ai-browser-bridge 0.6.0 → 0.7.1

package/README.es.md

@@ -177,6 +177,29 @@ Flow requiere un plan **Google AI Pro/Ultra**. Como los renders de Veo tardan mi
 
 **Mantenimiento de selectores:** los selectores de Flow fueron **verificados en vivo (LIVE-VERIFIED)** contra un editor de proyecto con sesión iniciada. Si Google cambia la UI, vuelve a capturarlos con `node scripts/dev/captureProviderSelectors.mjs`, luego actualiza [`src/config.ts`](src/config.ts); la generación vive en [`src/features/providers/flow/flowPage.ts`](src/features/providers/flow/flowPage.ts) y el CRUD de recursos en [`src/features/providers/flow/flowAssets.ts`](src/features/providers/flow/flowAssets.ts).
 
+## Soporte de Claude Design
+
+El bridge controla **[Claude Design](https://claude.ai/design)** desde tu Chrome del bridge con sesión iniciada. Las lecturas y los cambios de proyectos/archivos usan las propias peticiones de la app desde la pestaña; los turnos, plantillas y modelo/esfuerzo pasan por la interfaz real, una pestaña por proyecto.
+
+```bash
+bridge chrome start --provider design
+bridge design catalog                   # plantillas, modelos + esfuerzo, sistemas de diseño
+bridge design projects
+bridge design model --model "Sonnet 4.6" --effort Low   # modelo (incl. More models) + esfuerzo
+bridge design create --template Slides --prompt "lanzamiento Q3" --model "Haiku 4.5" --effort Low
+bridge design send --project <id> --message "título más grande"
+bridge design read --project <id>       # Conversaciones y últimos mensajes
+bridge design files --project <id>
+bridge design put --project <id> --file hero.png
+bridge design rm --project <id> --path hero.png --yes
+bridge design download --project <id>
+bridge design export --project <id>
+bridge design share --project <id> --access workspace
+bridge design state
+```
+
+Los agentes tienen lo mismo como herramientas MCP **`design_*`** en `bridge serve`; las destructivas requieren `confirm: true`. Publicar como artefacto, Claude Code, exportar PNG/vídeo/PDF/PowerPoint, comentarios y restaurar versiones quedan en la interfaz.
+
 ## Limitaciones
 
 - **Solo macOS** por ahora (ruta de Chrome fija y ayudantes `pbcopy`/`lsof`).

package/README.he.md

@@ -209,6 +209,29 @@ bridge flow project-delete --yes         # מחיקה לצמיתות של הפר
 
 **תחזוקת סלקטורים:** הסלקטורים של Flow **אומתו בזמן אמת (LIVE-VERIFIED)** מול עורך פרויקט מחובר. אם Google משנה את ה-UI, בצעו לכידה מחדש עם `node scripts/dev/captureProviderSelectors.mjs`, ואז עדכנו את [`src/config.ts`](src/config.ts); היצירה נמצאת ב-[`src/features/providers/flow/flowPage.ts`](src/features/providers/flow/flowPage.ts) וה-CRUD של הנכסים ב-[`src/features/providers/flow/flowAssets.ts`](src/features/providers/flow/flowAssets.ts).
 
+## תמיכה ב-Claude Design
+
+ה-bridge מפעיל את **[Claude Design](https://claude.ai/design)** מתוך ה-Chrome של ה-bridge שבו אתם מחוברים. קריאות ושינויים בפרויקטים ובקבצים עוברים דרך הבקשות של האפליקציה עצמה מתוך הלשונית; סבבי שיחה, תבניות, מודל ורמת מאמץ עוברים דרך הממשק האמיתי, לשונית אחת לכל פרויקט.
+
+```bash
+bridge chrome start --provider design
+bridge design catalog                   # תבניות, מודלים + רמות מאמץ, מערכות עיצוב
+bridge design projects
+bridge design model --model "Sonnet 4.6" --effort Low
+bridge design create --template Slides --prompt "השקת Q3" --model "Haiku 4.5"
+bridge design send --project <id> --message "כותרת גדולה יותר"
+bridge design read --project <id>       # שיחות והודעות אחרונות
+bridge design files --project <id>
+bridge design put --project <id> --file hero.png
+bridge design rm --project <id> --path hero.png --yes
+bridge design download --project <id>
+bridge design export --project <id>
+bridge design share --project <id> --access workspace
+bridge design state
+```
+
+סוכנים אחרים מקבלים את אותה יכולת ככלי MCP מסוג **`design_*`** דרך `bridge serve`; כלים הרסניים דורשים `confirm: true`. פרסום כ-artifact, שליחה ל-Claude Code, ייצוא PNG/וידאו/PDF/PowerPoint, תגובות ושחזור גרסאות נשארים ידניים בממשק.
+
 ## מגבלות
 
 - **macOS בלבד** כיום (נתיב Chrome קשיח ועוזרי `pbcopy`/`lsof`).

package/README.md

@@ -372,6 +372,40 @@ Flow requires a **Google AI Pro/Ultra** plan. Because Veo renders take minutes,
 
 **Selector maintenance:** Flow's selectors were **LIVE-VERIFIED** against a signed-in project editor. If Google changes the UI, recapture with `node scripts/dev/captureProviderSelectors.mjs`, then update [`src/config.ts`](src/config.ts); generation lives in [`src/features/providers/flow/flowPage.ts`](src/features/providers/flow/flowPage.ts) and asset CRUD in [`src/features/providers/flow/flowAssets.ts`](src/features/providers/flow/flowAssets.ts).
 
+## Claude Design support
+
+The bridge drives **[Claude Design](https://claude.ai/design)** — Claude's project workspace for slides, prototypes, and documents — from your signed-in bridge Chrome. Reads and project/file changes use the app's own requests from inside the tab (one call each); turns, templates, and model/effort go through the real UI, one tab per project.
+
+```bash
+bridge chrome start --provider design            # sign in at claude.ai
+bridge design catalog                            # templates, models + effort levels, design systems
+bridge design projects --query launch            # list / search projects (--design-systems for design systems)
+bridge design model --model "Sonnet 4.6" --effort Low   # pick model (incl. More models) + effort; --project for a project
+bridge design create --template Slides --prompt "our Q3 launch" --model "Haiku 4.5" --effort Low
+bridge design send --project <id> --message "make the title bolder" --model "Sonnet 4.6" --attach brief.md
+bridge design read --project <id>                # Conversations + latest messages (what you wrote, what Claude replied)
+bridge design new-conversation --project <id>
+bridge design rename-conversation --project <id> --conversation <cid> --title "Logo pass"
+bridge design files --project <id>
+bridge design put --project <id> --file hero.png --dir assets   # add, or replace the same path
+bridge design rm --project <id> --path assets/old.png --yes
+bridge design download --project <id>            # project files to <repo>/.bridge/downloads/design/<id>
+bridge design export --project <id>              # the project .zip
+bridge design share --project <id> --access workspace --permission comment
+bridge design rename --project <id> --name "Launch deck"
+bridge design duplicate --project <id>
+bridge design favorite --project <id>              # --off removes the star
+bridge design use-design-systems --project <id> --design-system <dsid>   # --none clears them
+bridge design delete --project <id> --yes
+bridge design state                              # where Claude Design is, busy tabs, available actions
+```
+
+Add `--json` to any verb for machine-readable output. `send` and `create` wait for Claude's reply (`--timeout`, default 600 s); `--no-wait` returns while the turn runs and `--auto-decide` answers clarifying questions with "Decide for me". A model or effort choice also becomes your Claude Design default, exactly as when you pick it in the UI.
+
+Agents get the same surface as **`design_*` MCP tools** over `bridge serve`: `design_state`, `design_list_projects`, `design_catalog`, `design_choose_model`, `design_list_files`, `design_read_conversation`, `design_open_project`, `design_create_project`, `design_send`, `design_new_conversation`, `design_rename_conversation`, `design_update_project`, `design_duplicate_project`, `design_delete_project`, `design_put_files`, `design_remove_files`, `design_download`, `design_share`. Destructive tools (`design_delete_project`, `design_remove_files`) require `confirm: true`; local paths must stay inside the target repo.
+
+**Left to you in the UI:** Publish as artifact, Send to Claude Code, PNG/video/PDF/PowerPoint export, partner app exports, comments, and version restore — `design state` lists them. Design is not a Fan-out provider: a Fan-out tab closes when its task ends, which would cancel the turn.
+
 ## Limitations
 
 - **macOS-only** today (`open`, `pbcopy`, and `lsof` helpers).

package/README.zh.md

@@ -177,6 +177,29 @@ Flow 需要 **Google AI Pro/Ultra** 套餐。由于 Veo 渲染需要数分钟，
 
 **选择器维护：** Flow 的选择器已针对已登录的项目编辑器**实时验证（LIVE-VERIFIED）**。如果 Google 更改了 UI，请使用 `node scripts/dev/captureProviderSelectors.mjs` 重新捕获，然后更新 [`src/config.ts`](src/config.ts)；生成逻辑位于 [`src/features/providers/flow/flowPage.ts`](src/features/providers/flow/flowPage.ts)，素材 CRUD 位于 [`src/features/providers/flow/flowAssets.ts`](src/features/providers/flow/flowAssets.ts)。
 
+## Claude Design 支持
+
+bridge 可以在已登录的 bridge Chrome 中驱动 **[Claude Design](https://claude.ai/design)**。读取以及项目/文件的修改通过标签页内应用自身的请求完成；对话轮次、模板、模型和推理强度则通过真实界面操作，每个项目一个标签页。
+
+```bash
+bridge chrome start --provider design
+bridge design catalog                   # 模板、模型 + 推理强度、设计系统
+bridge design projects
+bridge design model --model "Sonnet 4.6" --effort Low
+bridge design create --template Slides --prompt "Q3 发布" --model "Haiku 4.5"
+bridge design send --project <id> --message "标题再大一点"
+bridge design read --project <id>       # 对话与最新消息
+bridge design files --project <id>
+bridge design put --project <id> --file hero.png
+bridge design rm --project <id> --path hero.png --yes
+bridge design download --project <id>
+bridge design export --project <id>
+bridge design share --project <id> --access workspace
+bridge design state
+```
+
+其他代理可通过 `bridge serve` 使用相同能力的 **`design_*`** MCP 工具；破坏性工具需要 `confirm: true`。发布为 artifact、发送到 Claude Code、PNG/视频/PDF/PowerPoint 导出、评论和版本恢复仍需在界面中手动完成。
+
 ## 限制
 
 - 目前**仅支持 macOS**（硬编码的 Chrome 路径以及 `pbcopy`/`lsof` 辅助）。

package/SKILL.md

@@ -0,0 +1,235 @@
+---
+name: ai-browser-bridge
+description: Drive ChatGPT, Gemini, Claude, DeepSeek, Grok, Perplexity, Duck.ai, Arena, Google Flow, or Claude Design (claude.ai/design) through a signed-in Chrome session, either from the bridge CLI or its outbound MCP tools. Use when Claude Code, Codex, or another agent should ask a browser-hosted model, upload local files or screenshots, search, resume, or batch-organize browser conversations, fan out across providers, create or edit Claude Design projects (slides, prototypes, documents), or use bridge-managed ChatGPT and Flow capabilities.
+---
+
+# ai-browser-bridge
+
+Drive ChatGPT, Gemini, Claude, DeepSeek, Grok, Perplexity, Duck.ai, Arena, Google Flow, or Claude Design in a real browser from any agent — one provider or fanned out. Exposes sandboxed local repo tools to ChatGPT, Claude, and Grok over MCP, and serves outbound MCP `ask`, `search_conversations`, ChatGPT, Flow, and Claude Design tools so agents can call browser surfaces natively.
+
+## Prerequisites
+
+- macOS
+- Node.js ≥ 22
+- Google Chrome
+- `cloudflared` (optional, for ChatGPT, Claude, and Grok MCP tools)
+- Signed-in providers: run `bridge chrome start --provider <name>` and sign in if needed
+
+## Install & setup
+
+```bash
+npm install -g ai-browser-bridge   # installs `bridge` and ships this SKILL.md
+```
+
+The package folder is also the skill folder. Link it once into each agent's
+global skills directory; every later `npm install -g ai-browser-bridge` then
+updates the skill too:
+
+```bash
+PKG="$(npm root -g)/ai-browser-bridge"
+mkdir -p ~/.claude/skills ~/.agents/skills
+ln -sfn "$PKG" ~/.claude/skills/ai-browser-bridge   # Claude Code
+ln -sfn "$PKG" ~/.agents/skills/ai-browser-bridge   # Codex
+```
+
+## How to use as a tool
+
+### MCP stdio (Claude Code, Codex, Kiro, any MCP client)
+
+```bash
+bridge serve
+```
+
+Exposes tools over stdio:
+- `ask({ prompt, providers?, timeoutSeconds? })`
+- `search_conversations({ query, providers?, limit? })`
+- `design_*` for Claude Design: `design_state`, `design_list_projects`, `design_catalog`,
+  `design_choose_model`, `design_create_project`, `design_send`, `design_read_conversation`,
+  `design_new_conversation`, `design_rename_conversation`, `design_list_files`,
+  `design_put_files`, `design_remove_files`, `design_download`, `design_share`,
+  `design_update_project`, `design_duplicate_project`, `design_delete_project`,
+  `design_open_project`. `design_delete_project` and `design_remove_files` need
+  `confirm: true`; `design_put_files` replaces an existing path without asking.
+- `flow_*` for Google Flow: `flow_generate`, `flow_extend_clip`, `flow_reuse_clip`,
+  `flow_list_clips`, `flow_list_projects`, `flow_list_ingredients`, `flow_download_clips`,
+  `flow_rename_clip`, `flow_rename_project`, `flow_delete_clip`, `flow_delete_project`,
+  `flow_remove_ingredient`, `flow_clear_ingredients`
+- `chatgpt_render_state` for the live ChatGPT render (streaming, image progress, limits)
+
+### CLI (Codex, scripts, any shell-based agent)
+
+```bash
+# One provider
+bridge ask "summarize this repo" --provider chatgpt --json
+
+# Fan out across multiple
+bridge ask "compare approaches" --provider claude,deepseek,grok --json
+```
+
+`--json` emits machine-readable output. Never hangs in a pipe.
+
+## Claude Design
+
+Claude Design (claude.ai/design) is a project workspace for slides, prototypes,
+and documents. The bridge drives it in the signed-in bridge Chrome, one tab per
+project. It is not a fan-out provider, so `ask` does not reach it; use the
+`design_*` tools or `bridge design` instead.
+
+1. `bridge chrome start --provider design` and sign in at claude.ai if needed.
+2. `design_state` first: where Claude Design is, whether a turn is running, and
+   which actions are available.
+3. `design_catalog` for templates, models with effort levels, and design systems.
+4. New work: `design_create_project` with a prompt (and optional template, model,
+   effort, attachments). It waits for Claude's first reply.
+5. Follow-ups: `design_send` in the project's Conversation, then
+   `design_read_conversation` to read replies. For long turns pass `wait: false`
+   and poll `design_read_conversation`.
+6. Files: `design_list_files`, `design_put_files` (repo files only),
+   `design_download` into `.bridge/downloads/design`.
+
+Same surface from a shell:
+
+```bash
+bridge design state --json
+bridge design create --template Slides --prompt "our Q3 launch" --json
+bridge design send --project <id> --message "make the title bolder" --json
+bridge design read --project <id> --json
+```
+
+Left to the human in the UI: Publish as artifact, Send to Claude Code,
+PNG/video/PDF/PowerPoint export, comments, and version restore.
+
+## Per-agent setup
+
+### Claude Code
+
+```bash
+claude mcp add --transport stdio --scope user ai-browser-bridge -- bridge serve
+```
+
+### Codex
+
+```bash
+codex mcp add ai-browser-bridge -- bridge serve
+```
+
+This writes `[mcp_servers.ai-browser-bridge]` to `~/.codex/config.toml`. Codex can
+also call the CLI directly, for example `bridge ask "your question" --provider chatgpt --json`.
+
+### Kiro
+
+Add to your MCP config:
+```jsonc
+{
+  "mcpServers": {
+    "ai-browser-bridge": { "command": "bridge", "args": ["serve"] }
+  }
+}
+```
+
+### Cursor
+
+Add to `.cursor/mcp.json`:
+```json
+{
+  "mcpServers": {
+    "ai-browser-bridge": { "command": "bridge", "args": ["serve"] }
+  }
+}
+```
+
+## Available commands
+
+| Command | Purpose |
+|---------|---------|
+| `bridge` (bare) | Interactive TUI |
+| `bridge ask <prompt>` | One-shot send + reply |
+| `bridge chrome start --provider <name>` | Start existing Chrome profile with debug port |
+| `bridge status` / `bridge chrome status` | Show Chrome debug-port status |
+| `bridge cache list\|prune` | Inspect/prune safe generated Chrome cache |
+| `bridge serve` | Outbound MCP ask/search tools (stdio) |
+| `bridge download` | Download conversation attachments |
+| `bridge sessions` | List stored sessions |
+| `bridge stop` | Kill warm Chrome |
+| `bridge project list\|create\|rename\|delete` | Manage ChatGPT Projects |
+| `bridge chat list\|search\|move\|organize\|archive` | List, search, batch-organize & archive conversations |
+| `bridge chat organize status\|pause\|resume` | Inspect or control the latest persisted organization queue |
+| `bridge task list\|create` | Schedule ChatGPT Tasks |
+| `bridge chatgpt` | Inspect the live ChatGPT render |
+| `bridge flow` | Generate and manage Google Flow clips and ingredients |
+| `bridge design` | Claude Design projects, templates, model/effort, files, Conversations, share |
+
+## Keep conversations organized (ChatGPT)
+
+Before starting a **new** ChatGPT conversation, check whether it belongs in an
+existing Project instead of adding one more loose chat:
+
+1. `bridge project list` — the Projects that already exist.
+2. `bridge chat search "<topic>"` — a related past chat (and where it lives).
+3. If a Project fits, ask/resume there, then file the chat:
+   `bridge chat move "<idOrTitle>" --project "<Project>"`.
+4. Only leave a chat loose when nothing fits. The first time a **second**
+   related chat appears, `bridge project create "<Project>"` and move both in.
+
+For agents driving the bridge:
+
+- One Project per topic / repo / deliverable — reuse before you create.
+- `bridge chat list --orphans` shows only loose (project-less) chats; a growing list
+  there is the signal to file them into Projects.
+- Archive dead or scratch chats with `bridge chat archive "<idOrTitle>"`
+  (reversible — hides from the sidebar) to keep it lean. Batch with `--id`.
+- Don't spawn throwaway or test conversations in the signed-in account. Use an
+  isolate profile (`bridge ask --fan-out` with `isolate`) for scratch runs, and
+  clean up anything you create.
+
+For a full-history cleanup, scan only loose chats with
+`bridge chat list --orphans --json`, group clear recurring topics, and leave
+ambiguous or uncommon chats loose. Reuse existing Projects first; create a new
+Project only for a stable topic with at least two chats. Put every accepted move
+into one JSON plan of `{ "conversation": "<idOrTitle>", "project": "<name>" }`
+items, dry-run it, then start the persisted queue:
+
+```bash
+bridge chat organize --plan @organization-plan.json --dry-run
+bridge chat organize --plan @organization-plan.json \
+  --interval 60 --cooldown 600 --max-attempts 4 --json
+
+# Later lifecycle operations do not need the plan again
+bridge chat organize status --json
+bridge chat organize pause
+bridge chat organize resume --json
+```
+
+The queue persists under `.bridge/chat-organization-queues/`. Running the exact
+same plan again resumes pending work without replaying completed moves. Rate
+limits and closed Chrome sessions are deferred without consuming a move attempt;
+the queue relaunches its browser session automatically. Adaptive pacing starts at
+60 seconds, speeds up 20% after every three successful moves to a 15-second floor,
+and slows 50% after each rate limit to a 180-second ceiling, in addition to the
+600-second cooldown. Pace is persisted across pause/resume; use `--no-adaptive`
+only when a fixed/random interval is specifically required.
+
+At completion, the queue automatically runs `--orphans` discovery to the proven
+stable bottom of ChatGPT history and reports both intentional remaining orphans
+and any planned Conversation still loose. The scanner throws rather than silently
+accepting a partial inventory. Planned Conversations that remain loose are retried
+automatically up to `--max-attempts`. Start the queue, confirm it acquires the lock and
+processes or defers one item, then let it continue unattended—continuous agent
+watching is unnecessary. Use `bridge chat organize pause` instead of killing the
+process, `resume` to continue the latest queue without reconstructing its plan,
+and `--restart` only when the whole plan should intentionally be replayed.
+
+## Constraints
+
+- macOS only (hardcoded Chrome path, pbcopy/lsof)
+- Each provider needs Chrome started with `bridge chrome start --provider <name>` and a signed-in browser session
+- File operations are sandboxed to the target repo (no escape)
+- No raw shell — only validated MCP tools
+- Browser selectors may break when provider UIs update
+
+## Fan-out behavior
+
+- `--provider a,b,c` runs all in parallel
+- Partial-failure tolerant: exits non-zero only when ALL fail
+- `--strict`: exit non-zero if ANY fails
+- Replies keyed by provider in JSON output