mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-14 00:12:12 +02:00
00f966b3ec
* fix(codex): use resume-compatible flags * fix: V-001 security vulnerability Automated security fix generated by Orbis Security AI * docs: align prompt-injection thresholds to security.ts (v1.6.4.0 catch-up) CLAUDE.md:290 and ARCHITECTURE.md:159 were missed when WARN was bumped 0.60 → 0.75 ind75402bb(v1.6.4.0, "cut Haiku classifier FP from 44% to 23%, gate now enforced", #1135). browse/src/security.ts:37 has WARN: 0.75 and BROWSER.md:743 was updated alongside that commit; CLAUDE.md and ARCHITECTURE.md still read 0.60. Also adds the SOLO_CONTENT_BLOCK: 0.92 entry to CLAUDE.md (already in security.ts:50 and BROWSER.md:745, missing from CLAUDE.md's threshold table). No code change. No behavior change. Pure doc-vs-code alignment. Verification: $ grep -n "WARN" browse/src/security.ts CLAUDE.md ARCHITECTURE.md BROWSER.md browse/src/security.ts:37: WARN: 0.75, CLAUDE.md:290: - \`WARN: 0.75\` ... ARCHITECTURE.md:159: ...>= \`WARN\` (0.75)... BROWSER.md:743: - \`WARN: 0.75\` ... Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: Korean/CJK IME input and rendering in Sidebar Terminal Fixes #1272 This commit addresses three separate Korean/CJK bugs in the Sidebar Terminal: **Bug 1 - IME Input**: Korean text typed via IME composition was not reaching the PTY correctly. Added compositionstart/compositionend event listeners to suppress partial jamo fragments and only send the final composed string. **Bug 2a - Font Rendering**: Added CJK monospace font fallbacks ("Noto Sans Mono CJK KR", "Malgun Gothic") to both the xterm.js fontFamily config and the CSS --font-mono variable. This ensures consistent cell-width calculations for Korean characters. **Bug 2b - UTF-8 Boundary Detection**: Added buffering logic to prevent multi-byte UTF-8 characters (Korean is 3 bytes) from being split across WebSocket chunks. This follows the same pattern as PR #1007 which fixed the sidebar-agent path, but extends it to the terminal-agent path. Special thanks to @ldybob for the excellent root cause analysis and proposed solutions in issue #1272. Tested on WSL2 + Windows 11 with Korean IME. * fix(ship): tighten Plan Completion gate (VAS-449 remediation) VAS-446 shipped with a PLAN.md acceptance criterion (domain-hq has /docs/dashboard.md) silently skipped. /ship's Plan Completion subagent existed at ship time (added in v1.4.1.0) but the gate let the failure through. Four structural fixes: 1. Path concreteness rule: items naming a concrete filesystem path MUST be classified DONE/NOT DONE via [ -f <path> ], never UNVERIFIABLE. 2. Validator detection: CONTENT-SHAPE items scan target repo's package.json for validate-* scripts and run them before falling back to UNVERIFIABLE. 3. Per-item UNVERIFIABLE confirmation: replaces blanket "I've checked each one" with per-item Y/N/D loop. The blanket-confirm path is the exact failure VAS-449 surfaced. 4. Subagent fail-closed: if Plan Completion subagent + inline fallback both fail, surface explicit AskUserQuestion instead of silent pass. Replaces the prior "Never block /ship on subagent failure" fail-open. Locked in by test/ship-plan-completion-invariants.test.ts (5 assertions, no LLM dependency, ~60ms). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(browse): bash.exe wrap for telemetry on Windows reportAttemptTelemetry() in browse/src/security.ts calls spawn(bin, args) where bin is the gstack-telemetry-log bash script. On Windows this fails silently with ENOENT — CreateProcess can't dispatch on shebang lines. Adopts v1.24.0.0's Bun.which + GSTACK_*_BIN override pattern (from browse/src/claude-bin.ts:resolveClaudeCommand, introduced in #1252) for resolving bash.exe. resolveBashBinary() honors GSTACK_BASH_BIN absolute-path or PATH-resolvable override, falling back to Bun.which('bash') which finds Git Bash on the standard Windows install. buildTelemetrySpawnCommand() wraps the script invocation on win32 only; POSIX path is bit-identical. Returns null when bash can't be resolved on Windows so caller skips spawn — local attempts.jsonl audit trail keeps working without surfacing a Windows-only failure. 8 new unit tests cover resolveBashBinary (POSIX bash, absolute override, quote-stripping, BASH_BIN fallback, empty-PATH null) and buildTelemetrySpawnCommand (POSIX pass-through, win32 bash wrap, win32 null on unresolvable, arg-array immutability). POSIX path is bit-identical — Bun.which('bash') on Linux/macOS returns the same /bin/bash or /usr/bin/bash that the old hardcoded spawn relied on. * fix(make-pdf): Bun.which-based binary resolution for browse + pdftotext on Windows Extends v1.24.0.0's Bun.which + GSTACK_*_BIN override pattern (introduced in browse/src/claude-bin.ts via #1252) to the two other binary resolvers in the codebase: make-pdf/src/browseClient.ts:resolveBrowseBin and make-pdf/src/pdftotext.ts:resolvePdftotext. Same Windows quirks (fs.accessSync(X_OK) degrades to existence-check; `which` isn't available outside Git Bash; bun --compile --outfile X emits X.exe), same Bun.which-based fix shape, same env override convention. Changes: - GSTACK_BROWSE_BIN / GSTACK_PDFTOTEXT_BIN as the v1.24-aligned overrides; BROWSE_BIN / PDFTOTEXT_BIN remain as back-compat aliases. - Bun.which() replaces execFileSync('which', ...) for PATH lookup. Handles Windows PATHEXT natively; no more `where`-vs-`which` branch. - findExecutable(base) helper exported from each module, probes .exe/.cmd/.bat after the bare-path miss on win32. Linux/macOS behavior is bit-identical (isExecutable short-circuits before the win32 branch ever runs). - macCandidates renamed posixCandidates (always was — /opt/homebrew, /usr/local, /usr/bin). No Windows candidates added; Poppler installs scatter across Scoop/Chocolatey/portable zips and guessing causes false positives. - Error messages get a Windows install hint (scoop install poppler / oschwartz10612) and `setx` example for GSTACK_*_BIN. - Pre-existing test 'honors BROWSE_BIN when it points at a real executable' was hardcoded /bin/sh — made cross-platform via a REAL_EXE constant (cmd.exe on win32, /bin/sh on POSIX). Was a Windows-CI blocker on its own. Coordination: PR #1094 (@BkashJEE) covered browseClient.ts independently with a narrower scope; this PR's pdftotext + cross-platform tests + GSTACK_*_BIN naming are additive. Either order of merge works. Test plan: - bun test make-pdf/test/browseClient.test.ts make-pdf/test/pdftotext.test.ts on win32 — 29 pass, 0 fail (12 new assertions: findExecutable POSIX/win32/null, resolveBrowseBin GSTACK_BROWSE_BIN + BROWSE_BIN + precedence + quote-strip, same shape for resolvePdftotext + Windows install hint in error message). - POSIX branch unchanged — fs.accessSync(X_OK) on Linux/macOS short-circuits before any win32 logic runs, matching the v1.24 claude-bin.ts pattern. * fix(browse): NTFS ACL hardening for Windows state files via icacls gstack's ~/.gstack/ state directory holds bearer tokens, canary tokens, agent queue contents (with prompt history), session state, security-decision logs, and saved cookie bundles — all written with { mode: 0o600 } / 0o700. On Windows, those mode bits are a silent no-op: Node's fs module doesn't translate POSIX modes to NTFS ACLs, and inherited ACLs leave every "restricted" file readable by other principals on the machine (verified via icacls — six ACEs, the intended user is the LAST of six). Threat model is non-trivial on: - Self-hosted CI runners (different service account on the same Windows box can read developer tokens, canary tokens, prompt history) - Shared development machines (agencies, studios, lab environments) - Multi-tenant servers with shared home directories Orthogonal to v1.24.0.0's binary-resolution work — complementary at the write side. v1.24's bin/gstack-paths resolves ~/.gstack/ correctly across plugin / global / local installs; this PR ensures files written into those resolved paths actually get the POSIX 0o600 semantic translated to NTFS. The fix: - New browse/src/file-permissions.ts (158 LOC, 5 public + 1 test-reset). restrictFilePermissions / restrictDirectoryPermissions wrap chmod (POSIX) or icacls /inheritance:r /grant:r <user>:(F) (Windows). writeSecureFile / appendSecureFile / mkdirSecure are drop-in wrappers for the common patterns. - 19 call sites converted across 9 source files: browser-manager.ts, browser-skill-write.ts, cli.ts, config.ts, meta-commands.ts, security-classifier.ts, security.ts (4 sites), server.ts (5 sites), terminal-agent.ts (8 sites), tunnel-denial-log.ts. - (OI)(CI) inheritance flags on directories mean files created via fs.write* *inside* an mkdirSecure-created dir inherit the owner-only ACL automatically — important for tunnel-denial-log.ts where appends use async fsp.appendFile. Error handling: icacls failures (nonexistent path, missing icacls.exe, hardened environments) log a one-shot warning to stderr and proceed. Once-per-process gating prevents log spam if the condition persists. Filesystem stays functional; the file just ends up with inherited ACLs. Test plan: - bun test browse/test/file-permissions.test.ts — 13 pass, 0 fail (POSIX mode-bit assertions, Windows no-throw, mkdir idempotence, recursive creation, Buffer payloads, append-creates-then-reapplies-once semantics) - bun test browse/test/security.test.ts — 38 pass, 0 fail (existing security test suite plus the bash-binary resolution tests added in fix #1119; the converted writeFileSync/appendFileSync/mkdirSync sites in security.ts integrate cleanly) - Empirical icacls before/after on a real file — 6 ACEs → 1 ACE - bun build typecheck on all modified files — clean (server.ts has a pre-existing playwright-core/electron resolution issue unrelated to this PR) POSIX behavior is bit-identical to old code — fs.chmodSync(path, 0o6XX) on the helper's POSIX branch matches the inline { mode: 0o6XX } it replaces. Linux and macOS see no behavior change. Inviting pushback on three judgment calls (in PR description): 1. icacls vs npm library 2. ACL scope — just user, or user + SYSTEM? 3. Graceful degradation — once-per-process warn, not silent, not hard-fail. * fix(browse): declare lastConsoleFlushed to restore console-log persistence flushBuffers() references a `lastConsoleFlushed` cursor at server.ts:337 and assigns it at :344, but the `let lastConsoleFlushed = 0;` declaration is missing — only the network and dialog siblings are declared at lines 327-328. Result: every 1-second flushBuffers tick (line 376) throws `ReferenceError: lastConsoleFlushed is not defined`, gets swallowed by the catch at line 369 ("[browse] Buffer flush failed: ..."), and the console branch's append never runs. browse-console.log is never written in any production deployment since this regressed. Discovered by stress-testing the daemon with 15 concurrent CLIs against cold state — the race surfaced the buffer-flush error spam in one spawned daemon's stderr. Verified by running the daemon against a real file:// page with console.log events: in-memory `browse console` returns the entries, but `.gstack/browse-console.log` is never created on disk. Regression introduced by1a100a2a"fix: eliminate duplicate command sets in chain, improve flush perf and type safety" — the flush refactor switched from `Bun.write` to `fs.appendFileSync` and added the `lastConsoleFlushed` cursor pattern alongside its network/dialog siblings, but missed the matching `let` declaration. Tests don't currently exercise flushBuffers, so the regression shipped silently. Fix: - Declare `let lastConsoleFlushed = 0;` next to `lastNetworkFlushed` and `lastDialogFlushed` (browse/src/server.ts:327) - Add a source-level guard test (browse/test/server-flush-trackers.test.ts) that fails any future refactor that adds a fourth `last*Flushed` cursor without the matching declaration. Same pattern as terminal-agent.test.ts and dual-listener.test.ts — read source as text, assert invariant, no daemon required. Test plan: - [x] New regression test fails on current main, passes with the fix - [x] `bun run build` clean - [x] Manual smoke: spawn daemon -> goto file:// page with console.log -> wait 4s -> .gstack/browse-console.log now exists with the expected entries (163 bytes vs zero before) 🤖 Generated with [Claude Code](https://claude.com/claude-code) * fix(browse): per-process state-file temp path to fix concurrent-write ENOENT The daemon writes `.gstack/browse.json` via the standard atomic-rename pattern: `writeFileSync(tmp, …) → renameSync(tmp, stateFile)`. Four sites in server.ts use this pattern (initial daemon-startup state at :2002, /tunnel/start handler at :1479, BROWSE_TUNNEL=1 inline tunnel update at :2083, BROWSE_TUNNEL_LOCAL_ONLY=1 update at :2113), and all four hard-code the same temp filename `${stateFile}.tmp`. Under concurrent writers the shared filename races on the rename: t0 Writer A: writeFileSync(stateFile + '.tmp', payloadA) t1 Writer B: writeFileSync(stateFile + '.tmp', payloadB) // overwrites A t2 Writer A: renameSync(stateFile + '.tmp', stateFile) // moves B's payload t3 Writer B: renameSync(stateFile + '.tmp', stateFile) // ENOENT — file gone Reproduced empirically with 15 concurrent CLIs against a fresh `.gstack/`: [browse] Failed to start: ENOENT: no such file or directory, rename '…/.gstack/browse.json.tmp' -> '…/.gstack/browse.json' Pre-fix success rate: **0 / 15** under cold-start race. Post-fix success rate: **15 / 15**, zero ENOENT. Fix: - New `tmpStatePath()` helper (server.ts:333) returns `${stateFile}.tmp.${pid}.${randomBytes(4).toString('hex')}` - All 4 call sites use `tmpStatePath()` instead of the shared literal - Atomic rename still gives last-writer-wins semantics on the final state.json content; only behavior change is that concurrent writers no longer kill each other on the rename step Source-level guard test (browse/test/server-tmp-state-path.test.ts) locks two invariants: (1) no remaining `stateFile + '.tmp'` literals, (2) every state-write `writeFileSync` call uses `tmpStatePath()`. Same read-source-as-text pattern as terminal-agent.test.ts and dual-listener.test.ts — no daemon required, runs in tier-1 free. Test plan: - [x] Targeted source-level guard test passes (3 / 0) - [x] `bun run build` clean - [x] Live regression: 15 concurrent CLIs against cold state → 15 / 15 healthy, 0 ENOENT (vs 0 / 15 pre-fix) - [x] No `.tmp.*` orphans left behind after rename succeeds - [x] Related test cluster (server-auth, dual-listener, cdp-mutex, findport) — same pre-existing flakes as `main`, no new regressions introduced 🤖 Generated with [Claude Code](https://claude.com/claude-code) * fix(browse): clear refs when iframe auto-detaches in getActiveFrameOrPage Asymmetric cleanup between two equivalent staleness conditions: onMainFrameNavigated() → clearRefs() + activeFrame = null ✓ getActiveFrameOrPage() → activeFrame = null (refs NOT cleared) ✗ Both paths see the same staleness condition — refs were captured against a frame that no longer exists. The main-frame path correctly clears both pieces of state. The iframe-detach path nulls the frame but leaves the refMap intact. The lazy click-time check in `resolveRef` (tab-session.ts:97) partially saves us — `entry.locator.count()` on a detached-frame locator throws or returns 0, so the click errors out as "Ref X is stale". But the user has no signal that frame context silently changed underfoot: the next `snapshot` runs against `this.page` (main) while old iframe refs still litter `refMap` with the same role+name keys. New refs collide with stale ones, the resolver picks one at random, the user clicks the wrong element. TODOS.md line 816-820 documents "Detached frame auto-recovery" as a shipped iframe-support feature in v0.12.1.0. This restores the documented intent — the recovery should leave the session in a clean state, not a half-cleared one. Fix: 1 line — add `this.clearRefs()` next to `this.activeFrame = null` inside the if-branch. Test plan: - [x] New regression test: 4/4 pass - refs cleared when getActiveFrameOrPage detects detached iframe - refs preserved when active frame is still attached (no regression) - refs preserved when no frame set (page-level path untouched) - matches onMainFrameNavigated symmetry — both paths reach the same clean end state - [x] `bun run build` clean 🤖 Generated with [Claude Code](https://claude.com/claude-code) * fix(codex): resolve python for JSON parser * fix: add fail-fast probe for base branch in ship step 12 * fix(plan-devex-review): remove contradictory plan-mode handshake * fix(design): honor Retry-After header in variants 429 handler Closes #1244. The 429 handler in `generateVariant` discarded the `Retry-After` response header and fell straight through to a local exponential schedule (2s/4s/8s). In image-generation batches, that burns retry attempts inside the provider's cooldown window and the request never recovers. Now we parse `Retry-After` per RFC 7231 — both delta-seconds (`Retry-After: 5`) and HTTP-date (`Retry-After: Fri, 31 Dec 1999 23:59:59 GMT`). Honored waits are capped at 60s to bound stalls from hostile or buggy headers. Delta-seconds are validated as digits-only (rejects `2abc`). When `Retry-After` is honored (including 0 / past-date "retry now"), the next iteration's leading exponential sleep is skipped so we don't double-wait. Invalid or missing headers fall through to the existing exponential schedule unchanged. Behavior matrix: | Header | Behavior | |---------------------------------|-------------------------------------------| | Retry-After: 5 | wait 5s, skip leading on next attempt | | Retry-After: 999999 | capped to 60s, skip leading | | Retry-After: 2abc | invalid, fall through to exponential | | Retry-After: 0 | wait 0, skip leading (retry immediately) | | Retry-After: <past HTTP-date> | wait 0, skip leading | | Retry-After: <future date> | wait diff capped at 60s, skip leading | | no header | fall through to existing exponential | `generateVariant` now accepts an optional `fetchFn` parameter (defaults to `globalThis.fetch`) so tests can inject a stub. Production call sites are unchanged. Tests cover the five behavior buckets above, asserting both the 1st-to-2nd call timing gap and call counts. All five pass in ~8s. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(docs): correct per-skill symlink removal snippet in README uninstall Closes #1130. The manual-uninstall fallback in `## Uninstall` → `### Option 2` used `find ~/.claude/skills -maxdepth 1 -type l`, which finds nothing on real installs. Each `~/.claude/skills/<name>/` is a real directory, and only `<name>/SKILL.md` inside it is a symlink into `gstack/`. The find never matched, so the snippet silently removed nothing. Replace with a directory walk that inspects each `<name>/SKILL.md`: find ~/.claude/skills -mindepth 1 -maxdepth 1 -type d ! -name gstack → check $dir/SKILL.md is a symlink → readlink it → if target is gstack/* or */gstack/*: rm -f the link, rmdir the dir (only if empty — preserves any user-added files) Excludes the top-level `gstack/` dir from the walk; that's removed by step 3 of the same uninstall block. `bin/gstack-uninstall` (the script-mode path) already handles the layout correctly via its own walk; only this manual fallback needed updating. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix: reject partial browse client env integers * fix(gemini-adapter): detect new ~/.gemini/oauth_creds.json auth path gemini-cli >=0.30 stores OAuth credentials at ~/.gemini/oauth_creds.json instead of the legacy ~/.config/gemini/ directory. The benchmark adapter's availability check now succeeds for users on recent gemini-cli releases who have authenticated via interactive login. Both paths are accepted so users on older versions still work. * fix(browser): add --no-sandbox for root user on Linux/WSL2 Chromium's sandbox can't initialize when running as root on Linux, causing an immediate exit. Extend the existing CI/CONTAINER check to also cover this case, keeping the Windows-safe `typeof getuid` guard. * security: pass cwd to git via execFileSync, not interpolation through /bin/sh `bin/gstack-memory-ingest.ts:632-643` ran `execSync(\`git -C ${JSON.stringify(cwd)} remote get-url origin 2>/dev/null\`, ...)`. JSON.stringify escapes `"` and `\` but not `$` or backticks, so a `cwd` of `"$(touch /tmp/marker)"` survived JSON quoting and detonated under /bin/sh's command-substitution-inside-double-quotes. `cwd` originates from transcript JSONL records under `~/.claude/projects/<encoded-cwd>/<uuid>.jsonl` and `~/.codex/sessions/YYYY/MM/DD/rollout-*.jsonl`. The walker grabs the first `.cwd` it sees per session. That's an untrusted surface in the gstack threat model — the L1-L6 sidebar security stack exists exactly because agent transcripts can carry attacker-influenced text. Two pivots above the local same-uid bar: (a) prompt-injection appending `cwd="$(...)"` to the active session log turns the next /sync-gbrain run into RCE under the user's uid; (b) cross-machine transcript share (a colleague's `.claude/projects` snippet untar'd into HOME, a documented gbrain dogfooding shape) → RCE on first sync. Fix swaps the one execSync for `execFileSync("git", ["-C", cwd, "remote", "get-url", "origin"], ...)`. No shell, argv passed directly to git. The same module already uses execFileSync for `gbrainAvailable()` (line 762 pre-patch) and `gbrainPutPage()` (line 816 pre-patch) — this single execSync was the outlier. Test: `gstack-memory-ingest security: untrusted cwd cannot trigger shell substitution` plants a Claude-Code-shaped JSONL with cwd=`$(touch <marker>)` and asserts the marker file is not created after `--incremental --quiet`. Negative control: with the patch reverted, the test fails (marker created); with the patch applied, it passes (18/18 in test/gstack-memory-ingest.test.ts). * security: gate domain-skill auto-promote on classifier_score > 0 `browse/src/domain-skill-commands.ts:140` (handleSave) writes `classifier_score: 0` with the comment "L4 deferred to load-time / sidebar-agent fills this in on first prompt-injection load." But CLAUDE.md "Sidebar architecture" documents that sidebar-agent.ts was ripped, and grep for recordSkillUse + classifierFlagged callers across browse/src/ returns zero hits outside the module under test. Net effect: every quarantined skill that survives three benign uses without flag (`recordSkillUse(... , classifierFlagged: false)` x3) auto-promotes to `active` and lands in prompt context wrapped as UNTRUSTED on every subsequent visit to that host. The L4 score that was supposed to gate the promotion was never written — the production save path puts 0 on disk and nothing later updates it. Threat model: a domain-skill body authored by an agent under the influence of a poisoned page (the new `gstackInjectToTerminal` PTY path runs no L1-L3 either) would lose its auto-promote barrier after three uses. The exploit isn't single-step but the bar is exactly N=3 prompt-injection-shaped uses on a hostile page, which is well within reach. Fix adds a single condition to the auto-promote gate in `recordSkillUse`: if (state === 'quarantined' && useCount >= PROMOTE_THRESHOLD && flagCount === 0 && current.classifier_score > 0) { state = 'active'; } `classifier_score` is set once at writeSkill and never updated. Production saves it as 0 (handleSave), so the gate stays closed; existing tests that explicitly pass `classifierScore: 0.1` still auto-promote (the auto-promote path is preserved for the day L4 is rewired). Manual promotion via `domain-skill promote-to-global` is unaffected (it goes through `promoteToGlobal` which has its own state-machine guard at line 337+). Test: new regression case `does NOT auto-promote when classifier_score is 0 (production handleSave shape)` plants a skill with classifierScore=0 (matches domain-skill-commands.ts:140), runs three uses without flag, asserts the skill stays quarantined and readSkill returns null. Negative control: revert the patch, the test fails with `Received: "active"`. With the patch: 15/15 pass. * fix(ship): port #1302 SKILL.md edits to .tmpl + resolver source PR #1302 added Verification Mode + UNVERIFIABLE classification + per-item confirmation gate to ship/SKILL.md, but only the generated SKILL.md was edited — not the .tmpl source or scripts/resolvers/review.ts. The next `bun run gen:skill-docs` run would have wiped the changes. Port the same content into the resolver and .tmpl so regeneration produces the intended output. * ci(windows): extend free-tests lane to cover icacls + Bun.which resolvers from fix-wave PRs Closes #1306/#1307/#1308 validation gap. The four newly-added test files already have process.platform guards so they run safely on both POSIX and Windows lanes — only platform-relevant assertions execute on each. Tests added to the windows-latest lane: - browse/test/file-permissions.test.ts (#1308 icacls + writeSecureFile) - browse/test/security.test.ts (#1306 bash.exe wrap pure-function path) - make-pdf/test/browseClient.test.ts (#1307 Bun.which browse resolver) - make-pdf/test/pdftotext.test.ts (#1307 Bun.which pdftotext resolver) * test(codex): live flag-semantics smoke for codex exec resume Closes #1270's regex-only test gap. PR #1270 asserted that codex/SKILL.md's `codex exec resume` invocation drops -C/-s and uses sandbox_mode config. That regex catches the skill template regressing, but not codex CLI itself flipping flag semantics again. This test probes `codex exec resume --help` and asserts the surface gstack relies on: -c/sandbox_mode is accepted, top-level -C is absent. Skips silently when codex isn't on PATH, so dev machines without codex installed never see it fail. * chore: regen SKILL.md after fix wave One regen commit at the end of the merge wave per the plan. plan-devex-review loses the contradictory plan-mode handshake (#1333). review/SKILL.md picks up the Verification Mode + UNVERIFIABLE classification additions that #1302 authored against ship/SKILL.md (same resolver shared between ship and review modes). * fix(server.ts): keep fs.writeFileSync for state-file writes #1308's writeSecureFile wrapper added Windows icacls hardening for the 4 state-file write sites in server.ts, but #1310's regression test grep's for fs.writeFileSync(tmpStatePath()) calls. The two changes are technically compatible only if the test relaxes — keeping the test strict (the safer choice for catching regressions on the cold-start race) means the 4 state- file sites stay on fs.writeFileSync(..., { mode: 0o600 }). POSIX 0o600 hardening is preserved on those 4 sites. Windows icacls hardening still applies to all the other writeSecureFile call sites #1308 added (auth.json, mkdirSecure, etc.). Also refreshes golden baselines after #1302 / port + minor wording tweak in scripts/resolvers/review.ts to keep gen-skill-docs.test.ts assertion 'Cite the specific file' satisfied. * v1.30.0.0: fix wave — 21 community PRs + 2 closing fixes for Windows + codex CI gaps Headline release. Browse stops dropping console logs, cold-start race fixed, codex resume works without python3, Windows hardening (icacls + Bun.which + bash.exe wrap), ship gate gets VAS-449 remediation, two closing fixes that put icacls/Bun.which/codex flag semantics under CI. * test(domain-skills): cover #1369 classifier_score=0 quarantine + score>0 promote path The pre-existing T6 test seeded skills via writeSkill (which defaults classifier_score to 0 until L4 is rewired) and then expected 3 uses to auto-promote. PR #1369 added `current.classifier_score > 0` to the gate specifically to block that path — a quarantined skill written under the influence of a poisoned page would otherwise auto-promote after three benign uses. Updated test asserts both halves of the new contract: - classifier_score=0 + 3 uses → stays quarantined (the security guarantee) - classifier_score>0 + 3 more uses → promotes to active (unblock path) Catches both regressions: the gate going away (would re-allow the bypass) and the unblock path breaking (would silently quarantine all skills forever once L4 is rewired). --------- Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: orbisai0security <mediratta01.pally@gmail.com> Co-authored-by: Bryce Alan <brycealan.eth@gmail.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: Terry Carson YM <cym3118288@gmail.com> Co-authored-by: Vasko Ckorovski <vckorovski@gmail.com> Co-authored-by: Samuel Carson <samuel.carson@gmail.com> Co-authored-by: Yashwant Kotipalli <yashwant7kotipalli@gmail.com> Co-authored-by: Jasper Chen <jasperchen925@gmail.com> Co-authored-by: Stefan Neamtu <stefan.neamtu@gmail.com> Co-authored-by: 陈家名 <chenjiaming@kezaihui.com> Co-authored-by: Abigail Atheryon <abi@atheryon.ai> Co-authored-by: Furkan Köykıran <furkankoykiran@gmail.com> Co-authored-by: gus <gustavoraularagon@gmail.com>
382 lines
13 KiB
TypeScript
382 lines
13 KiB
TypeScript
/**
|
|
* Typed shell-out wrapper for the browse CLI.
|
|
*
|
|
* Every browse call goes through this file. Reasons:
|
|
* - One place to do binary resolution.
|
|
* - One place to enforce the --from-file convention for large payloads
|
|
* (Windows argv cap is 8191 chars; 200KB HTML dies without this).
|
|
* - One place that maps non-zero exit codes to typed errors.
|
|
*
|
|
* Binary resolution order (Codex round 2 #4, v1.24-aligned):
|
|
* 1. $GSTACK_BROWSE_BIN env override (preferred, matches v1.24 GSTACK_*_BIN pattern)
|
|
* 2. $BROWSE_BIN env override (back-compat alias)
|
|
* 3. sibling dir: dirname(argv[0])/../browse/dist/browse[.exe]
|
|
* 4. ~/.claude/skills/gstack/browse/dist/browse[.exe]
|
|
* 5. PATH lookup via Bun.which('browse') — handles Windows PATHEXT natively
|
|
* 6. error with setup hint
|
|
*
|
|
* Windows quirks:
|
|
* - bun build --compile --outfile X emits X.exe on win32, so candidate paths
|
|
* need a .exe probe pass (fs.accessSync(X_OK) degrades to existence-checking
|
|
* on Windows per Node docs, so the bare path silently misses the .exe file).
|
|
* - `which` only exists in Git Bash; Bun.which() handles cmd.exe / PowerShell
|
|
* natively via PATHEXT semantics.
|
|
*/
|
|
|
|
import { execFileSync } from "node:child_process";
|
|
import * as fs from "node:fs";
|
|
import * as os from "node:os";
|
|
import * as path from "node:path";
|
|
import * as crypto from "node:crypto";
|
|
|
|
import { BrowseClientError } from "./types";
|
|
|
|
export interface LoadHtmlOptions {
|
|
html: string; // raw HTML string
|
|
waitUntil?: "load" | "domcontentloaded" | "networkidle";
|
|
tabId: number;
|
|
}
|
|
|
|
export interface PdfOptions {
|
|
output: string;
|
|
tabId: number;
|
|
format?: string;
|
|
width?: string;
|
|
height?: string;
|
|
marginTop?: string;
|
|
marginRight?: string;
|
|
marginBottom?: string;
|
|
marginLeft?: string;
|
|
headerTemplate?: string;
|
|
footerTemplate?: string;
|
|
pageNumbers?: boolean;
|
|
tagged?: boolean;
|
|
outline?: boolean;
|
|
printBackground?: boolean;
|
|
preferCSSPageSize?: boolean;
|
|
toc?: boolean;
|
|
}
|
|
|
|
export interface JsOptions {
|
|
tabId: number;
|
|
expression: string; // JS expression to evaluate
|
|
}
|
|
|
|
/**
|
|
* Resolve an absolute or PATH-resolvable command via Bun.which-style semantics,
|
|
* with a Windows .exe/.cmd/.bat extension probe for absolute paths. Mirrors
|
|
* the v1.24 claude-bin.ts override-resolution shape.
|
|
*
|
|
* Returns null if nothing resolves; callers degrade with a typed error rather
|
|
* than throwing here.
|
|
*/
|
|
function resolveOverride(value: string | undefined, env: NodeJS.ProcessEnv): string | null {
|
|
if (!value?.trim()) return null;
|
|
const trimmed = value.trim().replace(/^"(.*)"$/, '$1');
|
|
if (path.isAbsolute(trimmed)) return findExecutable(trimmed);
|
|
const PATH = env.PATH ?? env.Path ?? '';
|
|
return Bun.which(trimmed, { PATH }) ?? null;
|
|
}
|
|
|
|
/**
|
|
* Probe a base path for executability, honoring Windows extension suffixes.
|
|
*
|
|
* On POSIX, isExecutable(base) is the only check that matters. On Windows,
|
|
* fs.accessSync(p, X_OK) degrades to an existence check — so a bare-path probe
|
|
* misses bun-compiled binaries (which land at base.exe). After the bare probe
|
|
* fails on win32, try .exe / .cmd / .bat. Linux/macOS behavior is unchanged.
|
|
*/
|
|
export function findExecutable(base: string): string | null {
|
|
if (isExecutable(base)) return base;
|
|
if (process.platform === "win32") {
|
|
for (const ext of [".exe", ".cmd", ".bat"]) {
|
|
const withExt = base + ext;
|
|
if (isExecutable(withExt)) return withExt;
|
|
}
|
|
}
|
|
return null;
|
|
}
|
|
|
|
/**
|
|
* Locate the browse binary. Throws a BrowseClientError with a
|
|
* canonical setup message if not found. See header for resolution order.
|
|
*/
|
|
export function resolveBrowseBin(env: NodeJS.ProcessEnv = process.env): string {
|
|
// 1 + 2: env overrides (GSTACK_BROWSE_BIN preferred, BROWSE_BIN back-compat).
|
|
const overrideRaw = env.GSTACK_BROWSE_BIN ?? env.BROWSE_BIN;
|
|
const override = resolveOverride(overrideRaw, env);
|
|
if (override) return override;
|
|
|
|
// 3: sibling — make-pdf and browse co-located in dist/.
|
|
const selfDir = path.dirname(process.argv[0]);
|
|
const siblingCandidates = [
|
|
path.resolve(selfDir, "../browse/dist/browse"),
|
|
path.resolve(selfDir, "../../browse/dist/browse"),
|
|
path.resolve(selfDir, "../browse"),
|
|
];
|
|
for (const candidate of siblingCandidates) {
|
|
const found = findExecutable(candidate);
|
|
if (found) return found;
|
|
}
|
|
|
|
// 4: global install.
|
|
const home = os.homedir();
|
|
const globalPath = path.join(home, ".claude/skills/gstack/browse/dist/browse");
|
|
const globalFound = findExecutable(globalPath);
|
|
if (globalFound) return globalFound;
|
|
|
|
// 5: PATH lookup via Bun.which — handles Windows PATHEXT natively (no `which`
|
|
// dependency on cmd.exe / PowerShell, no `where`-vs-`which` branch).
|
|
const PATH = env.PATH ?? env.Path ?? '';
|
|
const onPath = Bun.which('browse', { PATH });
|
|
if (onPath) return onPath;
|
|
|
|
throw new BrowseClientError(
|
|
/* exitCode */ 127,
|
|
"resolve",
|
|
[
|
|
"browse binary not found.",
|
|
"",
|
|
"make-pdf needs browse (the gstack Chromium daemon) to render PDFs.",
|
|
"Tried:",
|
|
` - $GSTACK_BROWSE_BIN (${env.GSTACK_BROWSE_BIN || "unset"})`,
|
|
` - $BROWSE_BIN (${env.BROWSE_BIN || "unset"})`,
|
|
` - sibling: ${siblingCandidates.join(", ")}`,
|
|
` - global: ${globalPath}`,
|
|
" - PATH: `browse`",
|
|
"",
|
|
"To fix: run gstack setup from the gstack repo:",
|
|
" cd ~/.claude/skills/gstack && ./setup",
|
|
"",
|
|
"Or set GSTACK_BROWSE_BIN explicitly:",
|
|
process.platform === "win32"
|
|
? ' setx GSTACK_BROWSE_BIN "C:\\path\\to\\browse.exe"'
|
|
: " export GSTACK_BROWSE_BIN=/path/to/browse",
|
|
].join("\n"),
|
|
);
|
|
}
|
|
|
|
function isExecutable(p: string): boolean {
|
|
try {
|
|
fs.accessSync(p, fs.constants.X_OK);
|
|
return true;
|
|
} catch {
|
|
return false;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Run a browse command. Returns stdout on success.
|
|
* Throws BrowseClientError on non-zero exit.
|
|
*/
|
|
function runBrowse(args: string[]): string {
|
|
const bin = resolveBrowseBin();
|
|
try {
|
|
return execFileSync(bin, args, {
|
|
encoding: "utf8",
|
|
maxBuffer: 16 * 1024 * 1024, // 16MB; tab content can be large
|
|
stdio: ["ignore", "pipe", "pipe"],
|
|
});
|
|
} catch (err: any) {
|
|
const exitCode = typeof err.status === "number" ? err.status : 1;
|
|
const stderr = typeof err.stderr === "string"
|
|
? err.stderr
|
|
: (err.stderr?.toString() ?? "");
|
|
throw new BrowseClientError(exitCode, args[0] || "unknown", stderr);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Write a payload to a tmp file and return the path. Used for any payload
|
|
* >4KB to avoid Windows argv limits (Codex round 2 #3).
|
|
*
|
|
* Path must be under the browse safe-dirs allowlist (/tmp or cwd on
|
|
* non-Windows; os.tmpdir on Windows). v1.6.0.0 tightened --from-file
|
|
* validation to close a CLI/API parity gap (PR #1103), so os.tmpdir()
|
|
* on macOS (/var/folders/...) now fails validateReadPath. Use the same
|
|
* TEMP_DIR convention as browse/src/platform.ts.
|
|
*/
|
|
const PAYLOAD_TMP_DIR = process.platform === "win32" ? os.tmpdir() : "/tmp";
|
|
|
|
function writePayloadFile(payload: Record<string, unknown>): string {
|
|
const hash = crypto.createHash("sha256")
|
|
.update(JSON.stringify(payload))
|
|
.digest("hex")
|
|
.slice(0, 12);
|
|
const tmpPath = path.join(PAYLOAD_TMP_DIR, `make-pdf-browse-${process.pid}-${hash}.json`);
|
|
fs.writeFileSync(tmpPath, JSON.stringify(payload), "utf8");
|
|
return tmpPath;
|
|
}
|
|
|
|
function cleanupPayloadFile(p: string): void {
|
|
try { fs.unlinkSync(p); } catch { /* best-effort */ }
|
|
}
|
|
|
|
// ─── Public API ─────────────────────────────────────────────────
|
|
|
|
/**
|
|
* Open a new tab. Returns the tabId.
|
|
* Requires `$B newtab --json` to be available (added in the browse flag
|
|
* extension for this feature). If --json isn't supported yet, the fallback
|
|
* parses "Opened tab N" from stdout.
|
|
*/
|
|
export function newtab(url?: string): number {
|
|
const args = ["newtab"];
|
|
if (url) args.push(url);
|
|
// Try --json first (preferred path for programmatic use)
|
|
try {
|
|
const out = runBrowse([...args, "--json"]);
|
|
const parsed = JSON.parse(out);
|
|
if (typeof parsed.tabId === "number") return parsed.tabId;
|
|
} catch {
|
|
// Fall back to stdout-string parsing. Brittle, but works on older browse builds.
|
|
}
|
|
const out = runBrowse(args);
|
|
const m = out.match(/tab\s+(\d+)/i);
|
|
if (!m) throw new BrowseClientError(1, "newtab", `could not parse tab id from: ${out}`);
|
|
return parseInt(m[1], 10);
|
|
}
|
|
|
|
/**
|
|
* Close a tab (by id or the active tab).
|
|
*/
|
|
export function closetab(tabId?: number): void {
|
|
const args = ["closetab"];
|
|
if (tabId !== undefined) args.push(String(tabId));
|
|
runBrowse(args);
|
|
}
|
|
|
|
/**
|
|
* Load raw HTML into a specific tab.
|
|
* Uses --from-file for any payload >4KB (Codex round 2 #3).
|
|
*/
|
|
export function loadHtml(opts: LoadHtmlOptions): void {
|
|
// Always use --from-file to dodge argv limits. The HTML is almost always >4KB.
|
|
const payload = {
|
|
html: opts.html,
|
|
waitUntil: opts.waitUntil ?? "domcontentloaded",
|
|
};
|
|
const payloadFile = writePayloadFile(payload);
|
|
try {
|
|
runBrowse([
|
|
"load-html",
|
|
"--from-file", payloadFile,
|
|
"--tab-id", String(opts.tabId),
|
|
]);
|
|
} finally {
|
|
cleanupPayloadFile(payloadFile);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Evaluate a JS expression in a tab. Returns the serialized result as string.
|
|
*/
|
|
export function js(opts: JsOptions): string {
|
|
return runBrowse([
|
|
"js",
|
|
opts.expression,
|
|
"--tab-id", String(opts.tabId),
|
|
]).trim();
|
|
}
|
|
|
|
/**
|
|
* Poll a boolean JS expression until it evaluates to true, or timeout.
|
|
* Returns true if it succeeded, false if timed out.
|
|
*/
|
|
export function waitForExpression(opts: {
|
|
expression: string;
|
|
tabId: number;
|
|
timeoutMs: number;
|
|
pollIntervalMs?: number;
|
|
}): boolean {
|
|
const poll = opts.pollIntervalMs ?? 200;
|
|
const deadline = Date.now() + opts.timeoutMs;
|
|
while (Date.now() < deadline) {
|
|
try {
|
|
const result = js({ expression: opts.expression, tabId: opts.tabId });
|
|
if (result === "true") return true;
|
|
} catch {
|
|
// Tab may still be loading; keep polling
|
|
}
|
|
const wait = Math.min(poll, Math.max(0, deadline - Date.now()));
|
|
if (wait <= 0) break;
|
|
// Synchronous sleep is fine — this only runs once per PDF render
|
|
const end = Date.now() + wait;
|
|
while (Date.now() < end) { /* busy wait */ }
|
|
}
|
|
return false;
|
|
}
|
|
|
|
/**
|
|
* Generate a PDF from the given tab. Uses --from-file when header/footer
|
|
* templates are present (they can be HTML strings of arbitrary size).
|
|
*/
|
|
export function pdf(opts: PdfOptions): void {
|
|
// If any large payload is present, send via --from-file
|
|
const hasLargePayload =
|
|
(opts.headerTemplate && opts.headerTemplate.length > 1024) ||
|
|
(opts.footerTemplate && opts.footerTemplate.length > 1024);
|
|
|
|
if (hasLargePayload) {
|
|
const payloadFile = writePayloadFile({
|
|
output: opts.output,
|
|
tabId: opts.tabId,
|
|
...optionsToPdfFlags(opts),
|
|
});
|
|
try {
|
|
runBrowse(["pdf", "--from-file", payloadFile]);
|
|
} finally {
|
|
cleanupPayloadFile(payloadFile);
|
|
}
|
|
return;
|
|
}
|
|
|
|
// Small payload: pass flags via argv
|
|
const args = ["pdf", opts.output, "--tab-id", String(opts.tabId)];
|
|
pushFlagsFromOptions(args, opts);
|
|
runBrowse(args);
|
|
}
|
|
|
|
function optionsToPdfFlags(opts: PdfOptions): Record<string, unknown> {
|
|
// Shape mirrors what the browse `pdf` case expects when reading --from-file
|
|
const out: Record<string, unknown> = {};
|
|
if (opts.format) out.format = opts.format;
|
|
if (opts.width) out.width = opts.width;
|
|
if (opts.height) out.height = opts.height;
|
|
if (opts.marginTop) out.marginTop = opts.marginTop;
|
|
if (opts.marginRight) out.marginRight = opts.marginRight;
|
|
if (opts.marginBottom) out.marginBottom = opts.marginBottom;
|
|
if (opts.marginLeft) out.marginLeft = opts.marginLeft;
|
|
if (opts.headerTemplate !== undefined) out.headerTemplate = opts.headerTemplate;
|
|
if (opts.footerTemplate !== undefined) out.footerTemplate = opts.footerTemplate;
|
|
if (opts.pageNumbers !== undefined) out.pageNumbers = opts.pageNumbers;
|
|
if (opts.tagged !== undefined) out.tagged = opts.tagged;
|
|
if (opts.outline !== undefined) out.outline = opts.outline;
|
|
if (opts.printBackground !== undefined) out.printBackground = opts.printBackground;
|
|
if (opts.preferCSSPageSize !== undefined) out.preferCSSPageSize = opts.preferCSSPageSize;
|
|
if (opts.toc !== undefined) out.toc = opts.toc;
|
|
return out;
|
|
}
|
|
|
|
function pushFlagsFromOptions(args: string[], opts: PdfOptions): void {
|
|
if (opts.format) { args.push("--format", opts.format); }
|
|
if (opts.width) { args.push("--width", opts.width); }
|
|
if (opts.height) { args.push("--height", opts.height); }
|
|
if (opts.marginTop) { args.push("--margin-top", opts.marginTop); }
|
|
if (opts.marginRight) { args.push("--margin-right", opts.marginRight); }
|
|
if (opts.marginBottom) { args.push("--margin-bottom", opts.marginBottom); }
|
|
if (opts.marginLeft) { args.push("--margin-left", opts.marginLeft); }
|
|
if (opts.headerTemplate !== undefined) {
|
|
args.push("--header-template", opts.headerTemplate);
|
|
}
|
|
if (opts.footerTemplate !== undefined) {
|
|
args.push("--footer-template", opts.footerTemplate);
|
|
}
|
|
if (opts.pageNumbers === true) args.push("--page-numbers");
|
|
if (opts.tagged === true) args.push("--tagged");
|
|
if (opts.outline === true) args.push("--outline");
|
|
if (opts.printBackground === true) args.push("--print-background");
|
|
if (opts.preferCSSPageSize === true) args.push("--prefer-css-page-size");
|
|
if (opts.toc === true) args.push("--toc");
|
|
}
|