mirror of
https://github.com/garrytan/gstack.git
synced 2026-06-02 00:01:37 +02:00
7ca04d8ef0
* fix(gstack-paths): guard CLAUDE_PLUGIN_DATA against cross-plugin contamination (#1569) gstack-paths previously trusted CLAUDE_PLUGIN_DATA as a fallback for GSTACK_STATE_ROOT whenever GSTACK_HOME was unset. When another plugin (e.g. Codex) persists its own CLAUDE_PLUGIN_DATA into the session env via CLAUDE_ENV_FILE, gstack picked it up and wrote checkpoints, analytics, and learnings into that plugin's directory. Anyone with the Codex plugin installed alongside gstack hit this silently. Fix: guard the CLAUDE_PLUGIN_DATA branch so it only fires when CLAUDE_PLUGIN_ROOT confirms we're running as the gstack plugin (path contains "gstack"). Skill installs fall through to \$HOME/.gstack. Contributed by @ElliotDrel via #1570. Closes #1569. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(gbrain-sync): sourceLocalPath handles wrapped {sources:[...]} shape from gbrain v0.20+ gbrain v0.20+ changed `gbrain sources list --json` to return {sources: [...]} instead of a flat array. sourceLocalPath crashed upstream with `list.find is not a function` on every /sync-gbrain invocation against modern gbrain. Accept both shapes for forward/backward compat, matching probeSource/sourcePageCount in lib/gbrain-sources.ts. Contributed by @jakehann11 via #1571. Closes #1567. Supersedes #1564 (@tonyjzhou, same fix, different shape — credit retained). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(brain-context-load): probe gbrain via execFile, not shell builtin (#1559) gbrainAvailable() used `execFileSync("command", ["-v", "gbrain"])`, which fails in any environment where the `command` builtin isn't on the spawned process's PATH (most non-interactive shells). The probe then reported gbrain as missing even when it was installed, and context-load silently skipped vector/list queries. Fix: probe `gbrain --version` directly with a 500ms timeout (matching the rest of the file's MCP_TIMEOUT_MS). Same semantics, works everywhere execFile works. Contributed by @jbetala7 via #1560. Closes #1559. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(gbrain-doctor): pin schema_version:2 doctor parse path (#1418) Adds an exec-path regression test that runs a fake gbrain shim emitting the v0.25+ doctor JSON shape (schema_version: 2, status: "warnings", exit 1 for health_score < 100, no top-level `engine` field). Confirms freshDetectEngineTier recovers stdout from the non-zero exit and falls back to GBRAIN_HOME/config.json for the engine label. The pre-existing test for #1415 only stripped gbrain from PATH; this test exercises the actual doctor parse path, closing the gap that codex's plan review flagged. Also documents the schema_version separation in lib/gbrain-local-status.ts: the local CacheEntry stays at version 1, distinct from the doctor-output schema_version which we accept across versions in gstack-memory-helpers. Closes #1418 (credit @mvanhorn for surfacing the doctor + schema_v2 collapse). The fix landed pre-emptively in v1.29.x; this commit pins it with a stronger test. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(memory-ingest): pin put_page regression + scrub stale name from --help and comments (#1346) #1346 reported that gstack-memory-ingest still called the renamed gbrain put_page subcommand on gbrain v0.18+. The actual code migrated to `gbrain put` and later to batch `gbrain import <dir>` before this report landed — only documentation lag remained. This commit: - Updates the --help string ("Skip gbrain put calls (still updates state file)") so user-facing docs match the shipped subcommand - Updates two inline comments that still referenced the old name - Adds test/memory-ingest-no-put_page.test.ts: a regression pin that strips comments from bin/gstack-memory-ingest.ts and fails the build if "put_page" appears in any active code or string literal, plus a sanity check that the file still calls a supported gbrain page-write verb (put or import) Closes #1346. Reporter @kylma-code surfaced the doc lag; the original code migration credit is on the v1.27.x wave. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(resolvers): rewrite all gbrain put_page instructions to canonical put <slug> scripts/resolvers/gbrain.ts emitted user-facing copy-paste instructions using the renamed `gbrain put_page` subcommand across 10 skills (office-hours, investigate, plan-ceo-review, retro, plan-eng-review, ship, cso, design-consultation, fallback, entity-stub). Every gstack user copying those snippets hit "unknown command: put_page" on gbrain v0.18+. This commit: - Rewrites all 10 instruction templates to use `gbrain put <slug> --content "$(cat <<EOF...EOF)"` with title/tags moved into YAML frontmatter inside --content, matching the v0.18+ subcommand shape - Updates README.md and USING_GBRAIN_WITH_GSTACK.md "common commands" table to reference `gbrain put` and `gbrain get` - Adds test/resolvers-gbrain-put-rewrite.test.ts pinning two invariants: (a) resolver source ships only canonical instructions, (b) every tracked SKILL.md file is free of `gbrain put_page` CHANGELOG entries are deliberately left untouched (historical record). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(build): extract package.json build to scripts/build.sh for Windows Bun compat (#1538, #1537, #1530, #1457, #1561) Bun's Windows shell parser rejects multiple constructs the inline package.json build chain used: brace groups `{ cmd; }`, subshells with redirection `( git ... ) > path/.version`, and (in Bun 1.3.x) subshells near redirections in general. Every Windows install + every auto-upgrade since v1.34.2.0 has failed on `bun run build`. Extracts the build chain to scripts/build.sh and the .version writes to scripts/write-version-files.sh. POSIX-portable, no Bun shell parsing involved. Also adds Windows-specific bun.exe handling for non-ASCII PATHs (a separate Windows footgun where Bun's --compile fails when the binary lives under a path with non-ASCII chars). Updates test/build-script-shell-compat.test.ts to assert the new shape: no subshells with redirections anywhere in the build chain, and build delegates to scripts/build.sh which delegates .version writes. Contributed by @Charlie-El via #1544. Supersedes #1531 (@scarson, fixed in build helper), #1480 (@mikepsinn, partial overlap), #1460 (@realcarsonterry, brace-group fix subsumed) — credit retained. Closes #1538, #1537, #1530, #1457, #1561. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(windows): .exe glob in .gitignore + .exe extension resolution in find-browse (#1554) bun build --compile on Windows appends .exe to the output filename, producing browse.exe instead of browse. find-browse's existsSync probe only checked the bare path and returned null on Windows even when the binary was correctly built. .gitignore similarly only excluded the bare bin/gstack-global-discover path, leaving the .exe variant tracked. This commit: - .gitignore: changes `bin/gstack-global-discover` → `bin/gstack-global-discover*` so the Windows .exe variant is ignored - browse/src/find-browse.ts: adds isExecutable + findExecutable helpers that fall back to .exe/.cmd/.bat probing on Windows, mirroring the same helper already in make-pdf/src/browseClient.ts and pdftotext.ts Contributed by @Mike-E-Log via #1554. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * ci(windows): add fresh-install E2E gate that runs bun run build on windows-latest Adds .github/workflows/windows-setup-e2e.yml as the gate that catches Bun shell-parser regressions in the build chain before they reach users. Triggers on PRs touching package.json, scripts/build.sh, scripts/write-version-files.sh, setup, browse cli/find-browse, or gstack-paths. What it verifies: 1. bun run build completes on Windows (the previously-broken path that #1538/#1537/#1530/#1457/#1561 reported) 2. All compiled binaries land on disk (browse.exe, find-browse.exe, design.exe, gstack-global-discover.exe) 3. find-browse resolves to the .exe variant on Windows (regression gate for #1554) 4. gstack-paths returns non-empty GSTACK_STATE_ROOT/PLAN_ROOT/TMP_ROOT on Windows (regression gate for #1570) Complements the existing windows-free-tests.yml (curated unit subset); this new workflow exercises the install path itself. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(codex): move diff scope into prompt instead of --base (Codex CLI 0.130+ argv conflict) (#1209) Codex CLI ≥ 0.130.0 rejects passing a custom prompt and --base together (mutually exclusive at argv level). Every /codex review, /review, and /ship structured Codex review call ended with an argv error before the model ran. Fix: scope the diff in prompt text using "Run git diff origin/<base>...HEAD 2>/dev/null || git diff <base>...HEAD" instead of `--base <base>`. Preserves the filesystem boundary instruction across all invocations and keeps Codex's review prompt tuning. Touches: - codex/SKILL.md.tmpl + regenerated codex/SKILL.md - scripts/resolvers/review.ts + regenerated review/SKILL.md, ship/SKILL.md - test/gen-skill-docs.test.ts: new regression that fails if any of the five known files still contain the prompt+--base shape - test/skill-validation.test.ts: corresponding negative + positive pin on the rendered SKILL.md files Contributed by @jbetala7 via #1209. Closes #1479. Supersedes #1527 (@mvanhorn — same intent, different patch shape, CONFLICTING) and #1449 (@Gujiassh — broader refactor, CONFLICTING). Credit retained in CHANGELOG. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(review): diff from git merge-base, not git diff origin/<base> (#1492) git diff origin/<base> shows everything since the common ancestor in both directions — it includes commits that landed on origin/<base> after this branch was created as deletions. That made /review and /ship's pre-landing structured review report inflated diff totals and flagged "removed" code that was actually still present in the working tree. Fix: compute DIFF_BASE via git merge-base origin/<base> HEAD and diff the working tree against that point. Same coverage of uncommitted edits, no phantom deletions from out-of-order base advancement. Applies to /review's Step 1 (diff existence check), Step 3 (get the diff), the build-on-intent scope-creep check, the structured review DIFF_INS/DIFF_DEL stats, and the Claude adversarial subagent prompt. Same change flows into ship/SKILL.md via the shared resolver. Touches: - review/SKILL.md.tmpl + regenerated review/SKILL.md, ship/SKILL.md - scripts/resolvers/review.ts - scripts/resolvers/review-army.ts Contributed by @mvanhorn via #1492. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(codex): pin filesystem-boundary preservation across all codex review surfaces (#1503, #1522) #1503 reported that the bare codex review --base path stripped the filesystem boundary instruction, letting Codex spend tokens reading .claude/skills/ and agents/. #1522 proposed adding a skill-path detector that switched to the custom-instructions route when the diff touched skill files. After C10 (#1209) restructured codex review to always carry the boundary in the prompt (the prompt+--base argv conflict forced the restructure), the skill-path detector becomes redundant — every default call already preserves the boundary. This commit pins the post-#1209 invariant with a test that fails the build if any future refactor strips the boundary from codex/SKILL.md, review/SKILL.md, or ship/SKILL.md. Closes #1503 by regression test. #1522 (@genisis0x) is superseded by #1209 (the prompt rewrite covers its safety concern); credit retained in CHANGELOG. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(skills): use command -v instead of which for codex detection (#1197) `which` is not on PATH in every shell — some Windows shells, BusyBox- only containers, and minimal CI images all fail when skills probe codex availability via `which codex`. `command -v` is a POSIX builtin and always available where the skill is running. Touched: - codex/SKILL.md.tmpl: CODEX_BIN=$(command -v codex || echo "") - scripts/resolvers/review.ts and scripts/resolvers/design.ts: 3 + 3 sites each rewritten to `command -v codex >/dev/null 2>&1` - Regenerated all 10 affected SKILL.md files (codex, review, ship, design-consultation, design-review, office-hours, plan-ceo-review, plan-design-review, plan-devex-review, plan-eng-review) - test/skill-validation.test.ts: updated pin + defensive regression test that fails if `which codex` returns to codex/SKILL.md - test/skill-e2e-plan.test.ts: updated summary regex Contributed by @mvanhorn via #1197. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(codex): surface non-zero exits so wrappers stop reading as silent stalls (#1467, #1327) When codex exits non-zero (parse errors, arg-shape breaks, model API errors that propagate as non-zero status), the calling agent previously saw an empty output and burned 30-60 minutes misdiagnosing as a silent model/API stall. The hang-detection block only caught exit 124 (the timeout-wrapper signal). Adds elif blocks in all four codex invocation sites (Review default, Challenge, Consult new-session, Consult resume) that: - Echo "[codex exit N] <stderr first line>" to stdout - Indent the first 20 stderr lines for inline context - Log codex_nonzero_exit telemetry tagged with the call site Contributed by @genisis0x via #1467. Closes #1327. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(design): disclose OpenAI key source + warn on cwd .env match (#1278, closes #1248) The design binary previously called process.env.OPENAI_API_KEY without checking where the key came from. If a user ran $D inside someone else's project that had OPENAI_API_KEY in its .env, the resulting generation billed that project's account. Silent and irreversible. Fix: resolveApiKeyInfo() returns both the key and its source. When the env-var path matches an OPENAI_API_KEY entry in the current directory's .env, .env.<NODE_ENV>, or .env.local file, we set a warning. requireApiKey() prints "Using OpenAI key from <source>" plus the warning before the run — never the key itself. Adds 6 unit tests covering: config-vs-env precedence, env-only (no match), env+cwd .env match, quoted/exported values, value-mismatch (no false positive), and the no-leak invariant for requireApiKey stderr output. Contributed by @jbetala7 via #1278. Closes #1248. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(browse): guard full-page screenshots against Anthropic vision API >2000px brick (#1214) Full-page screenshots of tall pages routinely exceeded 2000px on the longest dimension, silently bricking the agent's session: the resulting base64 reached the Anthropic vision API which rejected the oversized image, leaving the agent burning turns on a useless blob with no stderr trace from the browse side. Adds browse/src/screenshot-size-guard.ts as a shared helper: - guardScreenshotBuffer(buf) → downscales in-memory if max(w,h) > 2000 - guardScreenshotPath(path) → file-mode variant that rewrites in place - Aspect ratio preserved via sharp's resize fit:inside - Stderr diagnostic on any downscale so callers can see when it fired - Lazy sharp import so non-screenshot paths pay no startup cost Wires the guard into all three full-page callsites codex review flagged: - browse/src/snapshot.ts: annotated + heatmap fullPage captures - browse/src/meta-commands.ts: screenshot command (path + base64 fullPage modes) plus the responsive 3-viewport sweep - browse/src/write-commands.ts: prettyscreenshot fullPage path Covers seven unit cases (pass-through, downscale, aspect ratio, exactly-2000px edge, file-mode rewrite) plus a static invariant test that fails the build if any of the three callsites stops importing the guard. Closes #1214. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(security): add Node sidecar entry for L4 prompt-injection classifier (#1370) The L4 TestSavant classifier in browse/src/security-classifier.ts can't be imported into the compiled browse server (onnxruntime-node dlopen fails from Bun's compile extract dir per CLAUDE.md). The agent that used to host it (sidebar-agent.ts) was removed when the PTY proved out — leaving the classifier file shipped but with zero callers. Exactly the gap codex flagged in #1370. Adds browse/src/security-sidecar-entry.ts: a Node script that runs the classifier as a subprocess of the browse server. It reads NDJSON requests from stdin and writes id-correlated NDJSON responses to stdout, supporting: - op: "scan-page-content" — full L4 classifier scan - op: "ping" — liveness probe for the client's health check - op: "status" — classifier readiness (used by /pty-inject-scan to surface l4 { available: bool } in its response) Plus browse/src/find-security-sidecar.ts: a resolver that locates node + the bundled JS entry (browse/dist/security-sidecar.js, built in a follow-up package.json change) or falls back to the dev TS entry. Returns null cleanly when node isn't on PATH so the calling endpoint can degrade per D7 (extension WARN + user confirm). C17 of the security-stack wave. C18 adds the IPC client + lifecycle management; C19 wires the endpoint; C20 routes the extension through it. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(security): sidecar IPC client with lifecycle + circuit breaker (#1370) Adds browse/src/security-sidecar-client.ts to manage the Node L4 classifier subprocess from the compiled browse server: - Lazy spawn on first scan; reuses the same process across requests - Id-correlated request/response via NDJSON over stdio - 5s default per-scan timeout; 64KB payload cap (short-circuits before spawn so oversized requests don't waste a process) - 3-in-10-minutes respawn cap → trips circuit breaker; subsequent scans throw immediately so the /pty-inject-scan endpoint can surface l4 { available: false } to the extension and degrade to WARN+confirm - process.on('exit') sends SIGTERM to the child for clean teardown - isSidecarAvailable() lets the endpoint probe before scan calls so the response shape reflects degraded mode honestly Unit tests cover the payload cap, the availability probe, and the breaker-doesn't-crash invariant under repeated rejected calls. C18 of the security-stack wave. C19 adds POST /pty-inject-scan; C20 routes the extension through it. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(security): add POST /pty-inject-scan endpoint for pre-PTY-inject scans (#1370) The sidebar's gstackInjectToTerminal callers (toolbar Cleanup, Inspector "Send to Code") were piping page-derived text directly into the live claude PTY with ZERO classifier processing — the gap codex flagged in #1370. The documented sidebar security stack had a hole the size of every Cleanup-button click. Adds POST /pty-inject-scan to browse/src/server.ts: - Local-only binding (NOT in TUNNEL_PATHS — tunnel attempts get the general 404 path; never reaches the scan logic) - Root-token auth via existing validateAuth() — 401 on unauth - 64KB request cap → 413 + payload-too-large body - 5s scan timeout via sidecar client - URL-blocklist forced to BLOCK in PTY context (page-derived REPL input is higher-risk than ordinary tool output) - L4 ML classifier via the sidecar when available; degrades to WARN per D7 when sidecar is unavailable - Response goes through JSON.stringify(..., sanitizeReplacer) per v1.38.0.0 Unicode-egress hardening - Imports only from security-sidecar-client.ts, never directly from security-classifier.ts (which would brick the compiled Bun binary) Seven static-invariant tests pin the POST verb, auth gate, 64KB cap, tunnel-listener exclusion, sanitizeReplacer wrapping, l4 availability shape, and the no-direct-classifier-import rule. C19 of the security-stack wave. C20 routes the extension through it; C21 adds the invariant AST check. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(extension): route gstackInjectToTerminal through /pty-inject-scan (#1370) Closes the documented-vs-shipped gap codex flagged in #1370. The sidebar's two PTY-injection call sites (Inspector "Send to Code" and toolbar Cleanup) now pre-scan via the new /pty-inject-scan endpoint before writing to the live claude REPL. Adds window.gstackScanForPTYInject(text, origin) to extension/sidepanel-terminal.js: - Async, returns { allow, verdict, reasons, l4 } - POST to /pty-inject-scan with the existing root-token auth - WARN+confirm on scan failure (network down, sidecar absent, etc.) rather than silent PASS — D7 honest-degradation gstackInjectToTerminal stays synchronous, returns boolean. Per D6: keeping the inject sync means existing `const ok = ...?.()` callers don't break, and the invariant test in test/extension-pty-inject-invariant.test.ts can statically pin that every call goes through the scan first. extension/sidepanel.js call sites updated: - inspectorSendBtn click → await scan, BLOCK drops + WARN prompts via window.confirm, PASS injects silently - runCleanup() → same flow. Static cleanup prompt always PASSes but still routes through scan to honor the invariant. C20 of the security-stack wave. C21 adds the static invariant test. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(security): invariant — extension PTY inject must be scan-gated (#1370) Static-analysis invariant test that fails the build if any extension/*.js path calls window.gstackInjectToTerminal without a preceding window.gstackScanForPTYInject in the same enclosing function. Closes the documented-vs-shipped gap codex demanded a machine check on. Rules: - Rule 1: any file that calls inject must also reference scan - Rule 2: in the enclosing function (function declaration, arrow, async (), event handler), a scan call must appear before the inject call by source position - Exemption: sidepanel-terminal.js (the file that DEFINES the inject function) is exempt from Rule 2 since the definition is not a call Plus two structural checks: - sidepanel-terminal.js defines both the inject and scan functions - inject stays SYNCHRONOUS (no `async` modifier) per D6 — async would silently break the `const ok = ...?.()` pattern at every caller C21 of the security-stack wave. The sidecar architecture (#1370) is complete: server-side L1-L3 + L4-via-sidecar (C17+C18+C19), extension pre-scan wiring (C20), and now the regression gate (C21). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(browse): opt-in extended stealth mode with 6 detection-vector patches (#1112) Rebases @garrytan's PR #1112 (Apr 2026, abandoned) onto the current browse/src/stealth.ts contract. The existing minimal "codex narrowed" stealth (webdriver-mask + AutomationControlled launch arg) stays the default. PR #1112's six additional patches are added behind an opt-in GSTACK_STEALTH=extended env flag. Extended-mode patches (applied AFTER the default mask, in order): 1. delete navigator.webdriver from prototype (not just the getter — detectors check `"webdriver" in navigator`) 2. WebGL renderer spoof to Apple M1 Pro (SwiftShader was the #1 software-GPU tell in containers) 3. navigator.plugins returns a PluginArray-prototype-passing array with MimeType objects and namedItem() 4. window.chrome populated with chrome.app, chrome.runtime, chrome.loadTimes(), chrome.csi() with realistic shapes 5. navigator.mediaDevices backfilled when headless drops it 6. CDP cdc_*-prefixed window globals cleared Why opt-in: the default mode's contract is fingerprint CONSISTENCY, which protects against detectors that flag spoofing mismatch. Extended mode actively lies about the environment; sites that reflect on these properties can break. Users who hit detection in default mode can flip GSTACK_STEALTH=extended for SannySoft 100% pass-rate. Twenty unit tests pin the env-flag semantics, all six patches' code presence, and the applyStealth wiring order. Live SannySoft pass-rate verification stays in the periodic-tier E2E suite. Contributed by @garrytan via #1112 (rebased — original PR opened before the codex-narrowed minimum landed; rebase preserves the narrowed default while adding the SannySoft-passing path as opt-in). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test(fixtures): regenerate ship-SKILL.md golden baselines after C10-C13 + C16 templates Updates the three ship-SKILL.md golden baselines (claude, codex, factory hosts) to match the new shape produced by: - C10 #1209 codex argv (prompt + diff scope, no --base) - C11 #1492 merge-base diff (DIFF_BASE= preamble) - C13 #1197 command -v for codex detection - C12 + boundary preservation per regen-enforcing test Per CLAUDE.md SKILL.md workflow: edit the .tmpl, run gen:skill-docs, commit the regenerated outputs together. Goldens are part of the regen contract — without this commit, test/host-config.test.ts' golden-baseline checks fail with the diff codex review surfaced. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(release): v1.41.0.0 — Daegu wave (24 bisect commits, 14 user-facing fixes) Bumps VERSION 1.40.0.0 → 1.41.0.0. CHANGELOG entry follows the release-summary format in CLAUDE.md: two-line headline, lead paragraph, "The numbers that matter" table, "What this means for builders" closer, then itemized Added/Changed/Fixed/For contributors with inline credit to every PR author and original issue reporter. Scale-aware bump per CLAUDE.md: 24 commits, ~6000 LOC net, substantial new capability across security (PTY sidecar wiring), install (Windows build chain), compat (gbrain 0.18-0.35, Codex CLI 0.130+), and quality (screenshot guard, design key disclosure, extended stealth opt-in). MINOR is the right call. Closes for users: #1567, #1559, #1569, #1346, #1418, #1538, #1537, #1530, #1457, #1561, #1554, #1479, #1503, #1248, #1214, #1370, #1327, #1193 pattern, #1152 pattern. Credit retained inline. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(find-browse): resolve source-checkout layout <git-root>/browse/dist/browse[.exe] windows-setup-e2e.yml runs `bun browse/src/find-browse.ts` against a freshly-built repo where binaries land at browse/dist/browse.exe (no .claude/skills/gstack/ install layout). The previous markers chain only matched .codex/.agents/.claude prefixed paths, so find-browse exited "not found" even when the binary was present. Adds a source-checkout fallback after the marker scan: if no installed layout resolves but <git-root>/browse/dist/browse[.exe] exists, return that. Three real callers hit this path: - gstack repo dev workflow before `./setup` runs - windows-setup-e2e.yml CI (the breakage that surfaced this) - make-pdf consumers running from a sibling source checkout Smoke-verified: a fresh git repo with browse/dist/browse on disk now resolves through the source-checkout branch (was returning null before this commit). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(release): bump v1.41.0.0 → v1.42.0.0 to clear queue collision with #1574 The version-gate workflow flagged a collision: PR #1574 (garrytan/colombo-v3) already claims v1.41.0.0, and #1592 (fix/audit-critical-high-bugs) claims v1.41.1.0. Per CLAUDE.md's workspace-aware ship rule, queue-advancing past a claimed version within the same bump level is permitted — MINOR work landing on top of a queued MINOR still reads as MINOR relative to main. Util's suggested next slot is v1.42.0.0; taking it. CHANGELOG entry header bumped + dated 2026-05-19; entry body unchanged (same wave content, same credit list). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
635 lines
26 KiB
TypeScript
635 lines
26 KiB
TypeScript
/**
|
|
* Snapshot command — accessibility tree with ref-based element selection
|
|
*
|
|
* Architecture (Locator map — no DOM mutation):
|
|
* 1. page.locator(scope).ariaSnapshot() → YAML-like accessibility tree
|
|
* 2. Parse tree, assign refs @e1, @e2, ...
|
|
* 3. Build Playwright Locator for each ref (getByRole + nth)
|
|
* 4. Store Map<string, Locator> on BrowserManager
|
|
* 5. Return compact text output with refs prepended
|
|
*
|
|
* Extended features:
|
|
* --diff / -D: Compare against last snapshot, return unified diff
|
|
* --annotate / -a: Screenshot with overlay boxes at each @ref
|
|
* --output / -o: Output path for annotated screenshot
|
|
* -C / --cursor-interactive: Scan for cursor:pointer/onclick/tabindex elements
|
|
*
|
|
* Later: "click @e3" → look up Locator → locator.click()
|
|
*/
|
|
|
|
import type { Page, Frame, Locator } from 'playwright';
|
|
import type { TabSession, RefEntry } from './tab-session';
|
|
import * as Diff from 'diff';
|
|
import { TEMP_DIR, isPathWithin } from './platform';
|
|
import { escapeEnvelopeSentinels } from './content-security';
|
|
import { stripLoneSurrogates } from './sanitize';
|
|
import { guardScreenshotPath } from './screenshot-size-guard';
|
|
|
|
// Roles considered "interactive" for the -i flag
|
|
const INTERACTIVE_ROLES = new Set([
|
|
'button', 'link', 'textbox', 'checkbox', 'radio', 'combobox',
|
|
'listbox', 'menuitem', 'menuitemcheckbox', 'menuitemradio',
|
|
'option', 'searchbox', 'slider', 'spinbutton', 'switch', 'tab',
|
|
'treeitem',
|
|
]);
|
|
|
|
interface SnapshotOptions {
|
|
interactive?: boolean; // -i: only interactive elements
|
|
compact?: boolean; // -c: remove empty structural elements
|
|
depth?: number; // -d N: limit tree depth
|
|
selector?: string; // -s SEL: scope to CSS selector
|
|
diff?: boolean; // -D / --diff: diff against last snapshot
|
|
annotate?: boolean; // -a / --annotate: annotated screenshot
|
|
outputPath?: string; // -o / --output: path for annotated screenshot
|
|
cursorInteractive?: boolean; // -C / --cursor-interactive: scan cursor:pointer etc.
|
|
heatmap?: string; // -H / --heatmap: JSON color map for ref overlays
|
|
}
|
|
|
|
/**
|
|
* Snapshot flag metadata — single source of truth for CLI parsing and doc generation.
|
|
*
|
|
* Imported by:
|
|
* - gen-skill-docs.ts (generates {{SNAPSHOT_FLAGS}} tables)
|
|
* - skill-parser.ts (validates flags in SKILL.md examples)
|
|
*/
|
|
export const SNAPSHOT_FLAGS: Array<{
|
|
short: string;
|
|
long: string;
|
|
description: string;
|
|
takesValue?: boolean;
|
|
valueHint?: string;
|
|
optionKey: keyof SnapshotOptions;
|
|
}> = [
|
|
{ short: '-i', long: '--interactive', description: 'Interactive elements only (buttons, links, inputs) with @e refs. Also auto-enables cursor-interactive scan (-C) to capture dropdowns and popovers.', optionKey: 'interactive' },
|
|
{ short: '-c', long: '--compact', description: 'Compact (no empty structural nodes)', optionKey: 'compact' },
|
|
{ short: '-d', long: '--depth', description: 'Limit tree depth (0 = root only, default: unlimited)', takesValue: true, valueHint: '<N>', optionKey: 'depth' },
|
|
{ short: '-s', long: '--selector', description: 'Scope to CSS selector', takesValue: true, valueHint: '<sel>', optionKey: 'selector' },
|
|
{ short: '-D', long: '--diff', description: 'Unified diff against previous snapshot (first call stores baseline)', optionKey: 'diff' },
|
|
{ short: '-a', long: '--annotate', description: 'Annotated screenshot with red overlay boxes and ref labels', optionKey: 'annotate' },
|
|
{ short: '-o', long: '--output', description: 'Output path for annotated screenshot (default: <temp>/browse-annotated.png)', takesValue: true, valueHint: '<path>', optionKey: 'outputPath' },
|
|
{ short: '-C', long: '--cursor-interactive', description: 'Cursor-interactive elements (@c refs — divs with pointer, onclick). Auto-enabled when -i is used.', optionKey: 'cursorInteractive' },
|
|
{ short: '-H', long: '--heatmap', description: 'Color-coded overlay screenshot from JSON map: \'{"@e1":"green","@e3":"red"}\'. Valid colors: green, yellow, red, blue, orange, gray.', takesValue: true, valueHint: '<json>', optionKey: 'heatmap' },
|
|
];
|
|
|
|
interface ParsedNode {
|
|
indent: number;
|
|
role: string;
|
|
name: string | null;
|
|
props: string; // e.g., "[level=1]"
|
|
children: string; // inline text content after ":"
|
|
rawLine: string;
|
|
}
|
|
|
|
/**
|
|
* Parse CLI args into SnapshotOptions — driven by SNAPSHOT_FLAGS metadata.
|
|
*/
|
|
export function parseSnapshotArgs(args: string[]): SnapshotOptions {
|
|
const opts: SnapshotOptions = {};
|
|
for (let i = 0; i < args.length; i++) {
|
|
const flag = SNAPSHOT_FLAGS.find(f => f.short === args[i] || f.long === args[i]);
|
|
if (!flag) throw new Error(`Unknown snapshot flag: ${args[i]}`);
|
|
if (flag.takesValue) {
|
|
const value = args[++i];
|
|
if (!value) throw new Error(`Usage: snapshot ${flag.short} <value>`);
|
|
if (flag.optionKey === 'depth') {
|
|
(opts as any)[flag.optionKey] = parseInt(value, 10);
|
|
if (isNaN(opts.depth!)) throw new Error('Usage: snapshot -d <number>');
|
|
} else {
|
|
(opts as any)[flag.optionKey] = value;
|
|
}
|
|
} else {
|
|
(opts as any)[flag.optionKey] = true;
|
|
}
|
|
}
|
|
return opts;
|
|
}
|
|
|
|
/**
|
|
* Parse one line of ariaSnapshot output.
|
|
*
|
|
* Format examples:
|
|
* - heading "Test" [level=1]
|
|
* - link "Link A":
|
|
* - /url: /a
|
|
* - textbox "Name"
|
|
* - paragraph: Some text
|
|
* - combobox "Role":
|
|
*/
|
|
function parseLine(line: string): ParsedNode | null {
|
|
// Match: (indent)(- )(role)( "name")?( [props])?(: inline)?
|
|
const match = line.match(/^(\s*)-\s+(\w+)(?:\s+"([^"]*)")?(?:\s+(\[.*?\]))?\s*(?::\s*(.*))?$/);
|
|
if (!match) {
|
|
// Skip metadata lines like "- /url: /a"
|
|
return null;
|
|
}
|
|
return {
|
|
indent: match[1].length,
|
|
role: match[2],
|
|
name: match[3] ?? null,
|
|
props: match[4] || '',
|
|
children: match[5]?.trim() || '',
|
|
rawLine: line,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Take an accessibility snapshot and build the ref map.
|
|
*/
|
|
export async function handleSnapshot(
|
|
args: string[],
|
|
session: TabSession,
|
|
securityOpts?: { splitForScoped?: boolean },
|
|
): Promise<string> {
|
|
const opts = parseSnapshotArgs(args);
|
|
const page = session.getPage();
|
|
// Frame-aware target for accessibility tree
|
|
const target = session.getActiveFrameOrPage();
|
|
const inFrame = session.getFrame() !== null;
|
|
|
|
// Get accessibility tree via ariaSnapshot
|
|
let rootLocator: Locator;
|
|
if (opts.selector) {
|
|
rootLocator = target.locator(opts.selector);
|
|
const count = await rootLocator.count();
|
|
if (count === 0) throw new Error(`Selector not found: ${opts.selector}`);
|
|
} else {
|
|
rootLocator = target.locator('body');
|
|
}
|
|
|
|
const ariaText = await rootLocator.ariaSnapshot();
|
|
if (!ariaText || ariaText.trim().length === 0) {
|
|
session.setRefMap(new Map());
|
|
return '(no accessible elements found)';
|
|
}
|
|
|
|
// Parse the ariaSnapshot output
|
|
const lines = ariaText.split('\n');
|
|
const refMap = new Map<string, RefEntry>();
|
|
const output: string[] = [];
|
|
let refCounter = 1;
|
|
|
|
// Track role+name occurrences for nth() disambiguation
|
|
const roleNameCounts = new Map<string, number>();
|
|
const roleNameSeen = new Map<string, number>();
|
|
|
|
// First pass: count role+name pairs for disambiguation
|
|
for (const line of lines) {
|
|
const node = parseLine(line);
|
|
if (!node) continue;
|
|
const key = `${node.role}:${node.name || ''}`;
|
|
roleNameCounts.set(key, (roleNameCounts.get(key) || 0) + 1);
|
|
}
|
|
|
|
// Second pass: assign refs and build locators
|
|
for (const line of lines) {
|
|
const node = parseLine(line);
|
|
if (!node) continue;
|
|
|
|
const depth = Math.floor(node.indent / 2);
|
|
const isInteractive = INTERACTIVE_ROLES.has(node.role);
|
|
|
|
// Depth filter
|
|
if (opts.depth !== undefined && depth > opts.depth) continue;
|
|
|
|
// Interactive filter: skip non-interactive but still count for locator indices
|
|
if (opts.interactive && !isInteractive) {
|
|
// Still track for nth() counts
|
|
const key = `${node.role}:${node.name || ''}`;
|
|
roleNameSeen.set(key, (roleNameSeen.get(key) || 0) + 1);
|
|
continue;
|
|
}
|
|
|
|
// Compact filter: skip elements with no name and no inline content that aren't interactive
|
|
if (opts.compact && !isInteractive && !node.name && !node.children) continue;
|
|
|
|
// Assign ref
|
|
const ref = `e${refCounter++}`;
|
|
const indent = ' '.repeat(depth);
|
|
|
|
// Build Playwright locator
|
|
const key = `${node.role}:${node.name || ''}`;
|
|
const seenIndex = roleNameSeen.get(key) || 0;
|
|
roleNameSeen.set(key, seenIndex + 1);
|
|
const totalCount = roleNameCounts.get(key) || 1;
|
|
|
|
let locator: Locator;
|
|
if (opts.selector) {
|
|
locator = target.locator(opts.selector).getByRole(node.role as any, {
|
|
name: node.name || undefined,
|
|
});
|
|
} else {
|
|
locator = target.getByRole(node.role as any, {
|
|
name: node.name || undefined,
|
|
});
|
|
}
|
|
|
|
// Disambiguate with nth() if multiple elements share role+name
|
|
if (totalCount > 1) {
|
|
locator = locator.nth(seenIndex);
|
|
}
|
|
|
|
refMap.set(ref, { locator, role: node.role, name: node.name || '' });
|
|
|
|
// Format output line
|
|
let outputLine = `${indent}@${ref} [${node.role}]`;
|
|
if (node.name) outputLine += ` "${node.name}"`;
|
|
if (node.props) outputLine += ` ${node.props}`;
|
|
if (node.children) outputLine += `: ${node.children}`;
|
|
|
|
output.push(outputLine);
|
|
}
|
|
|
|
// ─── Cursor-interactive scan (-C, or auto with -i) ────────
|
|
// Auto-enable cursor scan when interactive mode is on — agents asking for
|
|
// interactive elements should always see clickable non-ARIA items too.
|
|
if (opts.interactive && !opts.cursorInteractive) {
|
|
opts.cursorInteractive = true;
|
|
}
|
|
if (opts.cursorInteractive) {
|
|
try {
|
|
const cursorElements = await target.evaluate(() => {
|
|
const STANDARD_INTERACTIVE = new Set([
|
|
'A', 'BUTTON', 'INPUT', 'SELECT', 'TEXTAREA', 'SUMMARY', 'DETAILS',
|
|
]);
|
|
|
|
const results: Array<{ selector: string; text: string; reason: string }> = [];
|
|
const allElements = document.querySelectorAll('*');
|
|
|
|
for (const el of allElements) {
|
|
// Skip standard interactive elements (already in ARIA tree)
|
|
if (STANDARD_INTERACTIVE.has(el.tagName)) continue;
|
|
// Skip hidden elements
|
|
if (!(el as HTMLElement).offsetParent && el.tagName !== 'BODY') continue;
|
|
|
|
const style = getComputedStyle(el);
|
|
const hasCursorPointer = style.cursor === 'pointer';
|
|
const hasOnclick = el.hasAttribute('onclick');
|
|
const hasTabindex = el.hasAttribute('tabindex') && parseInt(el.getAttribute('tabindex')!, 10) >= 0;
|
|
const hasRole = el.hasAttribute('role');
|
|
|
|
// Check if element is inside a floating container (portal/popover/dropdown)
|
|
const isInFloating = (() => {
|
|
let parent: Element | null = el;
|
|
while (parent && parent !== document.documentElement) {
|
|
const pStyle = getComputedStyle(parent);
|
|
const isFloating = (pStyle.position === 'fixed' || pStyle.position === 'absolute') &&
|
|
parseInt(pStyle.zIndex || '0', 10) >= 10;
|
|
const hasPortalAttr = parent.hasAttribute('data-floating-ui-portal') ||
|
|
parent.hasAttribute('data-radix-popper-content-wrapper') ||
|
|
parent.hasAttribute('data-radix-portal') ||
|
|
parent.hasAttribute('data-popper-placement') ||
|
|
parent.getAttribute('role') === 'listbox' ||
|
|
parent.getAttribute('role') === 'menu';
|
|
if (isFloating || hasPortalAttr) return true;
|
|
parent = parent.parentElement;
|
|
}
|
|
return false;
|
|
})();
|
|
|
|
if (!hasCursorPointer && !hasOnclick && !hasTabindex) {
|
|
// For elements inside floating containers, also check for role="option"/"menuitem"
|
|
if (isInFloating && hasRole) {
|
|
const role = el.getAttribute('role');
|
|
if (role !== 'option' && role !== 'menuitem' && role !== 'menuitemcheckbox' && role !== 'menuitemradio') continue;
|
|
} else {
|
|
continue;
|
|
}
|
|
}
|
|
// Skip elements with ARIA roles UNLESS they're inside a floating container
|
|
// (floating container items may be missed by the accessibility tree)
|
|
if (hasRole && !isInFloating) continue;
|
|
|
|
// Build deterministic nth-child CSS path
|
|
const parts: string[] = [];
|
|
let current: Element | null = el;
|
|
while (current && current !== document.documentElement) {
|
|
const parent = current.parentElement;
|
|
if (!parent) break;
|
|
const siblings = [...parent.children];
|
|
const index = siblings.indexOf(current) + 1;
|
|
parts.unshift(`${current.tagName.toLowerCase()}:nth-child(${index})`);
|
|
current = parent;
|
|
}
|
|
const selector = parts.join(' > ');
|
|
|
|
const text = (el as HTMLElement).innerText?.trim().slice(0, 80) || el.tagName.toLowerCase();
|
|
const reasons: string[] = [];
|
|
if (isInFloating) reasons.push('popover-child');
|
|
if (hasCursorPointer) reasons.push('cursor:pointer');
|
|
if (hasOnclick) reasons.push('onclick');
|
|
if (hasTabindex) reasons.push(`tabindex=${el.getAttribute('tabindex')}`);
|
|
if (hasRole) reasons.push(`role=${el.getAttribute('role')}`);
|
|
|
|
results.push({ selector, text, reason: reasons.join(', ') });
|
|
}
|
|
return results;
|
|
});
|
|
|
|
if (cursorElements.length > 0) {
|
|
output.push('');
|
|
output.push('── cursor-interactive (not in ARIA tree) ──');
|
|
let cRefCounter = 1;
|
|
for (const elem of cursorElements) {
|
|
const ref = `c${cRefCounter++}`;
|
|
const locator = target.locator(elem.selector);
|
|
refMap.set(ref, { locator, role: 'cursor-interactive', name: elem.text });
|
|
output.push(`@${ref} [${elem.reason}] "${elem.text}"`);
|
|
}
|
|
}
|
|
} catch (err: any) {
|
|
// Cursor scan fails on pages with strict CSP or when page has navigated
|
|
if (!err?.message?.includes('Execution context') && !err?.message?.includes('closed') && !err?.message?.includes('Target') && !err?.message?.includes('Content Security')) throw err;
|
|
output.push('');
|
|
output.push('(cursor scan failed — CSP restriction)');
|
|
}
|
|
}
|
|
|
|
// Store ref map on BrowserManager
|
|
session.setRefMap(refMap);
|
|
|
|
if (output.length === 0) {
|
|
return '(no interactive elements found)';
|
|
}
|
|
|
|
const snapshotText = output.join('\n');
|
|
|
|
// ─── Annotated screenshot (-a) ────────────────────────────
|
|
if (opts.annotate) {
|
|
const screenshotPath = opts.outputPath || `${TEMP_DIR}/browse-annotated.png`;
|
|
// Validate output path — resolve symlinks to prevent symlink traversal attacks
|
|
{
|
|
const nodePath = require('path') as typeof import('path');
|
|
const nodeFs = require('fs') as typeof import('fs');
|
|
const absolute = nodePath.resolve(screenshotPath);
|
|
const safeDirs = [TEMP_DIR, process.cwd()].map((d: string) => {
|
|
try { return nodeFs.realpathSync(d); } catch (err: any) { if (err?.code !== 'ENOENT') throw err; return d; }
|
|
});
|
|
let realPath: string;
|
|
try {
|
|
realPath = nodeFs.realpathSync(absolute);
|
|
} catch (err: any) {
|
|
if (err.code === 'ENOENT') {
|
|
try {
|
|
const dir = nodeFs.realpathSync(nodePath.dirname(absolute));
|
|
realPath = nodePath.join(dir, nodePath.basename(absolute));
|
|
} catch (err2: any) {
|
|
if (err2?.code !== 'ENOENT') throw err2;
|
|
realPath = absolute;
|
|
}
|
|
} else {
|
|
throw new Error(`Cannot resolve real path: ${screenshotPath} (${err.code})`);
|
|
}
|
|
}
|
|
if (!safeDirs.some((dir: string) => isPathWithin(realPath, dir))) {
|
|
throw new Error(`Path must be within: ${safeDirs.join(', ')}`);
|
|
}
|
|
}
|
|
try {
|
|
// Inject overlay divs at each ref's bounding box
|
|
const boxes: Array<{ ref: string; box: { x: number; y: number; width: number; height: number } }> = [];
|
|
for (const [ref, entry] of refMap) {
|
|
try {
|
|
const box = await entry.locator.boundingBox({ timeout: 1000 });
|
|
if (box) {
|
|
boxes.push({ ref: `@${ref}`, box });
|
|
}
|
|
} catch (err: any) {
|
|
// Element may be offscreen, hidden, or page navigated — skip
|
|
if (!err?.message?.includes('Timeout') && !err?.message?.includes('timeout') && !err?.message?.includes('closed') && !err?.message?.includes('Target') && !err?.message?.includes('Execution context')) throw err;
|
|
}
|
|
}
|
|
|
|
await page.evaluate((boxes) => {
|
|
for (const { ref, box } of boxes) {
|
|
const overlay = document.createElement('div');
|
|
overlay.className = '__browse_annotation__';
|
|
overlay.style.cssText = `
|
|
position: absolute; top: ${box.y}px; left: ${box.x}px;
|
|
width: ${box.width}px; height: ${box.height}px;
|
|
border: 2px solid red; background: rgba(255,0,0,0.1);
|
|
pointer-events: none; z-index: 99999;
|
|
font-size: 10px; color: red; font-weight: bold;
|
|
`;
|
|
const label = document.createElement('span');
|
|
label.textContent = ref;
|
|
label.style.cssText = 'position: absolute; top: -14px; left: 0; background: red; color: white; padding: 0 3px; font-size: 10px;';
|
|
overlay.appendChild(label);
|
|
document.body.appendChild(overlay);
|
|
}
|
|
}, boxes);
|
|
|
|
await page.screenshot({ path: screenshotPath, fullPage: true });
|
|
await guardScreenshotPath(screenshotPath);
|
|
|
|
// Always remove overlays
|
|
await page.evaluate(() => {
|
|
document.querySelectorAll('.__browse_annotation__').forEach(el => el.remove());
|
|
});
|
|
|
|
output.push('');
|
|
output.push(`[annotated screenshot: ${screenshotPath}]`);
|
|
} catch (err: any) {
|
|
// Remove overlays even on screenshot failure — but only swallow page/browser errors
|
|
if (!err?.message?.includes('closed') && !err?.message?.includes('Target') && !err?.message?.includes('Execution context') && !err?.message?.includes('screenshot')) throw err;
|
|
try {
|
|
await page.evaluate(() => {
|
|
document.querySelectorAll('.__browse_annotation__').forEach(el => el.remove());
|
|
});
|
|
} catch (err2: any) {
|
|
if (!err2?.message?.includes('closed') && !err2?.message?.includes('Target') && !err2?.message?.includes('Execution context')) throw err2;
|
|
}
|
|
}
|
|
}
|
|
|
|
// ─── Heatmap mode (-H) ──────────────────────────────────────
|
|
if (opts.heatmap) {
|
|
const heatmapPath = opts.outputPath || `${TEMP_DIR}/browse-heatmap.png`;
|
|
// Validate output path
|
|
{
|
|
const nodePath = require('path') as typeof import('path');
|
|
const nodeFs = require('fs') as typeof import('fs');
|
|
const absolute = nodePath.resolve(heatmapPath);
|
|
const safeDirs = [TEMP_DIR, process.cwd()].map((d: string) => {
|
|
try { return nodeFs.realpathSync(d); } catch (err: any) { if (err?.code !== 'ENOENT') throw err; return d; }
|
|
});
|
|
let realPath: string;
|
|
try {
|
|
realPath = nodeFs.realpathSync(absolute);
|
|
} catch (err: any) {
|
|
if (err.code === 'ENOENT') {
|
|
try {
|
|
const dir = nodeFs.realpathSync(nodePath.dirname(absolute));
|
|
realPath = nodePath.join(dir, nodePath.basename(absolute));
|
|
} catch (err2: any) {
|
|
if (err2?.code !== 'ENOENT') throw err2;
|
|
realPath = absolute;
|
|
}
|
|
} else {
|
|
throw new Error(`Cannot resolve real path: ${heatmapPath} (${err.code})`);
|
|
}
|
|
}
|
|
if (!safeDirs.some((dir: string) => isPathWithin(realPath, dir))) {
|
|
throw new Error(`Path must be within: ${safeDirs.join(', ')}`);
|
|
}
|
|
}
|
|
|
|
// Parse and validate color map
|
|
const VALID_COLORS = new Set(['green', 'yellow', 'red', 'blue', 'orange', 'gray']);
|
|
const COLOR_MAP: Record<string, { border: string; bg: string }> = {
|
|
green: { border: '#00b400', bg: 'rgba(0,180,0,0.15)' },
|
|
yellow: { border: '#ffb400', bg: 'rgba(255,180,0,0.15)' },
|
|
red: { border: '#ff0000', bg: 'rgba(255,0,0,0.15)' },
|
|
blue: { border: '#0066ff', bg: 'rgba(0,102,255,0.15)' },
|
|
orange: { border: '#ff6600', bg: 'rgba(255,102,0,0.15)' },
|
|
gray: { border: '#888888', bg: 'rgba(136,136,136,0.15)' },
|
|
};
|
|
|
|
let colorAssignments: Record<string, string>;
|
|
try {
|
|
const parsed = JSON.parse(opts.heatmap);
|
|
if (typeof parsed !== 'object' || parsed === null || Array.isArray(parsed)) {
|
|
throw new Error('not an object');
|
|
}
|
|
colorAssignments = parsed;
|
|
} catch {
|
|
throw new Error('Invalid heatmap JSON. Expected object: \'{"@e1":"green","@e3":"red"}\'');
|
|
}
|
|
|
|
// Validate colors
|
|
for (const [ref, color] of Object.entries(colorAssignments)) {
|
|
if (!VALID_COLORS.has(color)) {
|
|
throw new Error(`Invalid heatmap color "${color}" for ${ref}. Valid: ${[...VALID_COLORS].join(', ')}`);
|
|
}
|
|
}
|
|
|
|
try {
|
|
const boxes: Array<{ ref: string; box: { x: number; y: number; width: number; height: number }; color: string }> = [];
|
|
for (const [refKey, color] of Object.entries(colorAssignments)) {
|
|
const cleanRef = refKey.startsWith('@') ? refKey.slice(1) : refKey;
|
|
const entry = refMap.get(cleanRef);
|
|
if (!entry) continue; // Skip refs not found on page
|
|
try {
|
|
const box = await entry.locator.boundingBox({ timeout: 1000 });
|
|
if (box) {
|
|
const colors = COLOR_MAP[color] || COLOR_MAP.gray;
|
|
boxes.push({ ref: `@${cleanRef}`, box, color: JSON.stringify(colors) });
|
|
}
|
|
} catch {
|
|
// Element may be offscreen or hidden — skip
|
|
}
|
|
}
|
|
|
|
await page.evaluate((boxes) => {
|
|
for (const { ref, box, color } of boxes) {
|
|
const colors = JSON.parse(color);
|
|
const overlay = document.createElement('div');
|
|
overlay.className = '__browse_heatmap__';
|
|
overlay.style.cssText = `
|
|
position: absolute; top: ${box.y}px; left: ${box.x}px;
|
|
width: ${box.width}px; height: ${box.height}px;
|
|
border: 2px solid ${colors.border}; background: ${colors.bg};
|
|
pointer-events: none; z-index: 99999;
|
|
font-size: 10px; color: ${colors.border}; font-weight: bold;
|
|
`;
|
|
const label = document.createElement('span');
|
|
label.textContent = ref;
|
|
label.style.cssText = `position: absolute; top: -14px; left: 0; background: ${colors.border}; color: white; padding: 0 3px; font-size: 10px;`;
|
|
overlay.appendChild(label);
|
|
document.body.appendChild(overlay);
|
|
}
|
|
}, boxes);
|
|
|
|
await page.screenshot({ path: heatmapPath, fullPage: true });
|
|
await guardScreenshotPath(heatmapPath);
|
|
|
|
// Remove heatmap overlays
|
|
await page.evaluate(() => {
|
|
document.querySelectorAll('.__browse_heatmap__').forEach(el => el.remove());
|
|
});
|
|
|
|
output.push('');
|
|
output.push(`[heatmap screenshot: ${heatmapPath}]`);
|
|
} catch (err: any) {
|
|
// Cleanup on failure
|
|
try {
|
|
await page.evaluate(() => {
|
|
document.querySelectorAll('.__browse_heatmap__').forEach(el => el.remove());
|
|
});
|
|
} catch {}
|
|
if (!err?.message?.includes('closed') && !err?.message?.includes('Target') && !err?.message?.includes('Execution context') && !err?.message?.includes('screenshot')) throw err;
|
|
}
|
|
}
|
|
|
|
// ─── Diff mode (-D) ───────────────────────────────────────
|
|
if (opts.diff) {
|
|
const lastSnapshot = session.getLastSnapshot();
|
|
if (!lastSnapshot) {
|
|
session.setLastSnapshot(snapshotText);
|
|
return snapshotText + '\n\n(no previous snapshot to diff against — this snapshot stored as baseline)';
|
|
}
|
|
|
|
const changes = Diff.diffLines(lastSnapshot, snapshotText);
|
|
const diffOutput: string[] = ['--- previous snapshot', '+++ current snapshot', ''];
|
|
|
|
for (const part of changes) {
|
|
const prefix = part.added ? '+' : part.removed ? '-' : ' ';
|
|
const diffLines = part.value.split('\n').filter(l => l.length > 0);
|
|
for (const line of diffLines) {
|
|
diffOutput.push(`${prefix} ${line}`);
|
|
}
|
|
}
|
|
|
|
session.setLastSnapshot(snapshotText);
|
|
return stripLoneSurrogates(diffOutput.join('\n'));
|
|
}
|
|
|
|
// Store for future diffs
|
|
session.setLastSnapshot(snapshotText);
|
|
|
|
// Add frame context header when operating inside an iframe
|
|
if (inFrame) {
|
|
const frameUrl = session.getFrame()?.url() ?? 'unknown';
|
|
output.unshift(`[Context: iframe src="${frameUrl}"]`);
|
|
}
|
|
|
|
// Split output for scoped tokens: trusted refs + untrusted text
|
|
if (securityOpts?.splitForScoped) {
|
|
const trustedRefs: string[] = [];
|
|
const untrustedLines: string[] = [];
|
|
|
|
for (const line of output) {
|
|
// Lines starting with @ref are interactive elements (trusted metadata)
|
|
const refMatch = line.match(/^(\s*)@(e\d+|c\d+)\s+\[([^\]]+)\]\s*(.*)/);
|
|
if (refMatch) {
|
|
const [, indent, ref, role, rest] = refMatch;
|
|
// Truncate element name/content to 50 chars for trusted section
|
|
const nameMatch = rest.match(/^"(.+?)"/);
|
|
let truncName = nameMatch ? nameMatch[1] : rest.trim();
|
|
if (truncName.length > 50) truncName = truncName.slice(0, 47) + '...';
|
|
trustedRefs.push(`${indent}@${ref} [${role}] "${truncName}"`);
|
|
}
|
|
// All lines go to untrusted section (full content)
|
|
untrustedLines.push(line);
|
|
}
|
|
|
|
const parts: string[] = [];
|
|
if (trustedRefs.length > 0) {
|
|
parts.push('INTERACTIVE ELEMENTS (trusted — use these @refs for click/fill):');
|
|
parts.push(...trustedRefs);
|
|
parts.push('');
|
|
}
|
|
// Defuse any envelope sentinel that appears inside the page's own
|
|
// accessibility text. Without this, a page whose rendered content
|
|
// contains the literal `═══ END UNTRUSTED WEB CONTENT ═══` string
|
|
// can close the envelope early and forge a fake "trusted" block
|
|
// for the LLM. Same escape that wrapUntrustedPageContent applies.
|
|
const safeUntrusted = untrustedLines.map(escapeEnvelopeSentinels);
|
|
parts.push('═══ BEGIN UNTRUSTED WEB CONTENT ═══');
|
|
parts.push(...safeUntrusted);
|
|
parts.push('═══ END UNTRUSTED WEB CONTENT ═══');
|
|
return stripLoneSurrogates(parts.join('\n'));
|
|
}
|
|
|
|
return stripLoneSurrogates(output.join('\n'));
|
|
}
|