mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-09 10:18:32 +01:00
+22




![dependabot[bot]](/assets/img/avatar_default.png)
![capy-ai[bot]](/assets/img/avatar_default.png)



Garry Tan
Jim McKeeth
thearbajonart
capy-ai[bot]
dependabot[bot]
DanCanadian
Nader Helmy
Nader Helmy
Zee Zheng
Jack Thomas
Jayesh Betala
techcenter68
Mattias Petersson
Arno V
0xDevNinja
Benjamin D. Smith
Brian Majewski
neallee2012
Max Hogan
maxpetrusenkoagent
katlun-lgtm
mikehasa
Briac
JackJin
EmilianoU26
frosimanuel
Tom Lam
Yotam
Jinzhe
Xianying Tan
Boyard Engels
Jey2311
8bb6d65270
* docs: fix CONTRIBUTING.md test-tiers link in TESTING_INTERNALS The link resolved relative to docs/, pointing at a nonexistent docs/CONTRIBUTING.md. Adopts #3070. Co-authored-by: thearbajonart <334330110+thearbajonart@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * ci: refresh GitHub Actions SHA pins (setup-buildx 4.4.1, build-push 7.4.0, attest 4.2.2, setup-node 7.0.0) Rewrite of dependabot #2988. Every bumped `uses:` stays pinned to the full commit SHA (verified against the upstream tags) and now carries its exact version comment, including the lines that had none. setup-node 6.5.0 -> 7.0.0 is a major bump; its notes list an ESM migration, cache outputs and removal of a dummy NODE_AUTH_TOKEN export, none of which affect our node-version-only use. actionlint 1.7.11 (CI image) and 1.7.12 are clean. Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(openclaw): stop advising a per-spawn env for spawned sessions OpenClaw's sessions_spawn has no env argument (openclaw/openclaw#51654 was closed without adding one), so the documented env: { OPENCLAW_SESSION: "1" } silently did nothing. Point users at the ACP harness or Gateway environment instead and guard the old advice. Adopts #2749. Co-authored-by: DanCanadian <211164803+DanCanadian@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(benchmark): scope /benchmark routing to web page performance /benchmark claimed the bare words "benchmark" and "performance", so model and eval benchmark requests could route to the web performance skill instead of /benchmark-models. Narrow the description, Use-when list and triggers to web-specific phrases, point model/skill benchmarks at /benchmark-models, and split the root router line the same way. The catalog lead stays within the discovery budget ("Web performance ..."). Adopts #2302 and closes duplicate #2083 (rewritten on current main). Co-authored-by: Nader Helmy <31414549+creatornader@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(llms.txt): link skills by generated path, drop host-skipped skills gen-llms-txt built every skill link as <name>/SKILL.md, so the router pointed at a nonexistent gstack/SKILL.md (it is the root SKILL.md) and /claude-code pointed at a SKILL.md the Claude host never generates. Links now use the template's generated output path, and skills the Claude host skips are left out of the index. Adopts #2279. Co-authored-by: Nader Helmy <creator.nader@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(ci): install Bun from the SHA-256-verified release archive in GitLab CI and Ubicloud setup Rewrite of #1713. .gitlab-ci.yml's .setup-bun anchor and scripts/ubicloud/setup-free-suite.sh still piped https://bun.sh/install into bash. Both now download the bun-v$BUN_VERSION linux-x64 release zip, check it against the same SHA-256 Dockerfile.ci uses (#1706) before unzipping, install it to ~/.bun/bin and assert `bun --version`. test/ci-image-cli-pin.test.ts runs curlPipedToShell over both files and binds their hash and BUN_VERSION to Dockerfile.ci's amd64 arm and package.json's engines floor, so a Bun bump has to move all of them together. Verified by running the GitLab anchor in debian:stable-slim (bash and sh) and the Ubicloud block in a temp HOME. Co-authored-by: Zee Zheng <228040220+spacegeologist@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(browse): viewport auto unpins a pinned viewport without a restart `viewport WxH` pinned the page with no way back short of `browse restart`, which also drops a headed /connect-chrome session. `viewport auto` (aliases `reset`, `unpin`) now undoes the pin: - headed: the context already launches with `viewport: null`, but Playwright cannot drop a page's emulated size (and re-applies it on new frame sessions), so the active tab gets a fresh page in the same context at the same URL or load-html content. Cookies and storage persist, the tab id and ownership stay, refs reset as on navigation, and the page follows the real window again. - headless: back to the 1280x720 launch default, tracked viewport included. `auto` with --scale is rejected. Fixes #1059. Adopts #2782 and #1881. Co-authored-by: Jack Thomas <17882510+loulanyue@users.noreply.github.com> Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(browse): screenshot accepts --clip=x,y,w,h and --selector=<css> Agent-generated commands often use the GNU `--flag=value` form, which threw "Unknown screenshot flag". Both value flags now accept it, through the same validation and conflict checks as the space-separated form. Adopts #1563. Co-authored-by: techcenter68 <75930234+techcenter68@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(benchmark): price Codex cached input at the cache rate, stop calling Gemini OAuth ready Codex reports cached_input_tokens as a subset of input_tokens, but the adapter billed all of input_tokens at the full input rate. Split them into disjoint uncached and cached counts (what estimateCostUsd expects) and show new+cached input in the table and Markdown reports. A stored Gemini OAuth file alone is now reported as not ready, with a reason naming GEMINI_API_KEY; key-based auth stays ready. Adopts the focused subset of #2283; the capacity error code and stdin change are left out (no captured failure or reproduced hang). Co-authored-by: Mattias Petersson <mattias.petersson@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review): catch loosened-input consumers and stale user-facing strings The Enum & Value Completeness check fired only on newly added values, so a diff that widens what a validator, parser or guard accepts, and breaks an unchanged downstream consumer outside the diff, was a blind spot. Widen the check's trigger (heading unchanged) and add a consumer-grep bullet. Teach the maintainability specialist to flag user-facing strings whose guarding condition changed while the text did not. Adopts #2141 (rewritten on current main; the section heading is kept). Co-authored-by: Arno V <38716+aversini@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(global-discover): bucket Codex sessions by originator Every Codex rollout counted as one undifferentiated codex bucket, so /retro global could not tell interactive Codex Desktop work from codex_exec runs or Claude Code-driven calls. Normalize session_meta.payload.originator into desktop, exec, claude_code or other (missing, unknown and non-string values), report the split per repo as codex_originators and globally as tools.codex.originators, and print it in the summary. Existing totals are unchanged. Adopts #1488. Refs #1315. Co-authored-by: 0xDevNinja <manmit0x@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(hook-check): cover skill frontmatter hooks, sourced helpers, conflict markers and the caller's tsconfig Rewrite of #3066. bin/gstack-hook-check only listed setup's hooks plus /autoplan's by name, so the /careful and /freeze PreToolUse checks (also run by /guard and /investigate), /plan-ceo-review's hand-off hook and the helpers they source were never parse-checked before Claude Code ran them. - The hook list is setup's _hook_command_path arguments plus every gstack path on a `command:` line in a generated */SKILL.md frontmatter (9 hooks, up from 6). The generated files are read rather than the .tmpl sources because the /autoplan and /plan-ceo-review commands come from resolvers. - Each shell hook's gstack-tree helpers (`.`/`source` lines, assignments and shellcheck source= directives, followed transitively) are parsed too: careful/bin/hook-extract.sh and bin/gstack-state-root.sh for /careful and /freeze. - The shim, its helpers, each TypeScript entry and every local module the bundle used (bun build --metafile; entry only when bun lacks it) are scanned for conflict-marker lines, which still parse inside heredocs, strings and template literals. - bun build runs from the gstack root, so the caller's broken tsconfig.json or bunfig.toml no longer fails every TypeScript hook. Lists are newline separated, so a root with spaces works. Tests in test/setup-hook-syntax-gate.test.ts cover each case; the gstack-doctor fixture now copies autoplan/SKILL.md, whose frontmatter registers the hook its hooks-row test breaks. docs/troubleshooting.md describes the wider check. Co-authored-by: Benjamin D. Smith <7134745+BenjaminDSmithy@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(review): extend defensive-security framing to the security specialist and Red Team The "authorized defensive-security review" framing and fixture summary mode lived only in the adversarial subagent prompt. The security specialist and the Red Team also reason adversarially over the full diff, so repos whose test corpus is attack payloads could still get those passes refused. Move both paragraphs into scripts/resolvers/defensive-review.ts (the adversarial render stays byte-identical), state them once in the specialist dispatch for the security specialist and the Red Team, and have the Red Team prompt start from them. Testing and the other specialists keep full fixture reads; the codex host still strips Review Army. Parity caps for ship and review rise by the measured 1,380 bytes each (carve-guards notes). Adopts #1921 (rewritten on current main). Co-authored-by: Brian Majewski <1693720+bmajewski@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(team-init): make the required-mode hook shell-neutral (node CommonJS, no shell variables) Rewrite of #2217. Required team mode wrote a bash check-gstack.sh and registered it as "$CLAUDE_PROJECT_DIR/.claude/hooks/check-gstack.sh", which only works when the hook runner is a POSIX shell. Under cmd.exe or PowerShell (Windows, Copilot CLI) the variable is not expanded and the .sh cannot run, so an intended allow or deny became a hook error. - The hook is now .claude/hooks/check-gstack.cjs: the same root search (GSTACK_ROOT, every host's global root, the migrated repo), with the home directory from HOME, then USERPROFILE, then os.homedir(). It prints {} when gstack resolves and the PreToolUse deny JSON with exit 2 when not. - The registered command is `node -e "require(require('path').resolve( process.env.CLAUDE_PROJECT_DIR || '.', '.claude', 'hooks', 'check-gstack.cjs'))"`: no `$` or `%`, so sh, cmd.exe and PowerShell all pass it through unchanged. - An existing check-gstack registration (matcher Skill or Skill|skill) is replaced in place; duplicates are dropped and unrelated hooks in the same entry kept. The legacy .sh is deleted only after the settings write succeeds (a tracked one joins the suggested git add), and is kept when bun is missing or the write fails, which now reports instead of claiming success. Tests: team-mode and the hook-schema test run the command as registered; test/team-init-hook-shell-neutral.test.ts runs it through the platform's default shell (cmd.exe on the Windows lane, which curates it in) and through PowerShell when installed (verified here in the pwsh 7 container). The routing-probe check for the bash `_GSTACK_ROOT` gate now pins the same contract in the .cjs: every host root probed, block only when none resolves. Co-authored-by: neallee2012 <1499497+neallee2012@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup-gbrain): register the gbrain MCP through bun.exe on Windows so no console window opens Rewrite of #2007, folding #1963's MCP notes. On Windows the local stdio registration stored the bun `gbrain` binstub; gbrain.exe starts bun in a new console, so every Claude Code session opened a visible terminal for the MCP (the contributor's process trees show it; bun.exe launched directly attaches to Claude Code's headless ConPTY). Under MINGW/MSYS/Cygwin the skill now resolves BUN_ROOT from BUN_INSTALL or ~/.bun and registers `$BUN_ROOT/bin/bun.exe <global node_modules gbrain/src/cli.ts> serve`. That path also covers a `bun link`ed clone, whose global node_modules entry links to it; gstack-gbrain-install records no other clone location. When bun.exe or the entry is missing it registers `$BUN_ROOT/bin/gbrain.exe` by its full name, because Claude Code does not apply PATHEXT to a stored path (#1963). POSIX keeps the binstub line. The skill also notes that `claude mcp list` can show "Failed to connect" while a live session holds a local PGLite brain's single-writer lock (#1963). test/setup-gbrain-windows-mcp.test.ts runs the generated fence under bash with stub uname/claude and a temp HOME for MINGW64, MSYS with BUN_INSTALL, a missing entry, and Linux. It is listed as Windows-incompatible (POSIX stubs); the console behavior needs a manual Windows check. Co-authored-by: Max Hogan <max@maxhogan.dev> Co-authored-by: maxpetrusenkoagent <280464918+maxpetrusenkoagent@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(hosts): rewrite every "Agent tool" phrasing for agent-runtime hosts The Agent-tool rewrite for hermes, gbrain, openclaw and factory keyed only on "use the Agent tool", but templates mostly say "via the Agent tool", "with the Agent tool", "multiple Agent tool calls" or "Use the Agent tool", so the Claude tool name leaked into those hosts' skills and sections. Add ordered rules after the existing key (possessive, "the Agent tool", then bare "Agent tool") mapping to sessions_spawn (gbrain/openclaw), delegate_task (hermes) and delegation (factory). No goldens change. Adopts #1935 (rewritten on current main, without the new goldens). Co-authored-by: katlun-lgtm <264247399+katlun-lgtm@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(setup-deploy): Vercel auto-deploys only when connected to the Git repo /setup-deploy stated that Vercel always deploys on push, which is false for CLI-only projects with no Git integration, and its nothing-detected path did not say why such a project is invisible to detection. Qualify the Vercel trigger (ask for and record the CLI deploy command otherwise) and note that `vercel link` creates .vercel/ so a re-run detects the project. Adopts the Vercel accuracy part of #2992 (rewritten on current main); the third-party bring-up tool pointer is not adopted. Co-authored-by: mikehasa <91774998+mikehasa@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(retro): persist recommendations so the next retro detects follow-through /retro produced "3 Things to Improve" but never saved them in its JSON snapshot, so the next retro could not tell whether last week's recommendations were acted on. Step 13 now drafts the items before saving and always writes a `recommendations` array ({category, text}, [] when empty); Step 12 scores each prior recommendation addressed/partial/open against this window's commits, files and metrics and renders a follow-through line, skipping silently for snapshots without the key. The report format ties the items to the saved array. Global mode is unchanged. Adopts #1853 (rewritten on current main). Refs #1834. Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(global-discover): count the interactive Codex CLI (codex_cli_rs) in its own cli bucket * feat(developer-profile): --reconcile backfills office-hours tenure from timeline.jsonl sessions[] is written only at office-hours Phase 4.5, so runs that ended earlier never counted toward tenure and the tier undercounted. Add a manual `--reconcile` that scans projects/*/timeline.jsonl for office-hours `completed` events and appends a count-only row ({date, mode, project_slug, signal_count: 0, signals: [], backfilled: true}) for each run with no sessions[] entry for the same project within 60 minutes, extended back by a duration_s under 8h. It is idempotent, skips malformed lines, and leaves the file untouched on a no-op. `--read` counts backfilled rows for SESSION_COUNT and TIER but takes LAST_*, DESIGN_*, CROSS_PROJECT and the nudge from logged sessions only. Not wired into the preamble yet; the office-hours greeting guard for backfill-only profiles is left to the office-hours owner. Adopts #2668 (rewritten on current main). Closes part (b) of #2657. Co-authored-by: Briac <137724549+briacSck@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): the publication hook approves /autoplan's own Reads after the skill turn Claude Code applies a skill's allowed-tools only to the turn that invoked it. On 2.1.292 the default fork-subagent mode runs reviewers in the background, and the completion notice starts a new turn, so later Reads outside the working directory (the next phase's section file, the close packet) raised permission cards. Skill hooks stay registered for the session, and a PreToolUse "allow" skips the card (reproduced in a PTY on 2.1.292). autoplan/bin/owned-read.ts approves a parent Read only when the guard itself returned no output, and only for this installation's autoplan/sections/*.md (canonical path or the gbrain :user render) or an immutable phase artifact in <repo>/.gstack/tmp/autoplan/autoplan-<phase>-*/ whose repo is the session's project directory or contains it. Denials, unverified allows, child calls and every other path are unchanged. renderSectionBase and userRenderRoot move there with it. Tests that asserted a verified driver Read as {} now expect the approval; autoplan-owned-read covers the shipped shim, the close packet without a journal, verified artifacts through the guard, look-alikes (foreign install, writable copy, symlink alias, other repository, other names) and a guard denial staying a denial. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(autoplan): restore point and phase artifacts live in the project's .gstack/tmp/autoplan/ Skill hooks do not run inside subagents, so a reviewer launched after a background completion notice raised a card for its own input (native-prompt.md under the state root). Step 1 now puts RESTORE_PATH in the repository's git-excluded .gstack/tmp/autoplan/ (added to .git/info/exclude, mode 700), and the snapshot tool writes every phase artifact beside it, so /autoplan and its reviewers read them from the working directory without a card. The guard's bindings are unchanged: they anchor on the restore point's directory. Step 1 still prints the slug, which the old RESTORE_PATH carried. A free test runs the generated Step 1 block twice from a repository subdirectory: the restore point lands in <repo>/.gstack/tmp/autoplan/, the exclude line is written once and git status stays clean. The autoplan parity cap rises by the measured bytes (115,270 / 101,979 = 1.1303). Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(evals): autoplan-guard-pty fails on any permission card after the reviewer's notice turn The scripted boundary now mirrors Step 1's layout (restore point and artifacts in the project's .gstack/tmp/autoplan/) and continues past the Phase 2 entry to dispatch the Phase 2 reviewer after the CEO reviewer's completion notice. The case asserts four verified guard allows, that the close packet Read, the Phase 2 section Read and the Phase 2 dispatch came after a task-notification turn, that the Phase 2 reviewer read its input, and that no permission card appeared at all. Still one trial on haiku, about 75-85 seconds. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(autoplan): permission cards after a background reviewer, and where /autoplan keeps its files Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(outside-review): read a trailing '— Medium.' or '(High)' severity on a finding line, the shape Codex now writes * feat(design): honor OPENAI_BASE_URL for every design API call One resolver, openaiUrl() in design/src/auth.ts, now builds every OpenAI URL the design binary, its prototype and its live model check use. Setting OPENAI_BASE_URL sends image generation and screenshot analysis to an OpenAI-compatible gateway; unset or blank keeps api.openai.com. The prototype script now goes through receiptedFetch, so its egress is receipted like the rest, and receipts already record the gateway host. A source scan keeps any design file outside auth.ts from hardcoding an OpenAI API URL again, and a request-shape test proves the gateway reaches both the vision and image endpoints. Co-authored-by: JackJin <1037461232@qq.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review: testing specialist treats negative assertions as decisions A new assertion that something is absent records a behavior removal and needs cited intent. A rename or removal in the diff can empty a standing negative assertion so it passes forever; the specialist now greps the suite for negative assertions naming the old value. Adopted from the testing-specialist part of a community PR; the scope-check hunk targeted text that no longer exists. Co-authored-by: EmilianoU26 <314541067+EmilianoU26@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review: security specialist checks authorization a route-guard read misses Four access-control classes where the guard is correct and the object still leaks: error pages composed outside the guard, ownership surviving a role downgrade, list/detail/download paths checked as one, and a session mutated before the identity-switch callback is validated. Adopted to review/specialists/security.md only; the /cso hunk targeted a bullet list that is now an OWASP/ASVS table. Co-authored-by: EmilianoU26 <314541067+EmilianoU26@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * review: zero findings is valid; suppress six common false positives The checklist now says a clean diff may come back clean, and suppresses framework-owned error handling, long exhaustive switches, null derefs a type guard already narrows, N+1 on fixed-cardinality loops, hardcoded test fixture values and non-cryptographic Math.random(). The contributor's "missing input validation on an internal function" and "missing await on fire-and-forget" suppressions are left out: both can hide real bugs. Co-authored-by: frosimanuel <frosimanuel@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(todos): parked contributor ideas by theme; /autoplan permission follow-ups * design-review: capture code tokens before universal principles /design-review read only DESIGN.md and otherwise fell back to universal principles, so a project whose system lives in CSS custom properties, tailwind.config or a theme file got audited and mocked up against an invented aesthetic. The skill now reads code tokens before falling back, and the target-mockup brief reuses the captured colors, fonts, radii and spacing, changing layout only. The contributor's optional microcopy checks (domain vocabulary, human register) are not adopted here. Co-authored-by: Tom Lam <tomlam0811@berkeley.edu> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(sidebar): add a terminal text-size picker to the toolbar The sidebar terminal toolbar gets an XS-XL text-size picker beside Restart. SM (13px) stays the default, so nothing changes until a user picks a size; the choice persists in chrome.storage.local and applies to the live terminal, re-fitting xterm and re-sending the PTY size two frames later so the new character cell is measured first. A VM test runs the real sidepanel-terminal.js through one auto-connect and checks the creation size, the stored-size fallback, persistence and the live resize. Co-authored-by: Yotam <yotsurfing@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(design-shotgun): generate with Codex's built-in $imagegen on Codex On the Codex host, /design-shotgun now generates and edits mockups with Codex's documented $imagegen skill in its default built-in mode (the image_gen tool), so users signed in with ChatGPT need no OPENAI_API_KEY. The design binary stays for the local comparison board only, images are published with gstack-design-claim as before, and screenshot evolution loads the captured page with view_image before an $imagegen edit. Step 3c-3d moved into a DESIGN_SHOTGUN_GENERATION resolver that returns the existing design-binary text unchanged for every other host; the Claude output differs only in two host-neutral rewordings of the evolve-from-screenshot pointers. DESIGN_SETUP and the regenerate step of the board loop gain matching Codex-only text for design-shotgun. Co-authored-by: Jinzhe <hwang.phy@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * voice: ban the "load-bearing" stock phrase Models overuse "load-bearing"; it joins the AI-vocabulary ban line in both voice tiers. The tier-2 voice directive is also tightened (the meta "compressed for runtime" tag and the bounded closer's restated exemption clause) so the shared preamble shrinks by 163 bytes per tier-2+ skill, which also pays for the reply-language rule that follows. The ship goldens are refreshed for the new render. Co-authored-by: Nader Helmy <creator.nader@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * voice: reply in the language of the user's latest message Every skill's voice directive now tells the agent to reply in the language of the user's latest message unless asked otherwise, so long English skill text no longer drags a Chinese (or any non-English) session into English. Mixed-language sessions follow the latest message. Code, commands, paths, identifiers and quoted output stay verbatim, and at tier 2+ so do the machine-read question markers (D<N>, option letters, (recommended)). The rule costs 205 bytes per tier-2+ skill and 144 per tier-1 skill. A further 25-byte cut to the bounded closer's exemption list leaves the net for this wave at +17 bytes per tier-2+ skill and +158 per tier-1 skill. review, qa and browse caps rise with measured notes; the ship goldens are refreshed. Co-authored-by: Xianying Tan <shrektan@126.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(redact-prepush): committed exact-span allowlist at .gstack-redact-allowlist The pre-push hook never fed the engine's allowlist option, so a reviewed, known-benign value (a public dev-compose URL, a documented sample key) warned or blocked every push, and the only ways out were a bypass or reshaping code until the detector stopped matching. The hook now reads the repo-root .gstack-redact-allowlist from each pushed commit (never the working tree), one exact matched span per line with # comments. Only a finding whose matched text equals an entry is suppressed: a password alone, a substring, or a different key still reports and still blocks, and engine.* unscanned findings are untouched. Every push that carries entries prints the entry count and each suppressed finding's rule and file line. Oversized files (over 64 KiB) are ignored. gstack.redact.allowEmail keeps working as before. Co-authored-by: Boyard Engels <boyard.engels@gmail.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(brain-sync): opt-in removal publishing with a bulk-removal valve gstack-brain-sync never published a removal: a deleted synced file, or the old directory after a project slug migration, stayed on the remote forever and gbrain indexed both copies. New setting artifacts_sync_removals (off by default). When on, each drain commits and pushes, receipted like every push, the removal of tracked files that are gone from disk and match the sync allowlist. Transcript pages are never removed here, and a decision log goes only together with its active snapshot. One valve: a drain that would remove more than 20 files at once publishes none and says so. `gstack-brain-sync --publish-removals` lists the pending removals and `--publish-removals --yes` publishes them on demand, whatever the setting. Co-authored-by: Jey2311 <5177215+Jey2311@users.noreply.github.com> * feat(windows): setup.ps1 checks prerequisites and runs ./setup in Git Bash A PowerShell entry point for Windows users. It checks that Git for Windows, Bun and Node.js are on PATH (printing the winget command for each missing one and changing nothing), finds Git Bash from git.exe rather than a PATH bash that may be WSL's, and runs ./setup from the checkout with every argument passed as its own argv entry to a constant bash script. No argument is interpolated into shell source. ./setup itself is unchanged. Co-authored-by: Jim McKeeth <jim@mckeeth.org> * v1.91.63.0: CHANGELOG, version * fix(ci): link bunx after the SHA-verified Bun install in GitLab CI and the Ubicloud setup * fix(redact-prepush): strip every parent column from combined-diff lines, so a merged release bump is exempt like any other * fix(hook-check): treat a Windows drive path as absolute (cygpath when present), so --list finds the skill hooks from a native caller * fix(windows): owned-read requires the read-only attribute on Windows; setup.ps1 passes arguments NUL-separated through a private file; Windows-only tests expect the owned-read approval * perf(hook-check): bundle every hook's TypeScript entries in one bun process instead of two bun starts per entry (seconds each on Windows) * perf(hook-check): read all skill frontmatter in one awk and scan conflict markers with one grep per hook (half the process starts) --------- Co-authored-by: thearbajonart <334330110+thearbajonart@users.noreply.github.com> Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: DanCanadian <211164803+DanCanadian@users.noreply.github.com> Co-authored-by: Nader Helmy <31414549+creatornader@users.noreply.github.com> Co-authored-by: Nader Helmy <creator.nader@gmail.com> Co-authored-by: Zee Zheng <228040220+spacegeologist@users.noreply.github.com> Co-authored-by: Jack Thomas <17882510+loulanyue@users.noreply.github.com> Co-authored-by: Jayesh Betala <jayesh.betala7@gmail.com> Co-authored-by: techcenter68 <75930234+techcenter68@users.noreply.github.com> Co-authored-by: Mattias Petersson <mattias.petersson@gmail.com> Co-authored-by: Arno V <38716+aversini@users.noreply.github.com> Co-authored-by: 0xDevNinja <manmit0x@gmail.com> Co-authored-by: Benjamin D. Smith <7134745+BenjaminDSmithy@users.noreply.github.com> Co-authored-by: Brian Majewski <1693720+bmajewski@users.noreply.github.com> Co-authored-by: neallee2012 <1499497+neallee2012@users.noreply.github.com> Co-authored-by: Max Hogan <max@maxhogan.dev> Co-authored-by: maxpetrusenkoagent <280464918+maxpetrusenkoagent@users.noreply.github.com> Co-authored-by: katlun-lgtm <264247399+katlun-lgtm@users.noreply.github.com> Co-authored-by: mikehasa <91774998+mikehasa@users.noreply.github.com> Co-authored-by: Briac <137724549+briacSck@users.noreply.github.com> Co-authored-by: JackJin <1037461232@qq.com> Co-authored-by: EmilianoU26 <314541067+EmilianoU26@users.noreply.github.com> Co-authored-by: frosimanuel <frosimanuel@gmail.com> Co-authored-by: Tom Lam <tomlam0811@berkeley.edu> Co-authored-by: Yotam <yotsurfing@gmail.com> Co-authored-by: Jinzhe <hwang.phy@gmail.com> Co-authored-by: Xianying Tan <shrektan@126.com> Co-authored-by: Boyard Engels <boyard.engels@gmail.com> Co-authored-by: Jey2311 <5177215+Jey2311@users.noreply.github.com> Co-authored-by: Jim McKeeth <jim@mckeeth.org>
549 lines
22 KiB
TypeScript
549 lines
22 KiB
TypeScript
/**
|
|
* Generate N design variants from a brief.
|
|
* Uses staggered parallel: 1s delay between API calls to avoid rate limits.
|
|
* Falls back to exponential backoff on 429s.
|
|
*/
|
|
|
|
import fs from "fs";
|
|
import path from "path";
|
|
import { openaiUrl, requireApiKey } from "./auth";
|
|
import { receiptedFetch } from "./receipted-fetch";
|
|
import { imageRequestBody, modelRejectionHint } from "./models";
|
|
import { parseBrief } from "./brief";
|
|
import { normalizeIntFlag } from "./flag-utils";
|
|
import { checkMockup, type CheckResult } from "./check";
|
|
import { analyzeScreenshot, evolvePrompt } from "./evolve";
|
|
import {
|
|
emitResult,
|
|
exitCodeFor,
|
|
newAccounting,
|
|
persistImage,
|
|
type ExitCode,
|
|
type Recovery,
|
|
type RunAccounting,
|
|
} from "./persist";
|
|
|
|
export interface VariantsOptions {
|
|
brief?: string;
|
|
briefFile?: string;
|
|
/** JSON array of { brief, screenshot? }, one entry per variant. */
|
|
briefsFile?: string;
|
|
/**
|
|
* Raw CLI flag value or a number. Normalized inside variants() (#2032):
|
|
* nonsense errors loudly; above STYLE_VARIATIONS.length clamps with a
|
|
* warning — past that index variants degrade to duplicate base-brief runs.
|
|
*/
|
|
count?: number | string | boolean;
|
|
outputDir: string;
|
|
size?: string;
|
|
quality?: string;
|
|
viewports?: string; // "desktop,tablet,mobile" — generates at multiple sizes
|
|
}
|
|
|
|
const STYLE_VARIATIONS = [
|
|
"", // First variant uses the brief as-is
|
|
"Use a bolder, more dramatic visual style with stronger contrast and larger typography.",
|
|
"Use a calmer, more minimal style with generous whitespace and subtle colors.",
|
|
"Use a warmer, more approachable style with rounded corners and friendly typography.",
|
|
"Use a more professional, corporate style with sharp edges and structured grid layout.",
|
|
"Commit to one saturated hue across large surfaces (drenched color) with restrained decoration and texture from the product's material world.",
|
|
"Use a playful, modern style with asymmetric layout and unexpected color accents.",
|
|
];
|
|
|
|
export interface VariantResult {
|
|
requested: string;
|
|
path: string;
|
|
success: boolean;
|
|
error?: string;
|
|
recovered?: Recovery;
|
|
/** Exhausted its 429 retries. */
|
|
rateLimited?: boolean;
|
|
/** A rerun of the same operation could succeed (rate limit, timeout, deadline, 5xx, empty image). */
|
|
retryable?: boolean;
|
|
/** The API returned an empty image; nothing was saved. */
|
|
empty?: boolean;
|
|
}
|
|
|
|
type RequestFailure = { error: string; rateLimited?: boolean; retryable: boolean };
|
|
|
|
const DEADLINE_ERROR = "Batch deadline reached";
|
|
|
|
/** Resolves after `ms`, or as soon as `signal` aborts. */
|
|
function sleep(ms: number, signal?: AbortSignal): Promise<void> {
|
|
return new Promise(resolve => {
|
|
if (signal?.aborted) return resolve();
|
|
const done = () => { clearTimeout(timer); signal?.removeEventListener("abort", done); resolve(); };
|
|
const timer = setTimeout(done, ms);
|
|
signal?.addEventListener("abort", done, { once: true });
|
|
});
|
|
}
|
|
|
|
/**
|
|
* Request one variant image, retrying only the API call on 429. Returns the
|
|
* base64 image or the final error; nothing here touches the filesystem.
|
|
* `signal` (a batch deadline) stops backoff waits and the request; once it
|
|
* has aborted no new attempt starts.
|
|
*/
|
|
export async function requestVariantImage(
|
|
apiKey: string,
|
|
prompt: string,
|
|
size: string,
|
|
quality: string,
|
|
fetchFn: typeof globalThis.fetch = globalThis.fetch,
|
|
signal?: AbortSignal,
|
|
): Promise<{ imageData: string } | RequestFailure> {
|
|
const maxRetries = 3;
|
|
const MAX_RETRY_AFTER_MS = 60_000; // cap honored Retry-After to bound stalls
|
|
let lastError = "";
|
|
let skipLeadingDelay = false;
|
|
let body: string;
|
|
try {
|
|
body = imageRequestBody(prompt, { size, quality });
|
|
} catch (err: any) {
|
|
return { error: err.message, retryable: false };
|
|
}
|
|
|
|
for (let attempt = 0; attempt <= maxRetries; attempt++) {
|
|
if (attempt > 0 && !skipLeadingDelay) {
|
|
// Exponential backoff: 2s, 4s, 8s
|
|
const delay = Math.pow(2, attempt) * 1000;
|
|
console.error(` Rate limited, retrying in ${delay / 1000}s...`);
|
|
await sleep(delay, signal);
|
|
}
|
|
skipLeadingDelay = false;
|
|
if (signal?.aborted) return { error: DEADLINE_ERROR, retryable: true };
|
|
|
|
const controller = new AbortController();
|
|
const timeout = setTimeout(() => controller.abort(), 240_000);
|
|
|
|
let response: Response;
|
|
try {
|
|
response = await receiptedFetch("variants-image-request", openaiUrl("responses"), {
|
|
method: "POST",
|
|
headers: {
|
|
"Authorization": `Bearer ${apiKey}`,
|
|
"Content-Type": "application/json",
|
|
},
|
|
body,
|
|
signal: signal ? AbortSignal.any([controller.signal, signal]) : controller.signal,
|
|
}, fetchFn);
|
|
} catch (err: any) {
|
|
clearTimeout(timeout);
|
|
if (err.name === "AbortError") return { error: signal?.aborted ? DEADLINE_ERROR : "Timeout (240s)", retryable: true };
|
|
lastError = err.message;
|
|
continue;
|
|
}
|
|
clearTimeout(timeout);
|
|
|
|
if (response.status === 429) {
|
|
lastError = "Rate limited (429)";
|
|
const retryAfter = response.headers.get("retry-after");
|
|
if (retryAfter) {
|
|
const trimmed = retryAfter.trim();
|
|
let waitMs: number | null = null;
|
|
if (/^\d+$/.test(trimmed)) {
|
|
// delta-seconds (RFC 7231)
|
|
waitMs = Math.min(Number.parseInt(trimmed, 10) * 1000, MAX_RETRY_AFTER_MS);
|
|
} else {
|
|
// HTTP-date (RFC 7231)
|
|
const dateMs = Date.parse(trimmed);
|
|
if (!Number.isNaN(dateMs)) {
|
|
waitMs = Math.min(Math.max(0, dateMs - Date.now()), MAX_RETRY_AFTER_MS);
|
|
}
|
|
}
|
|
if (waitMs !== null) {
|
|
if (waitMs > 0) {
|
|
await sleep(waitMs, signal);
|
|
}
|
|
// Honored Retry-After (incl. 0 / past date "retry now") — skip the
|
|
// next iteration's leading exponential sleep so we don't double-wait.
|
|
skipLeadingDelay = true;
|
|
}
|
|
}
|
|
continue;
|
|
}
|
|
|
|
if (!response.ok) {
|
|
const error = await response.text();
|
|
if (response.status === 403 && error.includes("organization must be verified")) {
|
|
return { error: "OpenAI organization verification required. Go to https://platform.openai.com/settings/organization to verify.", retryable: false };
|
|
}
|
|
return { error: `API error (${response.status}): ${error.slice(0, 200)}${modelRejectionHint(response.status, error, "image")}`, retryable: response.status >= 500 };
|
|
}
|
|
|
|
try {
|
|
const data = await response.json() as any;
|
|
const imageItem = data.output?.find((item: any) => item.type === "image_generation_call");
|
|
if (!imageItem?.result) return { error: "No image data in response", retryable: true };
|
|
return { imageData: imageItem.result };
|
|
} catch (err: any) {
|
|
return { error: signal?.aborted ? DEADLINE_ERROR : `Unreadable API response: ${err.message}`, retryable: true };
|
|
}
|
|
}
|
|
|
|
return { error: lastError, rateLimited: lastError === "Rate limited (429)", retryable: true };
|
|
}
|
|
|
|
/**
|
|
* Generate a single variant: one API request (with 429 retry), then exactly
|
|
* one persistence attempt on the received bytes. A save failure is reported
|
|
* with its path and never triggers another request.
|
|
*
|
|
* Exported for testability. Pass `fetchFn` to inject a stubbed fetch in tests;
|
|
* production code uses the global fetch by default.
|
|
*/
|
|
export async function generateVariant(
|
|
apiKey: string,
|
|
prompt: string,
|
|
outputPath: string,
|
|
size: string,
|
|
quality: string,
|
|
fetchFn: typeof globalThis.fetch = globalThis.fetch,
|
|
signal?: AbortSignal,
|
|
): Promise<VariantResult> {
|
|
const received = await requestVariantImage(apiKey, prompt, size, quality, fetchFn, signal);
|
|
if ("error" in received) {
|
|
return { requested: outputPath, path: outputPath, success: false, ...received };
|
|
}
|
|
const outcome = persistImage(received.imageData, outputPath);
|
|
if (outcome.ok) return { requested: outputPath, path: outcome.path, success: true };
|
|
return {
|
|
requested: outputPath,
|
|
path: outputPath,
|
|
success: false,
|
|
error: outcome.failure.reason,
|
|
...(Buffer.from(received.imageData || "", "base64").length === 0 ? { retryable: true, empty: true } : { retryable: false }),
|
|
...(outcome.recovered ? { recovered: outcome.recovered } : {}),
|
|
};
|
|
}
|
|
|
|
interface VariantJob {
|
|
outputPath: string;
|
|
prompt: string;
|
|
size: string;
|
|
label: string;
|
|
}
|
|
|
|
/** Launch jobs 1.5s apart, wait for all, and fold them into run accounting. */
|
|
async function runVariantJobs(apiKey: string, quality: string, jobs: VariantJob[]): Promise<{
|
|
acct: RunAccounting;
|
|
errors: string[];
|
|
}> {
|
|
const promises = jobs.map((job, i) =>
|
|
new Promise(resolve => setTimeout(resolve, i * 1500)).then(() => {
|
|
console.error(` Starting ${job.label}...`);
|
|
return generateVariant(apiKey, job.prompt, job.outputPath, job.size, quality);
|
|
})
|
|
);
|
|
const results = await Promise.allSettled(promises);
|
|
|
|
const acct = newAccounting(jobs.length);
|
|
const errors: string[] = [];
|
|
results.forEach((result, i) => {
|
|
const requested = jobs[i].outputPath;
|
|
if (result.status === "fulfilled" && result.value.success) {
|
|
const size = fs.statSync(result.value.path).size;
|
|
console.error(` ✓ ${path.basename(result.value.path)} (${(size / 1024).toFixed(0)}KB)`);
|
|
acct.saved.push(result.value.path);
|
|
return;
|
|
}
|
|
const reason = result.status === "fulfilled" ? result.value.error || "unknown error" : (result.reason as Error).message;
|
|
console.error(` ✗ ${path.basename(requested)}: ${reason}`);
|
|
errors.push(path.basename(requested));
|
|
acct.failures.push({ file: requested, reason });
|
|
if (result.status === "fulfilled" && result.value.recovered) acct.recovered.push(result.value.recovered);
|
|
});
|
|
return { acct, errors };
|
|
}
|
|
|
|
function emitVariantsResult(outputDir: string, acct: RunAccounting, errors: string[], extra: Record<string, unknown> = {}, selected: string[] = acct.saved): ExitCode {
|
|
return emitResult({
|
|
outputDir,
|
|
...extra,
|
|
count: acct.requested,
|
|
succeeded: selected.length,
|
|
failed: errors.length,
|
|
paths: selected,
|
|
errors,
|
|
requested: acct.requested,
|
|
saved: acct.saved,
|
|
selected,
|
|
failures: acct.failures,
|
|
recovered: acct.recovered,
|
|
}, exitCodeFor(selected.length > 0, acct.saved.length));
|
|
}
|
|
|
|
export interface BriefEntry {
|
|
brief: string;
|
|
screenshot?: string;
|
|
}
|
|
|
|
/** One entry per variant; the ceiling matches the built-in style directions. */
|
|
export const MAX_BRIEFS = STYLE_VARIATIONS.length;
|
|
/** Whole-batch deadline; the skill's Bash call allows 600s. */
|
|
export const BATCH_DEADLINE_MS = 540_000;
|
|
const STAGGER_MS = 1500;
|
|
|
|
/**
|
|
* Read and validate a --briefs-file before any billable call. Errors name the
|
|
* file, the entry index and the field.
|
|
*/
|
|
export function readBriefsFile(file: string): BriefEntry[] {
|
|
const fail = (problem: string): never => { throw new Error(`--briefs-file ${file}: ${problem}`); };
|
|
let raw: unknown;
|
|
try {
|
|
raw = JSON.parse(fs.readFileSync(file, "utf-8"));
|
|
} catch (err: any) {
|
|
return fail(`cannot read a JSON array (${err.message})`);
|
|
}
|
|
if (!Array.isArray(raw) || raw.length < 1 || raw.length > MAX_BRIEFS) {
|
|
return fail(`expected a JSON array of 1 to ${MAX_BRIEFS} entries like [{"brief": "...", "screenshot": "optional.png"}]`);
|
|
}
|
|
return raw.map((entry: any, index) => {
|
|
if (!entry || typeof entry !== "object" || Array.isArray(entry)) fail(`entry ${index}: expected an object with a "brief" field`);
|
|
const unknown = Object.keys(entry).find(key => key !== "brief" && key !== "screenshot");
|
|
if (unknown) fail(`entry ${index}: unknown field "${unknown}" (allowed: brief, screenshot)`);
|
|
if (typeof entry.brief !== "string" || !entry.brief.trim()) fail(`entry ${index}: field "brief" must be a non-empty string`);
|
|
if (entry.screenshot === undefined) return { brief: entry.brief };
|
|
if (typeof entry.screenshot !== "string" || !entry.screenshot) fail(`entry ${index}: field "screenshot" must be a non-empty string`);
|
|
let readable = false;
|
|
try {
|
|
fs.accessSync(entry.screenshot, fs.constants.R_OK);
|
|
readable = fs.statSync(entry.screenshot).isFile();
|
|
} catch {}
|
|
if (!readable) fail(`entry ${index}: field "screenshot" is not a readable file: ${entry.screenshot}`);
|
|
return { brief: entry.brief, screenshot: entry.screenshot };
|
|
});
|
|
}
|
|
|
|
export interface BatchVariant {
|
|
variant: string;
|
|
/** This variant's pick: its last saved image, or the requested name when nothing was saved. */
|
|
path: string;
|
|
/** Every image this variant saved, in order (a failed check's regeneration adds one). */
|
|
saved: string[];
|
|
operation: "generate" | "evolve";
|
|
status: "done" | "failed" | "rate_limited";
|
|
error: string | null;
|
|
retryable: boolean;
|
|
check: { status: CheckResult["status"]; issues: string } | null;
|
|
}
|
|
|
|
export interface BatchOptions {
|
|
apiKey: string;
|
|
outputDir: string;
|
|
size: string;
|
|
quality: string;
|
|
fetchFn?: typeof globalThis.fetch;
|
|
deadlineMs?: number;
|
|
staggerMs?: number;
|
|
}
|
|
|
|
/**
|
|
* Generate one variant per brief with staggered parallel launches under one
|
|
* batch deadline. Every image is saved without overwriting. Each variant
|
|
* repeats its own operation (generate, or evolve when it has a screenshot)
|
|
* once for an empty image and once for a failed check, keeping both images,
|
|
* and always ends with a terminal status.
|
|
*/
|
|
export async function runBriefsBatch(entries: BriefEntry[], opts: BatchOptions, acct: RunAccounting = newAccounting(entries.length)): Promise<BatchVariant[]> {
|
|
const fetchFn = opts.fetchFn ?? globalThis.fetch;
|
|
const controller = new AbortController();
|
|
const deadline = setTimeout(() => controller.abort(), opts.deadlineMs ?? BATCH_DEADLINE_MS);
|
|
const signal = controller.signal;
|
|
|
|
const runOne = async (entry: BriefEntry, index: number): Promise<BatchVariant> => {
|
|
const variant = String.fromCharCode(65 + index);
|
|
const requested = path.join(opts.outputDir, `variant-${variant}.png`);
|
|
const operation = entry.screenshot ? "evolve" : "generate";
|
|
const saved: string[] = [];
|
|
let attempted = false;
|
|
const finish = (status: BatchVariant["status"], error: string | null, retryable: boolean, check: BatchVariant["check"]): BatchVariant => {
|
|
const pick = saved.at(-1) ?? requested;
|
|
if (error && !attempted) acct.failures.push({ file: requested, reason: error });
|
|
const detail = status === "done" ? `${saved.join(", ")} (check ${check!.status})` : error;
|
|
console.error(`VARIANT_${variant}_${status.toUpperCase()}: ${detail}`);
|
|
return { variant, path: pick, saved, operation, status, error, retryable, check };
|
|
};
|
|
const attempt = async (): Promise<VariantResult> => {
|
|
attempted = true;
|
|
let result: VariantResult;
|
|
if (!entry.screenshot) {
|
|
result = await generateVariant(opts.apiKey, entry.brief, requested, opts.size, opts.quality, fetchFn, signal);
|
|
} else {
|
|
let analysis: string | null = null;
|
|
try {
|
|
analysis = await analyzeScreenshot(opts.apiKey, fs.readFileSync(entry.screenshot).toString("base64"), fetchFn, signal);
|
|
} catch (err: any) {
|
|
result = { requested, path: requested, success: false, error: signal.aborted ? DEADLINE_ERROR : `Screenshot analysis failed: ${err.message}`, retryable: true };
|
|
}
|
|
if (analysis !== null) result = await generateVariant(opts.apiKey, evolvePrompt(analysis, entry.brief), requested, opts.size, opts.quality, fetchFn, signal);
|
|
}
|
|
if (result!.success) {
|
|
saved.push(result!.path);
|
|
acct.saved.push(result!.path);
|
|
} else {
|
|
acct.failures.push({ file: requested, reason: result!.error ?? "unknown error" });
|
|
}
|
|
if (result!.recovered) acct.recovered.push(result!.recovered);
|
|
return result!;
|
|
};
|
|
const check = async (): Promise<NonNullable<BatchVariant["check"]>> => {
|
|
if (signal.aborted) return { status: "skipped", issues: `${DEADLINE_ERROR} before the check` };
|
|
try {
|
|
const result = await checkMockup(saved.at(-1)!, entry.brief, { apiKey: opts.apiKey, fetchFn, signal });
|
|
return { status: result.status, issues: result.issues };
|
|
} catch (err: any) {
|
|
return { status: "skipped", issues: signal.aborted ? `${DEADLINE_ERROR} during the check` : `Check failed to run: ${err.message}` };
|
|
}
|
|
};
|
|
|
|
await sleep(index * (opts.staggerMs ?? STAGGER_MS), signal);
|
|
if (signal.aborted) return finish("failed", `${DEADLINE_ERROR} before start`, true, null);
|
|
console.error(` Starting variant ${variant} (${operation})...`);
|
|
|
|
let result = await attempt();
|
|
if (result.empty && !signal.aborted) result = await attempt();
|
|
if (!result.success) return finish(result.rateLimited ? "rate_limited" : "failed", result.error ?? "unknown error", result.retryable ?? true, null);
|
|
|
|
let checked = await check();
|
|
if (checked.status === "fail" && !signal.aborted) {
|
|
const regenerated = await attempt();
|
|
if (regenerated.success) checked = await check();
|
|
}
|
|
return finish("done", null, false, checked);
|
|
};
|
|
|
|
try {
|
|
return await Promise.all(entries.map(runOne));
|
|
} finally {
|
|
clearTimeout(deadline);
|
|
}
|
|
}
|
|
|
|
async function variantsFromBriefsFile(options: VariantsOptions): Promise<ExitCode> {
|
|
if (typeof options.briefsFile !== "string") throw new Error("--briefs-file needs the path of a JSON file");
|
|
if (options.brief !== undefined || options.briefFile !== undefined || options.viewports !== undefined) {
|
|
throw new Error("--briefs-file cannot be combined with --brief, --brief-file or --viewports; put each variant's brief in the file.");
|
|
}
|
|
const entries = readBriefsFile(options.briefsFile);
|
|
if (options.count !== undefined) console.error(`warning: --count is ignored with --briefs-file; generating ${entries.length} variants, one per entry.`);
|
|
const apiKey = requireApiKey();
|
|
|
|
console.error(`Generating ${entries.length} variants from ${options.briefsFile}...`);
|
|
const startTime = Date.now();
|
|
const acct = newAccounting(entries.length);
|
|
const results = await runBriefsBatch(entries, {
|
|
apiKey, outputDir: options.outputDir, size: options.size || "1536x1024", quality: options.quality || "high",
|
|
}, acct);
|
|
const done = results.filter(r => r.status === "done");
|
|
console.error(`\n${done.length}/${results.length} variants generated (${((Date.now() - startTime) / 1000).toFixed(1)}s)`);
|
|
return emitVariantsResult(options.outputDir, acct, results.filter(r => r.status !== "done").map(r => path.basename(r.path)), {
|
|
validated: done.filter(r => r.check?.status === "pass").length,
|
|
variants: results,
|
|
}, done.map(r => r.path));
|
|
}
|
|
|
|
/**
|
|
* Generate N variants with staggered parallel execution.
|
|
*/
|
|
export async function variants(options: VariantsOptions): Promise<ExitCode> {
|
|
if (options.briefsFile !== undefined) return variantsFromBriefsFile(options);
|
|
let apiKey: string;
|
|
let baseBrief: string;
|
|
try {
|
|
apiKey = requireApiKey();
|
|
baseBrief = options.briefFile
|
|
? parseBrief(options.briefFile, true)
|
|
: parseBrief(options.brief!, false);
|
|
} catch (err: any) {
|
|
const reason = err?.message || String(err);
|
|
console.error(reason);
|
|
const acct = newAccounting(0);
|
|
acct.failures.push({ file: options.outputDir, reason });
|
|
return emitVariantsResult(options.outputDir, acct, []);
|
|
}
|
|
|
|
const quality = options.quality || "high";
|
|
|
|
// If viewports specified, generate responsive variants instead of style variants
|
|
if (options.viewports) {
|
|
return generateResponsiveVariants(apiKey, baseBrief, options.outputDir, options.viewports, quality);
|
|
}
|
|
|
|
// #2032: normalize at the consumption site so every caller (CLI or
|
|
// programmatic) gets the loud-on-nonsense contract; the ceiling derives
|
|
// from STYLE_VARIATIONS so it self-adjusts when styles are added.
|
|
const count = normalizeIntFlag(options.count, {
|
|
name: "count",
|
|
def: 3,
|
|
min: 1,
|
|
max: STYLE_VARIATIONS.length,
|
|
});
|
|
const size = options.size || "1536x1024";
|
|
|
|
console.error(`Generating ${count} variants...`);
|
|
const startTime = Date.now();
|
|
|
|
const jobs: VariantJob[] = [];
|
|
for (let i = 0; i < count; i++) {
|
|
const variation = STYLE_VARIATIONS[i] || "";
|
|
const letter = String.fromCharCode(65 + i);
|
|
jobs.push({
|
|
outputPath: path.join(options.outputDir, `variant-${letter}.png`),
|
|
prompt: variation ? `${baseBrief}\n\nStyle direction: ${variation}` : baseBrief,
|
|
size,
|
|
label: `variant ${letter}`,
|
|
});
|
|
}
|
|
|
|
const { acct, errors } = await runVariantJobs(apiKey, quality, jobs);
|
|
const elapsed = ((Date.now() - startTime) / 1000).toFixed(1);
|
|
console.error(`\n${acct.saved.length}/${count} variants generated (${elapsed}s)`);
|
|
return emitVariantsResult(options.outputDir, acct, errors);
|
|
}
|
|
|
|
const VIEWPORT_CONFIGS: Record<string, { size: string; suffix: string; desc: string }> = {
|
|
desktop: { size: "1536x1024", suffix: "desktop", desc: "Desktop (1536x1024)" },
|
|
tablet: { size: "1024x1024", suffix: "tablet", desc: "Tablet (1024x1024)" },
|
|
mobile: { size: "1024x1536", suffix: "mobile", desc: "Mobile (1024x1536, portrait)" },
|
|
};
|
|
|
|
async function generateResponsiveVariants(
|
|
apiKey: string,
|
|
baseBrief: string,
|
|
outputDir: string,
|
|
viewports: string,
|
|
quality: string,
|
|
): Promise<ExitCode> {
|
|
const viewportList = viewports.split(",").map(v => v.trim().toLowerCase());
|
|
const configs = viewportList.map(v => VIEWPORT_CONFIGS[v]).filter(Boolean);
|
|
|
|
if (configs.length === 0) {
|
|
const reason = `No valid viewports. Use: desktop, tablet, mobile`;
|
|
console.error(reason);
|
|
const acct = newAccounting(viewportList.length);
|
|
acct.failures.push({ file: outputDir, reason });
|
|
return emitVariantsResult(outputDir, acct, [], { viewports: viewportList });
|
|
}
|
|
|
|
console.error(`Generating responsive variants: ${configs.map(c => c.desc).join(", ")}...`);
|
|
const startTime = Date.now();
|
|
|
|
const jobs: VariantJob[] = configs.map(config => ({
|
|
outputPath: path.join(outputDir, `responsive-${config.suffix}.png`),
|
|
prompt: `${baseBrief}\n\nViewport: ${config.desc}. Adapt the layout for this screen size. ${
|
|
config.suffix === "mobile" ? "Use a single-column layout, larger touch targets, and mobile navigation patterns." :
|
|
config.suffix === "tablet" ? "Use a responsive layout that works for medium screens." :
|
|
""
|
|
}`,
|
|
size: config.size,
|
|
label: config.desc,
|
|
}));
|
|
|
|
const { acct, errors } = await runVariantJobs(apiKey, quality, jobs);
|
|
const elapsed = ((Date.now() - startTime) / 1000).toFixed(1);
|
|
console.error(`\n${acct.saved.length}/${configs.length} responsive variants generated (${elapsed}s)`);
|
|
return emitVariantsResult(outputDir, acct, errors, { viewports: viewportList });
|
|
}
|