any test
|
|
// exercising a synthetic install dir blew up at module load. `codex-agent-toml.cjs`
|
|
// is already imported here, is a genuine leaf (node builtins only, zero
|
|
// side effects), and now exports `extractToolsValue` — a single-purpose
|
|
// `tools:`-VALUE reader (inline AND YAML block-list form, #3897 list-form
|
|
// parse fix), not a general frontmatter parser — for exactly this caller,
|
|
// shared with `bin/install.js`'s emitter so the two sandbox-feeding paths
|
|
// can never silently disagree, and no fourth copy of frontmatter parsing is
|
|
// added.
|
|
import { stripBOM, scanTomlLines, deriveCodexSandboxMode, extractToolsValue } from './codex-agent-toml.cjs';
|
|
|
|
interface AgentsInstalledResult {
|
|
agents_installed: boolean;
|
|
missing_agents: string[];
|
|
installed_agents: string[];
|
|
incomplete_agents: string[];
|
|
agents_dir: string;
|
|
agent_runtime: string;
|
|
}
|
|
|
|
/**
|
|
* Frozen reason enum for {@link checkCodexModelPosture}. Per CONTRIBUTING's
|
|
* typed-IR rule ("Error / status / reason → a frozen enum"): callers and tests
|
|
* assert on these wire values, never on prose. Adding a member is a deliberate
|
|
* three-way coordinated change — enum, emitting site, and the enum-lock test.
|
|
*/
|
|
const POSTURE_REASON = Object.freeze({
|
|
ANTHROPIC_FLAVORED_MODEL: 'anthropic_flavored_model',
|
|
ORPHANED_REASONING_EFFORT: 'orphaned_reasoning_effort',
|
|
UNREADABLE: 'unreadable',
|
|
NOT_CODEX: 'not_codex',
|
|
AGENTS_DIR_MISSING: 'agents_dir_missing',
|
|
});
|
|
|
|
type PostureReason = (typeof POSTURE_REASON)[keyof typeof POSTURE_REASON];
|
|
|
|
interface PostureViolation {
|
|
agent: string;
|
|
file: string;
|
|
reason: PostureReason;
|
|
value?: string;
|
|
}
|
|
|
|
interface CodexModelPostureResult {
|
|
ok: boolean;
|
|
violations: PostureViolation[];
|
|
checked: string[];
|
|
agents_dir: string;
|
|
agent_runtime: string;
|
|
reason?: PostureReason;
|
|
}
|
|
|
|
/**
|
|
* #3897 rung 3 (ADR-3473 §8.3, HALT.md option 2) — a violation entry for
|
|
* {@link checkCodexSandboxPosture}. Distinct shape from {@link PostureViolation}:
|
|
* this check reports a drift between an EXPECTED and a FOUND `sandbox_mode`,
|
|
* not a single offending value. `reason` is populated only for the UNREADABLE
|
|
* case (mirrors {@link checkCodexModelPosture}); a drift violation carries
|
|
* `expected`/`found` instead.
|
|
*/
|
|
interface SandboxPostureViolation {
|
|
agent: string;
|
|
file: string;
|
|
reason?: PostureReason;
|
|
expected?: string;
|
|
found?: string;
|
|
}
|
|
|
|
interface CodexSandboxPostureResult {
|
|
ok: boolean;
|
|
violations: SandboxPostureViolation[];
|
|
checked: string[];
|
|
agents_dir: string;
|
|
agent_runtime: string;
|
|
reason?: PostureReason;
|
|
}
|
|
|
|
// Matches the value-truncation convention in bin/install.js's
|
|
// _warnCodexModelOverrideDropped: values over 64 chars are capped so an
|
|
// oversized or secret-shaped config value can never reach a report in full.
|
|
function truncatePostureValue(value: string): string {
|
|
return value.length > 64 ? `${value.slice(0, 64)}…` : value;
|
|
}
|
|
|
|
/**
|
|
* Resolve the agents directory for the given runtime.
|
|
*
|
|
* Priority:
|
|
* 1. GSD_AGENTS_DIR env var (explicit override, any runtime)
|
|
* 2. For claude runtime: __dirname-relative path (agents/ sibling of
|
|
* gsd-core/) — correct for repo runs and runtime-config-dir installs,
|
|
* where the sibling agents/ IS the user's agents dir — UNLESS that path
|
|
* carries an exact node_modules segment. gsd-tools.cjs lives inside
|
|
* gsd-core/bin/ in every install shape, but on an npm-global install
|
|
* gsd-core/ sits inside the package (not the runtime config dir) and the
|
|
* package ships its own agents/, so the install-relative path resolves
|
|
* to the bundled copy and the check validates the package against
|
|
* itself — agents_installed can never be false. In that case resolve
|
|
* getGlobalConfigDir('claude')/agents (honours CLAUDE_CONFIG_DIR) like
|
|
* every other runtime (#3203).
|
|
* 3. For non-claude runtimes with a manifest-backed project-local install:
|
|
* <projectRoot>/<localConfigDir>/agents (or <projectRoot>/agents when
|
|
* the runtime's local install targets the project root). Requiring the
|
|
* GSD manifest prevents runtime-native project agents from shadowing a
|
|
* working global GSD install. Symlinked local agent directories are ignored.
|
|
* 4. For non-claude runtimes: getGlobalConfigDir(runtime)/agents
|
|
*
|
|
* @param runtime - the active runtime name; defaults to GSD_RUNTIME env, then 'claude'
|
|
* @param projectRoot - canonical project root for local-install discovery
|
|
*/
|
|
function getAgentsDir(runtime?: string, projectRoot?: string): string {
|
|
if (process.env['GSD_AGENTS_DIR']) {
|
|
return process.env['GSD_AGENTS_DIR'];
|
|
}
|
|
const resolved = runtime ?? (process.env['GSD_RUNTIME'] || 'claude');
|
|
if (resolved === 'claude') {
|
|
const installRelative = path.join(__dirname, '..', '..', '..', 'agents');
|
|
// #3203: a lexical guard, not an install-shape test. It targets the
|
|
// layouts where the sibling agents/ is the package's own bundled copy and
|
|
// the check would otherwise validate the package against itself; a path
|
|
// merely carrying a directory of that name resolves the same way, and a
|
|
// non-empty GSD_AGENTS_DIR overrides both.
|
|
if (installRelative.split(path.sep).includes('node_modules')) {
|
|
return path.join(getGlobalConfigDir('claude'), 'agents');
|
|
}
|
|
return installRelative;
|
|
}
|
|
if (projectRoot) {
|
|
// eslint-disable-next-line @typescript-eslint/no-require-imports
|
|
const { runtimes } = require('./capability-registry.cjs') as {
|
|
runtimes: Record<string, { runtime?: { hostBehaviors?: { localTargetIsProjectRoot?: boolean } } }>;
|
|
};
|
|
const runtimeConfig = runtimes[resolved]?.runtime;
|
|
const localConfigDirName = getDirName(resolved);
|
|
const localConfigDir = localConfigDirName === NO_LOCAL_CONFIG_DIR_SENTINEL
|
|
? undefined
|
|
: runtimeConfig?.hostBehaviors?.localTargetIsProjectRoot
|
|
? projectRoot
|
|
: path.join(projectRoot, localConfigDirName);
|
|
if (!localConfigDir) {
|
|
return path.join(getGlobalConfigDir(resolved), 'agents');
|
|
}
|
|
const localAgentsDir = path.join(localConfigDir, 'agents');
|
|
const manifestPath = path.join(localConfigDir, 'gsd-file-manifest.json');
|
|
try {
|
|
if (fs.lstatSync(localAgentsDir).isDirectory() && fs.lstatSync(manifestPath).isFile()) {
|
|
return localAgentsDir;
|
|
}
|
|
} catch {
|
|
// Local discovery is best-effort; any probe failure preserves global fallback.
|
|
}
|
|
}
|
|
return path.join(getGlobalConfigDir(resolved), 'agents');
|
|
}
|
|
|
|
/**
|
|
* Check which GSD agents are installed on disk.
|
|
*
|
|
* @param runtime - the active runtime name; defaults to GSD_RUNTIME env, then 'claude'
|
|
* @param projectRoot - canonical project root for local-install discovery
|
|
*/
|
|
function checkAgentsInstalled(runtime?: string, projectRoot?: string): AgentsInstalledResult {
|
|
const resolvedRuntime = runtime ?? (process.env['GSD_RUNTIME'] || 'claude');
|
|
const agentsDir = getAgentsDir(resolvedRuntime, projectRoot);
|
|
const expectedAgents = Object.keys(MODEL_PROFILES);
|
|
const installed: string[] = [];
|
|
const missing: string[] = [];
|
|
|
|
if (!fs.existsSync(agentsDir)) {
|
|
return {
|
|
agents_installed: false,
|
|
missing_agents: expectedAgents,
|
|
installed_agents: [],
|
|
incomplete_agents: [],
|
|
agents_dir: agentsDir,
|
|
agent_runtime: resolvedRuntime,
|
|
};
|
|
}
|
|
|
|
for (const agent of expectedAgents) {
|
|
if (agentFileExists(agentsDir, agent, resolvedRuntime)) {
|
|
installed.push(agent);
|
|
} else {
|
|
missing.push(agent);
|
|
}
|
|
}
|
|
|
|
// ── Manifest-backed completeness check ──────────────────────────────────────
|
|
// If a gsd-file-manifest.json exists alongside the agents dir (parent dir),
|
|
// verify that every manifest-tracked file for each expected agent is present
|
|
// on disk. Missing manifest-tracked files indicate an incomplete install even
|
|
// when the plain presence check above passed (e.g. .md present, .toml absent).
|
|
// If no manifest is found the check is a no-op (graceful for claude/bundled).
|
|
const incomplete: string[] = [];
|
|
// #2872: the manifest read is the Installer Migration Module's, not a
|
|
// fourth private copy of it. Lazily required — matching this file's own
|
|
// capability-registry idiom — so a pure read/verify surface on the
|
|
// init/verify hot path takes no new static dependency.
|
|
// eslint-disable-next-line @typescript-eslint/no-require-imports
|
|
const { readInstallManifest } = require('./installer-migrations.cjs') as {
|
|
readInstallManifest: (configDir: string) => { files: Record<string, string> };
|
|
};
|
|
const manifestFiles: Record<string, unknown> = readInstallManifest(path.dirname(agentsDir)).files;
|
|
|
|
if (Object.keys(manifestFiles).length > 0) {
|
|
for (const agent of expectedAgents) {
|
|
// Find all manifest keys that belong to this agent:
|
|
// key must be "agents/<agentName>.<ext>" with no further path segments.
|
|
const agentPrefix = `agents/${agent}.`;
|
|
const agentManifestKeys = Object.keys(manifestFiles).filter(key => {
|
|
if (!key.startsWith(agentPrefix)) return false;
|
|
const rest = key.slice(agentPrefix.length);
|
|
// rest must be a bare extension (no slashes, non-empty)
|
|
return rest.length > 0 && !rest.includes('/');
|
|
});
|
|
if (agentManifestKeys.length === 0) {
|
|
// Agent not tracked in manifest — skip completeness check for this agent
|
|
continue;
|
|
}
|
|
const allPresent = agentManifestKeys.every(key => {
|
|
const basename = key.slice('agents/'.length);
|
|
return fs.existsSync(path.join(agentsDir, basename));
|
|
});
|
|
if (!allPresent) {
|
|
incomplete.push(agent);
|
|
}
|
|
}
|
|
}
|
|
|
|
return {
|
|
agents_installed: installed.length > 0 && missing.length === 0 && incomplete.length === 0,
|
|
missing_agents: missing,
|
|
installed_agents: installed,
|
|
incomplete_agents: incomplete,
|
|
agents_dir: agentsDir,
|
|
agent_runtime: resolvedRuntime,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Validate Codex `.toml` agent files for Anthropic-flavored `model` pins and
|
|
* orphaned `model_reasoning_effort` values (ADR-2313 D6, #3242).
|
|
*
|
|
* A new sibling export to {@link checkAgentsInstalled}, deliberately — that
|
|
* function carries 33 upstream dependents and cyclomatic complexity 25, so this
|
|
* posture check gets zero new branches there (see 40-design.md "Rejected" #1).
|
|
* Presence is `checkAgentsInstalled`'s job; this function's job starts only once
|
|
* the runtime is confirmed `codex` and only inspects posture, never presence.
|
|
*
|
|
* Read-only: detects, never repairs (repair is Phase 3, #3243).
|
|
*
|
|
* @param runtime - the active runtime name; defaults to GSD_RUNTIME env, then 'claude'
|
|
* @param projectRoot - canonical project root for local-install discovery
|
|
*/
|
|
function checkCodexModelPosture(runtime?: string, projectRoot?: string): CodexModelPostureResult {
|
|
// Short-circuit BEFORE any filesystem access: a non-codex runtime must never
|
|
// have its agents directory resolved or a stray .toml inspected, however
|
|
// violating that file's contents would be if it were ever read (#3242 row 25).
|
|
const resolvedRuntime = runtime ?? (process.env['GSD_RUNTIME'] || 'claude');
|
|
if (resolvedRuntime !== 'codex') {
|
|
return {
|
|
ok: true,
|
|
violations: [],
|
|
checked: [],
|
|
agents_dir: '',
|
|
agent_runtime: resolvedRuntime,
|
|
reason: POSTURE_REASON.NOT_CODEX,
|
|
};
|
|
}
|
|
|
|
const agentsDir = getAgentsDir(resolvedRuntime, projectRoot);
|
|
if (!fs.existsSync(agentsDir)) {
|
|
// Presence is checkAgentsInstalled's job — an absent agents dir here is a
|
|
// distinct, non-violating outcome, not a failure of this check.
|
|
return {
|
|
ok: true,
|
|
violations: [],
|
|
checked: [],
|
|
agents_dir: agentsDir,
|
|
agent_runtime: resolvedRuntime,
|
|
reason: POSTURE_REASON.AGENTS_DIR_MISSING,
|
|
};
|
|
}
|
|
|
|
// Skip symlinks — matches cmdEffortSync's existing idiom in commands.cts
|
|
// ("Skip symlinks — only write regular files..."). Here the risk is reading
|
|
// (not writing) through a symlink: readFileSync follows symlinks, so an
|
|
// agents-dir symlink pointing at an arbitrary file would let that target's
|
|
// contents be echoed into this function's `value` field. A symlinked agent
|
|
// file is a structural install choice (checkAgentsInstalled's territory),
|
|
// not a model-content posture defect, so it is silently excluded from
|
|
// `checked` rather than reported as a distinct violation — same shape as
|
|
// cmdEffortSync, which silently drops symlinks from its file list rather
|
|
// than inventing a new skip/violation reason.
|
|
const tomlFiles = fs
|
|
.readdirSync(agentsDir)
|
|
.filter((entry) => {
|
|
if (!entry.endsWith('.toml')) return false;
|
|
try {
|
|
return fs.lstatSync(path.join(agentsDir, entry)).isFile();
|
|
} catch {
|
|
return false;
|
|
}
|
|
})
|
|
.sort();
|
|
|
|
const checked: string[] = [];
|
|
const violations: PostureViolation[] = [];
|
|
|
|
for (const entry of tomlFiles) {
|
|
const agentName = entry.slice(0, -'.toml'.length);
|
|
const filePath = path.join(agentsDir, entry);
|
|
checked.push(agentName);
|
|
|
|
let raw: string;
|
|
try {
|
|
raw = fs.readFileSync(filePath, 'utf8');
|
|
} catch {
|
|
// Never throws, never silently skips — an unreadable file is reported and
|
|
// the loop continues checking the rest (40-design.md "Rejected" #5).
|
|
violations.push({ agent: agentName, file: filePath, reason: POSTURE_REASON.UNREADABLE });
|
|
continue;
|
|
}
|
|
|
|
const { model, hasReasoningEffort } = scanTomlLines(stripBOM(raw));
|
|
|
|
if (model !== null && isAnthropicFlavoredModel(model)) {
|
|
violations.push({
|
|
agent: agentName,
|
|
file: filePath,
|
|
reason: POSTURE_REASON.ANTHROPIC_FLAVORED_MODEL,
|
|
value: truncatePostureValue(model),
|
|
});
|
|
} else if (model === null && hasReasoningEffort) {
|
|
// #838 coupling: a reasoning-effort pin with no model pin means Codex
|
|
// inherits the session model while the effort pin silently disagrees.
|
|
violations.push({
|
|
agent: agentName,
|
|
file: filePath,
|
|
reason: POSTURE_REASON.ORPHANED_REASONING_EFFORT,
|
|
});
|
|
}
|
|
}
|
|
|
|
return {
|
|
ok: violations.length === 0,
|
|
violations,
|
|
checked,
|
|
agents_dir: agentsDir,
|
|
agent_runtime: resolvedRuntime,
|
|
};
|
|
}
|
|
|
|
// #3897 rung 3 — the canonical bundled `agents/*.md` source directory (the
|
|
// tool-contract source of truth), resolved the same install-relative way
|
|
// getAgentsDir resolves the claude case, WITHOUT that function's npm-global
|
|
// node_modules redirect: that redirect exists so a Codex/claude INSTALL is
|
|
// never validated against itself, but here we deliberately want the bundled
|
|
// copy every time — it is the only place the `tools:` contract a role
|
|
// derives its sandbox_mode from actually lives, in every install shape
|
|
// (repo-dev tree or npm-global package, where the package still ships its
|
|
// own agents/ alongside bin/ and gsd-core/).
|
|
function _canonicalAgentSourceDir(): string {
|
|
return path.join(__dirname, '..', '..', '..', 'agents');
|
|
}
|
|
|
|
/**
|
|
* Validate installed Codex `.toml` agents' `sandbox_mode` against what each
|
|
* role's own tool contract derives (#3897, ADR-3473 §8.3 criterion 3,
|
|
* HALT.md option 2). Sibling to {@link checkCodexModelPosture} — same shape,
|
|
* same short-circuits — but a different defect class: a TOML whose
|
|
* `sandbox_mode` disagrees with the derived expectation, not a bad `model`.
|
|
*
|
|
* `deriveCodexSandboxMode` (and the `CODEX_SANDBOX_HOLDS` hold list + its own
|
|
* self-invalidation check it embeds) is imported from `codex-agent-toml.cjs`
|
|
* — the shared, side-effect-free leaf both `bin/install.js`'s emitter and
|
|
* this posture check import from (CAUSE A fix, #3897: this function used to
|
|
* lazily `require('bin/install.js')` to reach the same derivation, but
|
|
* requiring `bin/install.js` runs its whole CLI top-level, including an
|
|
* ASCII banner print to stdout, which corrupted every stdout-JSON caller of
|
|
* this posture check, e.g. `gsd-tools validate agents`) — so the emitter and
|
|
* this posture check can never silently diverge on the same tool-contract
|
|
* predicate — the exact generative-fix-divergence shape this epic exists to
|
|
* close. `deriveCodexSandboxMode` itself is total (never throws, #3897
|
|
* CAUSE C fix) — a held role whose supplied content no longer derives
|
|
* broader than its pin simply returns `read-only` rather than failing,
|
|
* because the pin is then a no-op. The staleness invariant (S4/S5) this
|
|
* check's imports still carry is enforced separately, at the real `agents/`
|
|
* roster level, by `validateCodexSandboxHolds` and
|
|
* `tests/codex-config.test.cjs` T24/T25 — not by this per-call derivation.
|
|
*
|
|
* Read-only: detects, never repairs — same posture as {@link checkCodexModelPosture}.
|
|
*
|
|
* @param runtime - the active runtime name; defaults to GSD_RUNTIME env, then 'claude'
|
|
* @param projectRoot - canonical project root for local-install discovery
|
|
*/
|
|
function checkCodexSandboxPosture(runtime?: string, projectRoot?: string): CodexSandboxPostureResult {
|
|
const resolvedRuntime = runtime ?? (process.env['GSD_RUNTIME'] || 'claude');
|
|
if (resolvedRuntime !== 'codex') {
|
|
return {
|
|
ok: true,
|
|
violations: [],
|
|
checked: [],
|
|
agents_dir: '',
|
|
agent_runtime: resolvedRuntime,
|
|
reason: POSTURE_REASON.NOT_CODEX,
|
|
};
|
|
}
|
|
|
|
const agentsDir = getAgentsDir(resolvedRuntime, projectRoot);
|
|
if (!fs.existsSync(agentsDir)) {
|
|
return {
|
|
ok: true,
|
|
violations: [],
|
|
checked: [],
|
|
agents_dir: agentsDir,
|
|
agent_runtime: resolvedRuntime,
|
|
reason: POSTURE_REASON.AGENTS_DIR_MISSING,
|
|
};
|
|
}
|
|
|
|
const canonicalAgentsDir = _canonicalAgentSourceDir();
|
|
|
|
// Same symlink guard as checkCodexModelPosture, same reason (never follow
|
|
// an agents-dir symlink into an arbitrary file's content).
|
|
const tomlFiles = fs
|
|
.readdirSync(agentsDir)
|
|
.filter((entry) => {
|
|
if (!entry.endsWith('.toml')) return false;
|
|
try {
|
|
return fs.lstatSync(path.join(agentsDir, entry)).isFile();
|
|
} catch {
|
|
return false;
|
|
}
|
|
})
|
|
.sort();
|
|
|
|
const checked: string[] = [];
|
|
const violations: SandboxPostureViolation[] = [];
|
|
|
|
for (const entry of tomlFiles) {
|
|
const agentName = entry.slice(0, -'.toml'.length);
|
|
const filePath = path.join(agentsDir, entry);
|
|
checked.push(agentName);
|
|
|
|
let raw: string;
|
|
try {
|
|
raw = fs.readFileSync(filePath, 'utf8');
|
|
} catch {
|
|
violations.push({ agent: agentName, file: filePath, reason: POSTURE_REASON.UNREADABLE });
|
|
continue;
|
|
}
|
|
|
|
// #3897 rung 4 (isolated correctness review, MINOR finding 2): route
|
|
// through the same block-aware `scanTomlLines` the sibling
|
|
// `checkCodexModelPosture` already uses, rather than a naive whole-file
|
|
// regex — a `sandbox_mode = "..."`-shaped line inside the
|
|
// `developer_instructions` block (prose) must never be read as a live
|
|
// value. A prior naive `raw.match(/^sandbox_mode.../m)` here produced a
|
|
// FALSE violation whenever an agent's own prompt prose happened to
|
|
// contain that shape.
|
|
const found = scanTomlLines(stripBOM(raw)).sandboxMode;
|
|
if (found === null) {
|
|
// No sandbox_mode line at all (e.g. sandboxTier "none") is a deliberate,
|
|
// documented state elsewhere — not this check's business.
|
|
continue;
|
|
}
|
|
|
|
const canonicalFile = path.join(canonicalAgentsDir, `${agentName}.md`);
|
|
let canonicalContent: string;
|
|
try {
|
|
canonicalContent = fs.readFileSync(canonicalFile, 'utf8');
|
|
} catch {
|
|
// No canonical role source (a custom/non-roster agent) — nothing to
|
|
// derive an expectation from, so this is not this check's business.
|
|
continue;
|
|
}
|
|
|
|
// `canonicalContent` is always a real string here (read via fs.readFileSync
|
|
// above), so extractToolsValue's `undefined` (non-string input) branch is
|
|
// unreachable on this path — the `?? ''` is a type-level formality, not a
|
|
// behavior change (F4, #3897 security review: extractToolsValue is TOTAL).
|
|
const toolsRaw = extractToolsValue(canonicalContent) ?? '';
|
|
const expected = deriveCodexSandboxMode(agentName, toolsRaw);
|
|
if (expected !== found) {
|
|
// #3897 rung 4 (isolated correctness review, MINOR finding 3):
|
|
// truncatePostureValue matches the sibling checkCodexModelPosture's
|
|
// convention (see its own `value: truncatePostureValue(model)` above)
|
|
// so an oversized or secret-shaped `sandbox_mode` value can never
|
|
// reach `validate agents --raw` output at full length.
|
|
violations.push({
|
|
agent: agentName,
|
|
file: filePath,
|
|
expected: truncatePostureValue(expected),
|
|
found: truncatePostureValue(found),
|
|
});
|
|
}
|
|
}
|
|
|
|
return {
|
|
ok: violations.length === 0,
|
|
violations,
|
|
checked,
|
|
agents_dir: agentsDir,
|
|
agent_runtime: resolvedRuntime,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Probe a single agents dir for `<name>` across runtime filename variants.
|
|
* Mirrors {@link checkAgentsInstalled}'s probe (`.md`, `.agent.md`, `.toml`,
|
|
* and the kimi `subagents/<name>.{yaml,md}` pair) so the two can never disagree
|
|
* about which on-disk shapes count as "installed". Not exported — internal to
|
|
* {@link resolveAgentHint}.
|
|
*/
|
|
function agentFileExists(agentsDir: string, name: string, runtime: string): boolean {
|
|
const base = path.join(agentsDir, `${name}.md`);
|
|
const copilot = path.join(agentsDir, `${name}.agent.md`);
|
|
const codex = path.join(agentsDir, `${name}.toml`);
|
|
if (fs.existsSync(base) || fs.existsSync(copilot) || fs.existsSync(codex)) {
|
|
return true;
|
|
}
|
|
// kimi requires BOTH the persona yaml and the prompt md (same as checkAgentsInstalled).
|
|
const kimiYaml = path.join(agentsDir, 'subagents', `${name}.yaml`);
|
|
const kimiPrompt = path.join(agentsDir, 'subagents', `${name}.md`);
|
|
return runtime === 'kimi' && fs.existsSync(kimiYaml) && fs.existsSync(kimiPrompt);
|
|
}
|
|
|
|
/**
|
|
* Resolve a per-plan `agent_hint` specialist name to a dispatchable subagent
|
|
* type on the active runtime (#1689). Unlike {@link checkAgentsInstalled},
|
|
* which validates the fixed GSD roster, this answers "does an agent file for
|
|
* this ARBITRARY name exist in the active runtime's agent dir(s)?" — so a plan
|
|
* can opt into a domain specialist (e.g. a Flutter engineer) that shares the
|
|
* gsd-executor contract without being part of the built-in roster.
|
|
*
|
|
* Probes BOTH the runtime-canonical agents dir ({@link getAgentsDir}, which
|
|
* honors `GSD_AGENTS_DIR`, project-local manifest-backed installs, and the
|
|
* claude install-relative path) AND the runtime's global config agents dir, so
|
|
* a specialist installed at either level is recognized. The decision in #1689
|
|
* explicitly requires consulting the active runtime's agent dir rather than
|
|
* only the Claude runtime's user-global and project-local agent dirs.
|
|
*
|
|
* @returns the name when a matching agent file exists; `null` when it does not
|
|
* (the caller falls back to `gsd-executor`). An empty/whitespace name always
|
|
* returns `null`.
|
|
*/
|
|
function resolveAgentHint(name: string, runtime?: string, projectRoot?: string): string | null {
|
|
const trimmed = String(name ?? '').trim();
|
|
if (trimmed === '') return null;
|
|
// A hint is a bare agent name. Reject path separators and `..` so a value
|
|
// like `../../README` cannot path-traverse out of the agents dir via
|
|
// path.join and match an unrelated file — that would echo an invalid
|
|
// subagent_type and block the wave, defeating fail-closed resolution.
|
|
if (trimmed.includes('/') || trimmed.includes('\\') || trimmed.includes('..')) return null;
|
|
const resolvedRuntime = runtime ?? (process.env['GSD_RUNTIME'] || 'claude');
|
|
|
|
const candidateDirs = new Set<string>();
|
|
candidateDirs.add(getAgentsDir(resolvedRuntime, projectRoot));
|
|
candidateDirs.add(path.join(getGlobalConfigDir(resolvedRuntime), 'agents'));
|
|
|
|
for (const dir of candidateDirs) {
|
|
if (agentFileExists(dir, trimmed, resolvedRuntime)) {
|
|
return trimmed;
|
|
}
|
|
}
|
|
return null;
|
|
}
|
|
|
|
export = {
|
|
getAgentsDir,
|
|
checkAgentsInstalled,
|
|
checkCodexModelPosture,
|
|
checkCodexSandboxPosture,
|
|
POSTURE_REASON,
|
|
resolveAgentHint,
|
|
};
|