gflow-cli 0.20.1__tar.gz → 0.21.0__tar.gz

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/.env.template

@@ -129,3 +129,14 @@
 # scripts/dev/capture_locale_invariants.py or to live-verify a non-EN
 # language end-to-end (see KNOWN_ISSUES § issue #24).
 # GFLOW_CLI_LOCALE=en-US
+
+# -----------------------------------------------------------------------------
+# Headless Daemon (gflow serve)
+# -----------------------------------------------------------------------------
+
+# API Token header for gflow serve authentication (required when binding to non-local interface, e.g. 0.0.0.0).
+# GFLOW_DAEMON_TOKEN=
+
+# Port for gflow serve. Default is 8000.
+# GFLOW_DAEMON_PORT=8000
+

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/.github/workflows/ci.yml

@@ -16,7 +16,7 @@ jobs:
     name: Secret scan (gitleaks)
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
         with:
           fetch-depth: 0  # full history so gitleaks can diff against base
 
@@ -25,6 +25,20 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
+  # ── Security gate: dependency CVE audit against locked deps ──────────────
+  deps-audit:
+    name: Dependency audit (pip-audit)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v7
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+      - name: Audit locked dependencies for known CVEs
+        # Fails the build on any known advisory. Accept later via: pip-audit --ignore-vuln <GHSA-id>
+        run: |
+          uv export --frozen --format requirements-txt --no-emit-project > requirements-audit.txt
+          uvx pip-audit -r requirements-audit.txt
+
   # ── Main test matrix ──────────────────────────────────────────────────────
   test:
     runs-on: ubuntu-latest
@@ -32,7 +46,7 @@ jobs:
       matrix:
         python-version: ["3.11", "3.12", "3.13"]
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
 
       - name: Install uv
         uses: astral-sh/setup-uv@v7
@@ -88,7 +102,7 @@ jobs:
         github.event.pull_request.head.repo.full_name == github.repository
       )
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
         with:
           fetch-depth: 0  # shallow clones break blame / new-code detection
 

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/.github/workflows/governance-advisory.yml

@@ -19,7 +19,7 @@ jobs:
     name: Materiality + traceability (advisory)
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
         with:
           fetch-depth: 0 # full history so `git diff origin/<base>..HEAD` resolves
 

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/.github/workflows/governance-benchmark.yml

@@ -18,7 +18,7 @@ jobs:
     name: Materiality gate backtest
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
         with:
           fetch-depth: 0 # full history — the backtest replays every commit
 

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/.github/workflows/release.yml

@@ -19,7 +19,7 @@ jobs:
       ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION: true
       NODE_VERSION: '22'
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
         with:
           fetch-depth: 0
 

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/.gitignore

@@ -92,3 +92,4 @@ worktrees/
 
 # Understand Anything (local knowledge graph)
 .understand-anything/
+.worktrees

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/AGENTS.md

@@ -58,6 +58,7 @@ Or invoke the wrapper: `/gflow:check`.
 - Structured logging only (`structlog`) — **never** raw `print()` or `import logging` in `src/`.
 - Errors as RFC 9457 Problem Details with stable per-class exit codes (3–22, e.g. 16 is the `DataStoreError` family, 19 `SceneConcatError`, 20 `FrameExtractionError`, 21 `ChainPartialError`, 22 `UpscaleUnavailableError`). See `src/gflow_cli/errors.py::EXIT_CODE_MAP` for the complete mapping.
 - 100-char line length, `ruff` configured. Imports sorted by `ruff` (isort rules).
+- **MCP & CLI Schema Symmetry**: Any updates or additions to user-facing CLI command parameters (e.g., `gflow image t2i`, `gflow video`) must be mirrored in the corresponding MCP tool definitions. Never add option/argument fields to Click commands without updating the MCP server implementation. This symmetry is enforced programmatically in CI via `tests/mcp/test_server.py`.
 
 ## PR instructions
 
@@ -80,7 +81,7 @@ The `skills/` directory ships installable agent skill docs in plain Markdown wit
 | `status` | [`skills/status/SKILL.md`](skills/status/SKILL.md) | Show current plan state, progress, and next unchecked task |
 | `pr-council-review` | [`skills/pr-council-review/SKILL.md`](skills/pr-council-review/SKILL.md) | Multi-dimensional PR council review |
 
-**Cursor / Aider / Codex / Gemini CLI:** paste or include the relevant `SKILL.md` in your system context.
+**Cursor / Aider / Codex / Gemini CLI (`agy`):** paste or include the relevant `SKILL.md` in your system context. Note: in the `agy` TUI prompt, custom slash commands (e.g. `/gflow:pr-council-review`) are blocked by the TUI's command parser. Type them as plain text without the leading slash (e.g. `gflow:pr-council-review`, `gflow:branch-review`, or `gflow:check`) to trigger the corresponding agent skill workflow.
 **Claude Code:** the `/gflow:` slash commands in `.claude/commands/gflow/` are auto-discovered when the project is open — no extra setup needed. To register a skill globally, copy the command file to `~/.claude/commands/`.
 **Custom agents:** fetch `skills/gflow-cli/SKILL.md` into your knowledge base before answering gflow questions.
 

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/CHANGELOG.md

@@ -7,6 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.21.0] — 2026-06-26
+
+### Added
+
+- **MCP server** (`gflow mcp run`): a [Model Context Protocol](https://modelcontextprotocol.io) server over **stdio** that exposes gflow's image / video / data operations to MCP-aware agents (Claude Desktop, Cursor, VS Code) as JSON-RPC **tools, resources, and prompts**. Point the client at `gflow mcp run` (example config in `gflow mcp run --help` and [docs/MCP.md](docs/MCP.md)). `gflow mcp setup --target <claude-desktop|cursor|vscode>` is scaffolded for future auto-configuration.
+- **MCP over HTTP/SSE** (`gflow serve`): serves the same MCP server over Server-Sent Events — stream at `/sse`, POST messages to `/messages/`. Binds `127.0.0.1:8000` by default; non-loopback binds require `GFLOW_DAEMON_TOKEN`. Foundation for the forthcoming Gflow Studio Web UI and REST `/api/v1` surface.
+- **Daemon & generation-queue scaffolding** (internal foundation): a FastAPI lifespan daemon, a `FlowWorker` background processor, and a SQLite-backed generation queue (`QueueRepository` + migration `0007_queue`, swept to `failed` on restart). Lays the groundwork for queued asynchronous generation; not yet wired into a user command (`gflow serve` currently runs the MCP/SSE server only).
+
+### Fixed
+
+- **Security — `cryptography` advisory** ([GHSA-537c-gmf6-5ccf](https://github.com/advisories/GHSA-537c-gmf6-5ccf)): bumped the locked `cryptography` from 48.0.0 to 49.0.0 (transitive dependency).
+
+### Changed
+
+- **CI — dependency CVE gate**: added a `pip-audit` job that audits the locked dependency set on every PR and fails on known advisories.
+- **Code health**: SonarCloud cleanup sweep across the CLI, API, transport drivers, and movie/manifest layers (cognitive-complexity, duplicate-literal, and unused-argument refactors) with no behavioral change.
+
 ## [0.20.1] — 2026-06-16
 
 ### Fixed
@@ -1565,7 +1582,8 @@ shell-script template that branches on these codes.
 
 First skeleton. Not functional end-to-end yet.
 
-[Unreleased]: https://github.com/ffroliva/gflow-cli/compare/v0.20.1...HEAD
+[Unreleased]: https://github.com/ffroliva/gflow-cli/compare/v0.21.0...HEAD
+[0.21.0]: https://github.com/ffroliva/gflow-cli/compare/v0.20.1...v0.21.0
 [0.20.1]: https://github.com/ffroliva/gflow-cli/compare/v0.20.0...v0.20.1
 [0.20.0]: https://github.com/ffroliva/gflow-cli/compare/v0.19.0...v0.20.0
 [0.19.0]: https://github.com/ffroliva/gflow-cli/compare/v0.18.0...v0.19.0

gflow_cli-0.21.0/GEMINI.md

@@ -0,0 +1,31 @@
+# GEMINI.md
+
+> Project memory hub for **Gemini CLI**. The universal coding-agent rules for any tool (Cursor, Codex, Aider, Gemini CLI, etc.) live in [AGENTS.md](AGENTS.md) — this file carries Gemini-specific session protocol only.
+
+## What this project is
+
+`gflow-cli` is an unofficial Python CLI that drives [Google Flow](https://labs.google/fx/tools/flow) (Veo image-to-video, Imagen text-to-image) from the terminal by reverse-engineering Flow's private REST API. See [README.md](README.md) for the user-facing overview.
+
+## On every session start
+
+1. Read **[AGENTS.md](AGENTS.md)** — universal rules every agent must follow.
+2. Read **[docs/INDEX.md](docs/INDEX.md)** — routing layer for all project docs and commands.
+3. Pull deeper context on demand (type as plain text in the `agy` TUI prompt):
+   - Current task / where we left off → `gflow:status`
+   - Starting a new feature → `gflow:predict` → `gflow:scenario` → `gflow:plan <feature>`
+   - Touching auth or reCAPTCHA → `gflow:known-issues`
+   - Cutting a release → `gflow:release`
+   - Before any commit → `gflow:check`
+
+## Gemini-specific
+
+- Use specialized skills when relevant (e.g., `find-docs` for library research, `pr-council-review` for PR audits).
+- Maintain memory via the `mcp-mempalace` tool if available.
+- Prioritize **turn efficiency** and **high-signal output**.
+
+## Active phase
+
+- **Decoupled Daemon/Worker Plan:** The blueprint for the headless SSE Daemon, SQLite generation queue, and Tauri/React editor is scheduled in [PLAN.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-23-mcp-ui-worker-integration/PLAN.md) and [SCENARIO.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-23-mcp-ui-worker-integration/SCENARIO.md).
+- **Core Lesson (Retrospective):** Kept `gflow-cli` strictly headless (running Uvicorn and FastMCP over localhost HTTP/SSE). Bypassed browser context locks by serializing task writes in SQLite queue, allowing parallel client database reads via WAL mode.
+
+See [PLAN.md](PLAN.md) or type `gflow:status` for the current task. Type `gflow:plan <feature>` to create a new feature plan.

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gflow-cli
-Version: 0.20.1
+Version: 0.21.0
 Summary: Unofficial CLI for Google Flow — drive Veo image-to-video generations from the terminal.
 Project-URL: Homepage, https://github.com/ffroliva/gflow-cli
 Project-URL: Issues, https://github.com/ffroliva/gflow-cli/issues
@@ -39,13 +39,17 @@ Classifier: Topic :: Multimedia :: Video
 Requires-Python: >=3.11
 Requires-Dist: browser-cookie3>=0.20.1
 Requires-Dist: click>=8.1.0
+Requires-Dist: fastapi>=0.115.0
 Requires-Dist: httpx>=0.27.0
+Requires-Dist: mcp>=1.0.0
 Requires-Dist: platformdirs>=4.0.0
 Requires-Dist: playwright>=1.45.0
 Requires-Dist: pydantic-settings>=2.5.0
 Requires-Dist: rich>=13.7.0
+Requires-Dist: sse-starlette>=2.0.0
 Requires-Dist: structlog>=24.0.0
 Requires-Dist: tenacity>=8.2
+Requires-Dist: uvicorn[standard]>=0.34.0
 Provides-Extra: chain
 Requires-Dist: av>=12; extra == 'chain'
 Provides-Extra: dev
@@ -54,7 +58,7 @@ Requires-Dist: numpy>=1.24; extra == 'dev'
 Requires-Dist: pyright>=1.1.0; extra == 'dev'
 Requires-Dist: pytest-asyncio>=0.23.0; extra == 'dev'
 Requires-Dist: pytest>=8.0.0; extra == 'dev'
-Requires-Dist: ruff>=0.15.16; extra == 'dev'
+Requires-Dist: ruff==0.15.18; extra == 'dev'
 Provides-Extra: gcs
 Requires-Dist: gcsfs>=2024.2.0; extra == 'gcs'
 Requires-Dist: universal-pathlib>=0.2.5; extra == 'gcs'
@@ -67,7 +71,7 @@ Description-Content-Type: text/markdown
 
 # gflow-cli
 
-> **Unofficial Python CLI for Google Flow.** Drive [Veo](https://labs.google/fx/tools/flow) (image-to-video, text-to-video) and Imagen (text-to-image) generations from your terminal — scripted, batched, pipeline-friendly.
+> Unofficial Python CLI for Google Flow. Drive [Veo](https://labs.google/fx/tools/flow) (image-to-video, text-to-video) and Imagen (text-to-image) from your terminal: scripted, batched, pipeline-ready.
 
 [![PyPI version](https://img.shields.io/pypi/v/gflow-cli.svg)](https://pypi.org/project/gflow-cli/)
 [![CI](https://github.com/ffroliva/gflow-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/ffroliva/gflow-cli/actions/workflows/ci.yml)
@@ -80,26 +84,25 @@ Description-Content-Type: text/markdown
 [![Tests: TDD](https://img.shields.io/badge/tests-TDD-brightgreen.svg)](CONTRIBUTING.md)
 [![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=ffroliva_gflow-cli&metric=alert_status)](https://sonarcloud.io/summary/new_code?id=ffroliva_gflow-cli)
 
-> ⚠️ **Unofficial. Reverse-engineered. Not affiliated with Google.** Endpoints can change at any time. Full [DISCLAIMER](DISCLAIMER.md).
+> ⚠️ **Unofficial, reverse-engineered, not affiliated with Google.** Endpoints can change without notice. Read the full [DISCLAIMER](DISCLAIMER.md).
 >
-> 🌐 **Headed-browser today.** gflow drives Flow via a persistent Playwright Chromium profile — Google's auth + reCAPTCHA gates currently require it. See [Architecture & current limitations](#architecture--current-limitations) for the contributor opportunity.
-
+> 🌐 **Headed browser today.** gflow drives Flow through a persistent Playwright Chromium profile, because Google's auth and reCAPTCHA gates require it. The [Architecture](#architecture--current-limitations) section shows where you can help.
 
 ## Why gflow-cli?
 
-For Google AI Ultra / Pro subscribers with Veo credits and batch workloads:
+You pay for Google AI Ultra or Pro, you have Veo credits, and you run real batch work. gflow-cli gives you:
 
-- **Burn credits efficiently** — `for p in $(cat prompts.txt); do gflow image t2i "$p"; done` _(image batching, plus `gflow video t2v`/`i2v`/`r2v`, all ship today)_
-- **Reuse a subject across shots** — `gflow character create` mints a Flow **Character** (face + body reference) so the same person appears consistently from generation to generation
-- **Build pipelines** — wire Veo into your content automation, AI video stack, or batch experiments
-- **Stay in the terminal** — no Chromium UI, no clicking through dialogs (after a one-time `gflow auth login`)
+- **Batch generation.** Loop prompts straight from the shell: `for p in $(cat prompts.txt); do gflow image t2i "$p"; done`. Image batching plus `gflow video t2v` / `i2v` / `r2v` all ship today.
+- **Consistent subjects.** `gflow character create` mints a Flow Character (face and body reference) so the same person appears from one generation to the next.
+- **Pipelines.** Wire Veo into your content automation, AI-video stack, or batch experiments.
+- **Terminal-native.** After one `gflow auth login`, you stay in the shell. No clicking through dialogs.
 
-Same Veo + Imagen models, same quality, same Ultra/Pro billing — programmatic.
+Same Veo and Imagen models, same quality, same Ultra/Pro billing, now programmatic.
 
 ## 60-second quick start
 
 ```bash
-# 1 · Install (uv recommended — also: pip install gflow-cli)
+# 1 · Install (uv recommended; also: pip install gflow-cli)
 uv tool install gflow-cli
 uv tool run --from gflow-cli playwright install chromium     # one-time, ~150 MB
 
@@ -114,26 +117,25 @@ gflow video t2v "Slow cinematic push-in on a sunlit forest clearing" --aspect 16
 gflow character create --project <id> --name "Aria" --face-prompt "..." --body-prompt "..."
 ```
 
-Outputs land under `$GFLOW_CLI_OUTPUT_DIR` unless
-[`GFLOW_CLI_STORAGE_URI`](docs/EXTERNAL_STORAGE.md) sends generated assets to
-S3, MinIO, or Google Cloud Storage. First call is ~30–90 s while Chromium warms;
-subsequent calls reuse the warm session.
+Outputs land under `$GFLOW_CLI_OUTPUT_DIR`, or you can route them to S3, MinIO, or Google Cloud Storage with [`GFLOW_CLI_STORAGE_URI`](docs/EXTERNAL_STORAGE.md). The first call takes 30 to 90 seconds while Chromium warms up; later calls reuse the warm session.
 
 > **Why `--browser chrome`?** Google rejects Playwright's bundled Chromium. The CLI fails fast with a friendly error (`AuthBrowserRejectedError`, exit code 14) if you pick anything else.
 
-## In-depth quick start
+For the full 10-minute walkthrough with troubleshooting and multi-account setup, see **[USER_GUIDE: Journey 1](docs/USER_GUIDE.md#journey-1--first-time-setup-10-minutes)**.
 
-See **[USER_GUIDE — Journey 1: First-time setup](docs/USER_GUIDE.md#journey-1--first-time-setup-10-minutes)** for the 10-minute walkthrough with troubleshooting, multi-account setup, and the structured-log primer.
+## Examples
 
-## Demo
+One command in, real Flow output back. Left: `gflow image t2i` generating a photorealistic scene in your library. Right: a frame-to-frame transform.
+
+![gflow-cli examples: text-to-image generation, and a before/after frame transform](https://raw.githubusercontent.com/ffroliva/gflow-cli/main/docs/assets/examples.webp)
 
-![gflow image t2i — single 9:16 prompt, streaming structlog output, PNG on disk](docs/assets/example-run.gif)
+## Demo
 
-*A single `gflow image t2i "..." --aspect 9:16 --model nano2` call against a logged-in Pro/Ultra profile. Terminal shows the streaming `structlog` JSON for the run, the final `ls` of the written PNG, and nothing else — Chromium drives the Flow editor silently in the background.*
+![gflow image t2i runs a single 9:16 prompt, streams structlog output, and writes a PNG to disk](https://raw.githubusercontent.com/ffroliva/gflow-cli/main/docs/assets/example-run.gif)
 
-Reproduce the recording: [`scripts/record_demo.ps1`](scripts/record_demo.ps1) (Windows + OBS + ffmpeg + gifski).
+A single `gflow image t2i "..." --aspect 9:16 --model nano2` call against a logged-in Pro/Ultra profile. The terminal streams the run's `structlog` JSON, then lists the written PNG. Chromium drives the Flow editor silently in the background.
 
-**▶ More demos** — split-screen (terminal command + Flow generating, side-by-side) and other formats: **[docs/DEMOS.md](docs/DEMOS.md)**.
+Reproduce the recording with [`scripts/record_demo.ps1`](scripts/record_demo.ps1) (Windows, OBS, ffmpeg, gifski). More formats, including the side-by-side split-screen: **[docs/DEMOS.md](docs/DEMOS.md)**.
 
 ## Documentation
 
@@ -143,25 +145,24 @@ Reproduce the recording: [`scripts/record_demo.ps1`](scripts/record_demo.ps1) (W
 |---|---|
 | 🎯 **Getting started** | [User Guide](docs/USER_GUIDE.md) · [Usage](docs/USAGE.md) · [Configuration](docs/CONFIGURATION.md) |
 | **Storage & catalog** | [External Storage](docs/EXTERNAL_STORAGE.md) · [Data Layer](docs/DATA_LAYER.md) |
-| 🎭 **Characters** | [Characters](docs/CHARACTER.md) — reusable subjects (`gflow character`) |
+| 🎭 **Characters** | [Characters](docs/CHARACTER.md), reusable subjects (`gflow character`) |
 | 🔐 **Auth & sessions** | [Authentication](docs/AUTHENTICATION.md) · [Known issues](KNOWN_ISSUES.md) |
-| 🏗️ **Internals** | [Architecture](docs/ARCHITECTURE.md) · [Security](docs/SECURITY.md) · [Debugging](docs/DEBUGGING.md) |  
+| 🏗️ **Internals** | [Architecture](docs/ARCHITECTURE.md) · [Security](docs/SECURITY.md) · [Debugging](docs/DEBUGGING.md) |
 | 📦 **Releases** | [Changelog](CHANGELOG.md) · [Roadmap](ROADMAP.md) · [Release protocol](RELEASE.md) · [Project status](docs/PROJECT_STATUS.md) |
 | 🤝 **Contributing** | [Contributing](CONTRIBUTING.md) · [Development](docs/DEVELOPMENT.md) · [GitHub workflow](docs/GITHUB.md) |
 
-
 ## For AI agents & LLMs
 
-gflow-cli ships three agent entry points — pick the one your tool reads first.
+gflow-cli ships three agent entry points. Pick the one your tool reads first.
 
 | File | Audience | Tools |
 |---|---|---|
-| [**AGENTS.md**](AGENTS.md) | Universal coding-agent spec | Cursor · Codex · Aider · Gemini CLI · Jules · Devin · Windsurf · Zed · Warp · opencode · Copilot · 60k+ repos |
+| [**AGENTS.md**](AGENTS.md) | Universal coding-agent spec | Cursor · Codex · Aider · Gemini CLI · Jules · Devin · Windsurf · Zed · Warp · opencode · Copilot |
 | [**CLAUDE.md**](CLAUDE.md) | Claude Code's auto-loaded memory | Claude Code |
-| [**llms.txt**](llms.txt) | LLM-readable summary (llmstxt.org format) | Paste into ChatGPT / Claude / Gemini to onboard the model |
+| [**llms.txt**](llms.txt) | LLM-readable summary (llmstxt.org format) | Paste into ChatGPT, Claude, or Gemini to onboard the model |
 | [`skills/gflow-cli/SKILL.md`](skills/gflow-cli/SKILL.md) | Claude Code Skill | Symlink into `~/.claude/skills/` |
 
-**Onboarding any agent in one line:** paste this into your agent of choice —
+Onboard any agent in one line. Paste this into your agent of choice:
 
 > *"Read [AGENTS.md](https://github.com/ffroliva/gflow-cli/blob/main/AGENTS.md) and [docs/INDEX.md](https://github.com/ffroliva/gflow-cli/blob/main/docs/INDEX.md), then help me with my Flow batch."*
 
@@ -175,25 +176,27 @@ gflow CLI  →  Provider (interchangeable)  →  Flow (ui_automation) / Mock (te
                               aisandbox-pa.googleapis.com  (Google's private Flow API)
 ```
 
-**Current transport:** `ui_automation` — drives Flow via a persistent Playwright Chromium profile. Production-stable, end-to-end verified per release (see [LIVE_VERIFICATION_*](docs/) per-release evidence files).
+**Current transport:** `ui_automation` drives Flow through a persistent Playwright Chromium profile. It is production-stable and verified end-to-end every release (see the per-release `LIVE_VERIFICATION_*` evidence files).
 
-**What's blocked:** A pure HTTP transport for video generation. The video upload endpoint returns HTTP 401 under non-Chrome browsers + a reCAPTCHA mint we cannot reproduce headlessly. Three earlier HTTP strategies (`evaluate_fetch` / `bearer` / `sapisidhash`) live under `src/gflow_cli/api/transports/experimental/` — they are importable for research but not on the production critical path.
+**What's blocked:** a pure HTTP transport for video generation. The video upload endpoint returns HTTP 401 under non-Chrome browsers plus a reCAPTCHA mint we cannot reproduce headlessly. Three earlier HTTP strategies (`evaluate_fetch`, `bearer`, `sapisidhash`) live under `src/gflow_cli/api/transports/experimental/` for research, off the production path.
 
-**How you can help:** If you have successfully driven `aisandbox-pa.googleapis.com` from outside a real Chrome session — or have insight into Google's anti-bot stack here — please open an issue. A working REST transport would unlock serverless deployments, true horizontal concurrency, and roughly 10× the project's reach. Details: [docs/ARCHITECTURE.md § Headed-browser dependency](docs/ARCHITECTURE.md#headed-browser-dependency--current-limitation).
+**How you can help:** if you have driven `aisandbox-pa.googleapis.com` from outside a real Chrome session, or you understand Google's anti-bot stack here, please open an issue. A working REST transport would unlock serverless deployments, true horizontal concurrency, and roughly 10x the project's reach. Details: [docs/ARCHITECTURE.md § Headed-browser dependency](docs/ARCHITECTURE.md#headed-browser-dependency--current-limitation).
 
 ## Project status
 
-**v0.12.0 — alpha.** Three new capabilities. **`gflow character`** mints reusable, project-scoped Flow **Character** entities — a named subject with reference images, an optional voice, and an optional personality — so the same subject stays consistent across generations (`create` / `list` / `show` / `voices`, #145). **`gflow scene`** composes ordered clips into a scene and renders a credit-free, server-side **extended video** (no local ffmpeg). **`gflow video chain`** links last-frame image-to-video clips from a JSONL manifest into one continuous sequence. This release also fixes create-project generation when Flow surfaces Agent mode as a docked chat panel. Baseline: Image (T2I / I2I / upload) + Video T2V / I2V / R2V live end-to-end on `ui_automation`, with a video `--model` picker (5 Veo models) + `--duration` / `--count` (v0.11.0 repaired `gflow video i2v`, issue #125, and hardened image-model selection for non-English Flow UIs, #94; v0.10.0 added `--json` across every generation command, a `gflow models` catalog, per-model reference caps, persisted profile identity, external S3 / MinIO / GCS storage, and `gflow data prune`). Only video `batch` (manifest runner) is still queued for Phase B — use a shell for-loop until then ([USAGE](docs/USAGE.md#gflow-video-batch)). Full milestone history → [docs/PROJECT_STATUS.md](docs/PROJECT_STATUS.md). Changelog → [CHANGELOG.md](CHANGELOG.md). Where the project is heading → [ROADMAP.md](ROADMAP.md).
+**Alpha.** Image (t2i, i2i, upload) and video (t2v, i2v, r2v) run end-to-end on `ui_automation`, with a 5-model Veo picker plus `--duration` and `--count`. Recent additions: `gflow character` for reusable subjects, `gflow scene` for credit-free server-side stitching, and `gflow video chain` for linked clips. Video `batch` is still queued for Phase B, so use a shell for-loop until then ([USAGE](docs/USAGE.md#gflow-video-batch)).
+
+Full milestone history lives in [CHANGELOG.md](CHANGELOG.md). Where the project is heading: [ROADMAP.md](ROADMAP.md).
 
 ## License & legal
 
-[MIT License](LICENSE) © 2026 Flavio Oliva (`ffroliva`). The MIT license covers `gflow-cli`'s code only — it does not grant rights to Flow, Veo model output, or any Google service. Google's own terms (Labs Additional Terms, Ultra/Pro subscription terms) govern your generations. See [DISCLAIMER](DISCLAIMER.md).
+[MIT License](LICENSE) © 2026 Flavio Oliva (`ffroliva`). The MIT license covers `gflow-cli`'s code only. It grants no rights to Flow, Veo model output, or any Google service. Google's own terms (Labs Additional Terms, Ultra/Pro subscription terms) govern your generations. See the [DISCLAIMER](DISCLAIMER.md).
 
 ## Acknowledgements
 
-- [`edge-tts`](https://github.com/rany2/edge-tts) — design inspiration for community SDKs over private cloud APIs.
-- [`googleapis/python-genai`](https://github.com/googleapis/python-genai) — the official Veo SDK that a future provider release may alias.
-- [Keysight — *Google Labs – Flow AI with Veo3: A Network Traffic Analysis*](https://www.keysight.com/blogs/en/tech/nwvs/2025/08/04/google-flow-ai-har-analysis) — independent capture that helped validate the captured route patterns.
+- [`edge-tts`](https://github.com/rany2/edge-tts), design inspiration for community SDKs over private cloud APIs.
+- [`googleapis/python-genai`](https://github.com/googleapis/python-genai), the official Veo SDK that a future provider release may alias.
+- [Keysight, *Google Labs – Flow AI with Veo3: A Network Traffic Analysis*](https://www.keysight.com/blogs/en/tech/nwvs/2025/08/04/google-flow-ai-har-analysis), an independent capture that helped validate the route patterns.
 
 ---
 
@@ -208,4 +211,4 @@ gflow CLI  →  Provider (interchangeable)  →  Flow (ui_automation) / Mock (te
 [![GitHub repo size](https://img.shields.io/github/repo-size/ffroliva/gflow-cli?cacheSeconds=3600)](https://github.com/ffroliva/gflow-cli)
 [![PyPI downloads](https://static.pepy.tech/badge/gflow-cli/month)](https://pepy.tech/project/gflow-cli)
 
-If `gflow-cli` saves you time, please ⭐ the repo — it is the cheapest way to support the project.
+If `gflow-cli` saves you time, please ⭐ the repo. It is the cheapest way to support the project.

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/PLAN.md

@@ -358,7 +358,9 @@ The video-generation feature has its own sub-phase plan (spike → Phase A → P
   - **Phase 3 (PR #90 / [#63](https://github.com/ffroliva/gflow-cli/issues/63), 2026-05-26, develop `9a0896a8`):** replaced `FRAME_SLOTS_STRUCT` with the locale-free pattern `div[type='button'][aria-haspopup='dialog']` (verified via DOM probe — matches exactly 2). Also fixed the End-frame OOB index after Start is attached. **I2V live-proof on de-DE: 124 s, mp4 with `ftyp` magic bytes, both `frame_attached` events fired (Start + End).**
   - **Phase 4 (Task #6, 2026-05-26, branch `claude/next-quick-win-gBPqS`, PR #93):** `NEW_PROJECT_SELECTORS` expanded to all 14 locales (icon-first tier + 14-locale text tier); English-only ARIA fallbacks (`[aria-label*='New project']`, `[aria-label*='Project']`) removed. `SUBMIT_BUTTON_SELECTORS` drops its English-only `button[aria-label*="Create"]` entry — `arrow_forward` icon selectors cover it in all locales. Both tuples are now fully locale-invariant. Note: issue #24 was closed 2026-05-24 after Phases 1–3; Phase 4 is cosmetic tail work. `--lang=en-US` retained only to stabilise `IMAGE_MODEL_OPTION_SELECTORS` (product names like "Nano Banana 2" may be localised). Removing it requires converting the image model picker to a structural anchor — tracked as issue #94 (Phase 5 below). **R2V live e2e on non-EN not yet exercised** — still open.
   - **Phase 5 (2026-05-30, branch `claude/issue-94-staleness-check-MnsEY`, PR #127):** `IMAGE_MODEL_OPTION_SELECTORS` and `VIDEO_MODEL_OPTION_SELECTORS` converted from `dict[Model, str]` to `dict[Model, tuple[str, ...]]` (cascade discipline; Tier 1 structural slots reserved for future DOM-probe-confirmed anchors). `--lang=en-US` removed from Chromium launch args — locale controlled by `locale=locale_env` Playwright kwarg (persists across all navigations including `/project/<uuid>` deep-links) + `FLOW_URL`'s `?hl=en` on initial load. Branded model names confirmed locale-stable. Four new `TestSelectorLocaleInvariance` tests + four `TestSelectImageModel` runtime tests. **R2V live e2e on non-EN still pending (owner gate — requires authenticated non-EN Chrome profile).**
-- [ ] **Model Context Protocol (MCP) Server.** (Backlog) Expose core gflow-cli tools via MCP for language-agnostic agentic access.
+- [ ] **Model Context Protocol (MCP) Server.** (Backlog) Expose core gflow-cli tools via MCP for language-agnostic agentic access. Planned in [PREDICT.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-22-mcp-server/PREDICT.md) / [SCENARIO.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-22-mcp-server/SCENARIO.md) / [PLAN.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-22-mcp-server/PLAN.md).
+- [ ] **Prompt Expansion ("Creative Director" mode).** (Backlog) Add an option to expand prompts using Google's official 5-component formula via Gemini. Planned in [PREDICT.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-22-prompt-expansion/PREDICT.md) / [SCENARIO.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-22-prompt-expansion/SCENARIO.md) / [PLAN.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-22-prompt-expansion/PLAN.md).
+- [ ] **Integrated Filmmaking Studio, Flow Worker & MCP SSE Service.** (Backlog) Port google-flow-worker, construct a local FastAPI/React filmmaking studio dashboard, and support HTTP/SSE MCP. Planned in [DESIGN.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-23-mcp-ui-worker-integration/DESIGN.md) / [PLAN.md](file:///C:/development/github/gflow-cli/docs/superpowers/plans/2026-06-23-mcp-ui-worker-integration/PLAN.md).
 - [x] **Issue #92: Google account identity persistence shipped 2026-05-28 (PR #110).** After every `gflow auth login`, both auth strategies write the verified email to `$GFLOW_CLI_HOME/profile_<name>/.gflow_account`. `ProfileMeta.google_account` surfaces it; `gflow auth list` and `gflow auth list --json` display it. First-login auto-rename: when no `--profile` flag was given and the only profile is named `default`, it is renamed to the email local-part. `profile_store.rename_profile()` primitive added. Zero-credit smoke test (`tests/smoke/test_profile_account_smoke.py`) ships with backfill path for pre-existing profiles. LLM council (9-dim) run; all must-fix items applied before merge. See `KNOWN_ISSUES.md` § Resolved for full detail.
 - [x] **`/gflow:pr-council-review` slash command shipped 2026-05-26 (PR #97).** Multi-dimensional LLM council for open PRs (4 baseline + 8 adaptive dimensions, mandatory memory-slug binding, draft-PR guard, YELLOW escape valve, live-verify gate). Validated on PR #93; self-audited by 3-agent meta-council surfacing 13 must-fix items applied before merge. See memory `[[llm-council-code-review-pr93]]`.
   - **Phase A (Backlog — Portability):** extract command body into `skills/pr-council-review/SKILL.md` so Gemini CLI / Codex / Cursor / Aider can consume it. Keep `.claude/commands/gflow/pr-council-review.md` as a thin wrapper. Memory: `[[pr-council-review-portability-backlog]]`.
@@ -662,6 +664,19 @@ Today the CLI writes media to `$GFLOW_CLI_OUTPUT_DIR` on the local filesystem. P
 
 ---
 
+### Unified Multi-Account Management — BACKLOG
+
+**Background:** A key strength of the gflow architecture is its capacity to drive and coordinate across multiple Google Accounts in a unified way. This enables horizontal scale, credit pooling, and parallel batch generation bypassing individual account quotas.
+
+**Requirements & Implications:**
+- **Cross-Account Session Inventory:** A unified credential manager tracking persistent browser context directories (`profile_<email_local>`) and session lifespans.
+- **Concurrent Warm Context Pool:** A background daemon scheduling across a warm browser context pool representing multiple active Google Accounts (e.g., executing parallel worker queues on different profiles).
+- **Round-Robin Queue Dispatcher:** A dispatcher that distributes task batches dynamically across profiles based on quota availability or idle status.
+- **Aggregated Provenance Mapping:** The local `gflow.db` data layer indexes projects, operations, and downloaded files back to the generating Google identity.
+- **Studio UI Integration:** Dropdowns displaying connected profiles, quota/credit tracking, active account tags on workflow nodes, and single-click profile swapping.
+
+---
+
 ## 5. Decision log (ADRs in miniature)
 
 | # | Decision | Rationale |

gflow_cli-0.21.0/README.md

@@ -0,0 +1,143 @@
+# gflow-cli
+
+> Unofficial Python CLI for Google Flow. Drive [Veo](https://labs.google/fx/tools/flow) (image-to-video, text-to-video) and Imagen (text-to-image) from your terminal: scripted, batched, pipeline-ready.
+
+[![PyPI version](https://img.shields.io/pypi/v/gflow-cli.svg)](https://pypi.org/project/gflow-cli/)
+[![CI](https://github.com/ffroliva/gflow-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/ffroliva/gflow-cli/actions/workflows/ci.yml)
+[![Release](https://github.com/ffroliva/gflow-cli/actions/workflows/release.yml/badge.svg)](https://github.com/ffroliva/gflow-cli/actions/workflows/release.yml)
+[![Python versions](https://img.shields.io/pypi/pyversions/gflow-cli.svg)](https://pypi.org/project/gflow-cli/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
+[![Status: alpha](https://img.shields.io/badge/status-alpha-orange.svg)](docs/PROJECT_STATUS.md)
+[![Code style: ruff](https://img.shields.io/badge/code%20style-ruff-000000.svg)](https://github.com/astral-sh/ruff)
+[![Type checked: pyright](https://img.shields.io/badge/type%20checked-pyright-blue.svg)](https://github.com/microsoft/pyright)
+[![Tests: TDD](https://img.shields.io/badge/tests-TDD-brightgreen.svg)](CONTRIBUTING.md)
+[![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=ffroliva_gflow-cli&metric=alert_status)](https://sonarcloud.io/summary/new_code?id=ffroliva_gflow-cli)
+
+> ⚠️ **Unofficial, reverse-engineered, not affiliated with Google.** Endpoints can change without notice. Read the full [DISCLAIMER](DISCLAIMER.md).
+>
+> 🌐 **Headed browser today.** gflow drives Flow through a persistent Playwright Chromium profile, because Google's auth and reCAPTCHA gates require it. The [Architecture](#architecture--current-limitations) section shows where you can help.
+
+## Why gflow-cli?
+
+You pay for Google AI Ultra or Pro, you have Veo credits, and you run real batch work. gflow-cli gives you:
+
+- **Batch generation.** Loop prompts straight from the shell: `for p in $(cat prompts.txt); do gflow image t2i "$p"; done`. Image batching plus `gflow video t2v` / `i2v` / `r2v` all ship today.
+- **Consistent subjects.** `gflow character create` mints a Flow Character (face and body reference) so the same person appears from one generation to the next.
+- **Pipelines.** Wire Veo into your content automation, AI-video stack, or batch experiments.
+- **Terminal-native.** After one `gflow auth login`, you stay in the shell. No clicking through dialogs.
+
+Same Veo and Imagen models, same quality, same Ultra/Pro billing, now programmatic.
+
+## 60-second quick start
+
+```bash
+# 1 · Install (uv recommended; also: pip install gflow-cli)
+uv tool install gflow-cli
+uv tool run --from gflow-cli playwright install chromium     # one-time, ~150 MB
+
+# 2 · Authenticate (one-time, opens a real Chrome window)
+gflow auth login --browser chrome
+
+# 3 · Generate
+gflow image t2i "a hot air balloon over Tokyo at sunrise"
+# or:
+gflow video t2v "Slow cinematic push-in on a sunlit forest clearing" --aspect 16:9
+# or mint a reusable Character (face + body reference):
+gflow character create --project <id> --name "Aria" --face-prompt "..." --body-prompt "..."
+```
+
+Outputs land under `$GFLOW_CLI_OUTPUT_DIR`, or you can route them to S3, MinIO, or Google Cloud Storage with [`GFLOW_CLI_STORAGE_URI`](docs/EXTERNAL_STORAGE.md). The first call takes 30 to 90 seconds while Chromium warms up; later calls reuse the warm session.
+
+> **Why `--browser chrome`?** Google rejects Playwright's bundled Chromium. The CLI fails fast with a friendly error (`AuthBrowserRejectedError`, exit code 14) if you pick anything else.
+
+For the full 10-minute walkthrough with troubleshooting and multi-account setup, see **[USER_GUIDE: Journey 1](docs/USER_GUIDE.md#journey-1--first-time-setup-10-minutes)**.
+
+## Examples
+
+One command in, real Flow output back. Left: `gflow image t2i` generating a photorealistic scene in your library. Right: a frame-to-frame transform.
+
+![gflow-cli examples: text-to-image generation, and a before/after frame transform](https://raw.githubusercontent.com/ffroliva/gflow-cli/main/docs/assets/examples.webp)
+
+## Demo
+
+![gflow image t2i runs a single 9:16 prompt, streams structlog output, and writes a PNG to disk](https://raw.githubusercontent.com/ffroliva/gflow-cli/main/docs/assets/example-run.gif)
+
+A single `gflow image t2i "..." --aspect 9:16 --model nano2` call against a logged-in Pro/Ultra profile. The terminal streams the run's `structlog` JSON, then lists the written PNG. Chromium drives the Flow editor silently in the background.
+
+Reproduce the recording with [`scripts/record_demo.ps1`](scripts/record_demo.ps1) (Windows, OBS, ffmpeg, gifski). More formats, including the side-by-side split-screen: **[docs/DEMOS.md](docs/DEMOS.md)**.
+
+## Documentation
+
+[**docs/INDEX.md**](docs/INDEX.md) is the master routing layer. Quick links:
+
+| Topic | Read |
+|---|---|
+| 🎯 **Getting started** | [User Guide](docs/USER_GUIDE.md) · [Usage](docs/USAGE.md) · [Configuration](docs/CONFIGURATION.md) |
+| **Storage & catalog** | [External Storage](docs/EXTERNAL_STORAGE.md) · [Data Layer](docs/DATA_LAYER.md) |
+| 🎭 **Characters** | [Characters](docs/CHARACTER.md), reusable subjects (`gflow character`) |
+| 🔐 **Auth & sessions** | [Authentication](docs/AUTHENTICATION.md) · [Known issues](KNOWN_ISSUES.md) |
+| 🏗️ **Internals** | [Architecture](docs/ARCHITECTURE.md) · [Security](docs/SECURITY.md) · [Debugging](docs/DEBUGGING.md) |
+| 📦 **Releases** | [Changelog](CHANGELOG.md) · [Roadmap](ROADMAP.md) · [Release protocol](RELEASE.md) · [Project status](docs/PROJECT_STATUS.md) |
+| 🤝 **Contributing** | [Contributing](CONTRIBUTING.md) · [Development](docs/DEVELOPMENT.md) · [GitHub workflow](docs/GITHUB.md) |
+
+## For AI agents & LLMs
+
+gflow-cli ships three agent entry points. Pick the one your tool reads first.
+
+| File | Audience | Tools |
+|---|---|---|
+| [**AGENTS.md**](AGENTS.md) | Universal coding-agent spec | Cursor · Codex · Aider · Gemini CLI · Jules · Devin · Windsurf · Zed · Warp · opencode · Copilot |
+| [**CLAUDE.md**](CLAUDE.md) | Claude Code's auto-loaded memory | Claude Code |
+| [**llms.txt**](llms.txt) | LLM-readable summary (llmstxt.org format) | Paste into ChatGPT, Claude, or Gemini to onboard the model |
+| [`skills/gflow-cli/SKILL.md`](skills/gflow-cli/SKILL.md) | Claude Code Skill | Symlink into `~/.claude/skills/` |
+
+Onboard any agent in one line. Paste this into your agent of choice:
+
+> *"Read [AGENTS.md](https://github.com/ffroliva/gflow-cli/blob/main/AGENTS.md) and [docs/INDEX.md](https://github.com/ffroliva/gflow-cli/blob/main/docs/INDEX.md), then help me with my Flow batch."*
+
+## Architecture & current limitations
+
+```text
+gflow CLI  →  Provider (interchangeable)  →  Flow (ui_automation) / Mock (tests) / [planned: Official Veo]
+                                              ↓
+                                      Playwright Chromium (headed login, headless after)
+                                              ↓
+                              aisandbox-pa.googleapis.com  (Google's private Flow API)
+```
+
+**Current transport:** `ui_automation` drives Flow through a persistent Playwright Chromium profile. It is production-stable and verified end-to-end every release (see the per-release `LIVE_VERIFICATION_*` evidence files).
+
+**What's blocked:** a pure HTTP transport for video generation. The video upload endpoint returns HTTP 401 under non-Chrome browsers plus a reCAPTCHA mint we cannot reproduce headlessly. Three earlier HTTP strategies (`evaluate_fetch`, `bearer`, `sapisidhash`) live under `src/gflow_cli/api/transports/experimental/` for research, off the production path.
+
+**How you can help:** if you have driven `aisandbox-pa.googleapis.com` from outside a real Chrome session, or you understand Google's anti-bot stack here, please open an issue. A working REST transport would unlock serverless deployments, true horizontal concurrency, and roughly 10x the project's reach. Details: [docs/ARCHITECTURE.md § Headed-browser dependency](docs/ARCHITECTURE.md#headed-browser-dependency--current-limitation).
+
+## Project status
+
+**Alpha.** Image (t2i, i2i, upload) and video (t2v, i2v, r2v) run end-to-end on `ui_automation`, with a 5-model Veo picker plus `--duration` and `--count`. Recent additions: `gflow character` for reusable subjects, `gflow scene` for credit-free server-side stitching, and `gflow video chain` for linked clips. Video `batch` is still queued for Phase B, so use a shell for-loop until then ([USAGE](docs/USAGE.md#gflow-video-batch)).
+
+Full milestone history lives in [CHANGELOG.md](CHANGELOG.md). Where the project is heading: [ROADMAP.md](ROADMAP.md).
+
+## License & legal
+
+[MIT License](LICENSE) © 2026 Flavio Oliva (`ffroliva`). The MIT license covers `gflow-cli`'s code only. It grants no rights to Flow, Veo model output, or any Google service. Google's own terms (Labs Additional Terms, Ultra/Pro subscription terms) govern your generations. See the [DISCLAIMER](DISCLAIMER.md).
+
+## Acknowledgements
+
+- [`edge-tts`](https://github.com/rany2/edge-tts), design inspiration for community SDKs over private cloud APIs.
+- [`googleapis/python-genai`](https://github.com/googleapis/python-genai), the official Veo SDK that a future provider release may alias.
+- [Keysight, *Google Labs – Flow AI with Veo3: A Network Traffic Analysis*](https://www.keysight.com/blogs/en/tech/nwvs/2025/08/04/google-flow-ai-har-analysis), an independent capture that helped validate the route patterns.
+
+---
+
+## Stats
+
+[![GitHub stars](https://img.shields.io/github/stars/ffroliva/gflow-cli?style=social&cacheSeconds=3600)](https://github.com/ffroliva/gflow-cli/stargazers)
+[![GitHub forks](https://img.shields.io/github/forks/ffroliva/gflow-cli?style=social&cacheSeconds=3600)](https://github.com/ffroliva/gflow-cli/network/members)
+[![GitHub watchers](https://img.shields.io/github/watchers/ffroliva/gflow-cli?style=social&cacheSeconds=3600)](https://github.com/ffroliva/gflow-cli/watchers)
+[![GitHub issues](https://img.shields.io/github/issues/ffroliva/gflow-cli?cacheSeconds=3600)](https://github.com/ffroliva/gflow-cli/issues)
+[![GitHub pull requests](https://img.shields.io/github/issues-pr/ffroliva/gflow-cli?cacheSeconds=3600)](https://github.com/ffroliva/gflow-cli/pulls)
+[![GitHub last commit](https://img.shields.io/github/last-commit/ffroliva/gflow-cli?cacheSeconds=3600)](https://github.com/ffroliva/gflow-cli/commits/main)
+[![GitHub repo size](https://img.shields.io/github/repo-size/ffroliva/gflow-cli?cacheSeconds=3600)](https://github.com/ffroliva/gflow-cli)
+[![PyPI downloads](https://static.pepy.tech/badge/gflow-cli/month)](https://pepy.tech/project/gflow-cli)
+
+If `gflow-cli` saves you time, please ⭐ the repo. It is the cheapest way to support the project.

{gflow_cli-0.20.1 → gflow_cli-0.21.0}/ROADMAP.md

@@ -23,14 +23,15 @@ Extends the data layer surface from read-only listing to inspection and selectiv
 - `gflow data export` — JSON / CSV / TSV
 - `gflow data prune` — retention controls (`--older-than`, `--keep-last-n`)
 
-## v0.11.0 — Local HTTP API + Web UI
+## v0.11.0 — Local Studio, Background Worker & MCP SSE Service (in progress / develop)
 
-The API and the UI ship together as one deliverable — neither is useful alone. `gflow ui` boots a local HTTP server on `127.0.0.1` that hosts both the API and the UI; everything stays loopback-only.
+The local Web UI Filmmaking Studio, background task worker, and MCP HTTP/SSE service are integrated into a single unified daemon interface under `gflow serve`.
 
-- `gflow ui` — single command, single port
-- Local REST API over the SQLite catalog with read endpoints for projects / images / videos / profiles
-- Web UI consumes the API; browses generations with thumbnails
-- Aggregated view across local profiles (read-only)
+- [x] **Uvicorn Daemon:** `gflow serve` starts the local FastAPI/Uvicorn server with background task loop.
+- [x] **MCP SSE Server:** Exposes the MCP server over HTTP/SSE, allowing IDE clients and external tools to run JSON-RPC commands.
+- [x] **Flow Worker Daemon:** Local queue manager and `FlowWorker` background task processor reading from SQLite queue tables and managing sequential profile-locked generation runs.
+- [ ] **REST & Static UI:** FastAPI endpoints for asset management and hosting of the Filmmaking Studio (single-page app).
+- [ ] **Aggregated Management:** Full view of accounts, profiles, projects, and active storyboarding queues.
 
 ## v1.0.0 — Stable API