project-chats 0.2.0__tar.gz

project_chats-0.2.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Project Chats contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

project_chats-0.2.0/PKG-INFO

@@ -0,0 +1,187 @@
+Metadata-Version: 2.4
+Name: project-chats
+Version: 0.2.0
+Summary: Find project-related ChatGPT conversations, review them in a desktop app, and move approved chats into a ChatGPT Project.
+Author: Project Chats contributors
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/michaeljeisner/project-chats
+Project-URL: Issues, https://github.com/michaeljeisner/project-chats/issues
+Project-URL: Source, https://github.com/michaeljeisner/project-chats
+Keywords: chatgpt,projects,migration,conversation-export
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Operating System :: OS Independent
+Classifier: Environment :: X11 Applications
+Classifier: Environment :: MacOS X
+Classifier: Environment :: Win32 (MS Windows)
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: Topic :: Communications :: Chat
+Classifier: Topic :: Utilities
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: browser
+Requires-Dist: playwright>=1.45; extra == "browser"
+Dynamic: license-file
+
+# Project Chats
+
+Project Chats is a local desktop tool that finds project-related ChatGPT conversations, helps you review them, and moves approved chats into a shared ChatGPT Project. It is designed for one-off ChatGPT Business/Team cleanup work where each user can only access their own chats — each person runs it on their own account, reviews the results, and ships the approved chats into a shared Project.
+
+The GUI is the primary interface. A CLI is available for scripting.
+
+## Install
+
+```bash
+git clone https://github.com/michaeljeisner/project-chats.git
+cd project-chats
+python3 scripts/install.py
+```
+
+That creates a `.venv` in the repo, installs everything including Playwright, and writes `./project-chats-gui` and `./project-chats` launchers at the repo root. On macOS you can also double-click `Project Chats.command` after the script finishes.
+
+Then launch the GUI:
+
+```bash
+./project-chats-gui
+```
+
+The GUI will offer to install browser automation (Playwright + Chromium) if it wasn't included, and the first run of Auto-Move will prompt you to sign into ChatGPT in the opened browser window.
+
+> **PyPI release coming.** Once the package is published you'll be able to install with `pipx install 'project-chats[browser]'` and skip the clone.
+
+## What It Does
+
+- Imports a ChatGPT export (`conversations.json`), normalized JSON, Markdown, or text files.
+- Scores conversations against a project profile (name + terms).
+- Lets you review high-confidence and possible matches in-app, with snippets.
+- Generates project memory files from approved chats:
+  - `project_brief.md`
+  - `decisions.md`
+  - `requirements.md`
+  - `open_questions.md`
+  - `source_chats.csv`
+- Generates `move_queue.html` with links and per-chat move instructions.
+- Optionally drives ChatGPT in a browser to move approved chats into the selected Project.
+- Creates a handoff zip for teammates or a project coordinator.
+
+## What It Does Not Do
+
+- Does not scrape workspace-wide chats — only what your account can see.
+- Does not read browser cookies, passwords, or ChatGPT session storage.
+- Does not use undocumented ChatGPT APIs.
+- Does not use a ChatGPT Project API (OpenAI does not expose one). The optional `auto-move` step drives the visible ChatGPT UI in a browser.
+
+## Using the GUI
+
+Launch:
+
+```bash
+project-chats-gui
+```
+
+The GUI walks you through four steps:
+
+1. **New Project** — name it and add terms (project names, aliases, people, repos, clients, domains, or any words that identify relevant chats).
+2. **Import Chats** — drop a `conversations.json`, normalized JSON, Markdown, or text. Classification runs automatically.
+3. **Review** — check the candidates, approve the right ones, hit Save & Continue.
+4. **Move** — open the move queue HTML for manual moving, or use Auto-Move to drive ChatGPT in a real browser.
+
+The browser used by Auto-Move is a separate Playwright profile, not your everyday Chrome — sign into the ChatGPT account you want to use the first time. You can point at a different profile directory from Settings to use a different account.
+
+## Quick Start (CLI)
+
+The CLI mirrors what the GUI does and is useful for scripting or headless runs:
+
+```bash
+project-chats init --project-name "Project Atlas" \
+  --term "Atlas" --term "launch" --term "fidelity"
+
+project-chats ingest ~/Downloads/conversations.json --user-label michael
+project-chats classify
+project-chats build
+project-chats bundle
+```
+
+This writes everything under `./project-chat-run/`:
+
+```text
+project-chat-run/outputs/review_queue.html
+project-chat-run/outputs/move_queue.html
+```
+
+Edit `project-chat-run/outputs/review_queue.csv` and set `approved=true` only for chats you want moved, then rerun `project-chats build`. The GUI does this in-app.
+
+To move approved chats automatically through the ChatGPT UI:
+
+```bash
+project-chats auto-move
+```
+
+The first run opens a real browser profile at `project-chat-run/browser-profile`. Sign into ChatGPT there when prompted. The command writes `project-chat-run/outputs/move_log.csv`.
+
+To use a specific browser profile/account from the CLI:
+
+```bash
+project-chats auto-move --user-data-dir ./profiles/alice
+```
+
+## Multi-User Workflow
+
+1. Project coordinator creates a profile:
+
+   ```bash
+   project-chats init --project-name "Shared Project" --term "client" --term "repo-name"
+   ```
+
+2. Send `project-chat-run/project_profile.json` to each participant.
+3. Each participant runs the same workflow on their own account.
+4. Each participant reviews and either uses the move queue HTML manually or runs `project-chats auto-move` while signed in.
+5. Participants send the generated zip to the coordinator if a consolidated memory pack is needed.
+
+## Inputs
+
+### ChatGPT Export
+
+Personal ChatGPT exports include `conversations.json`. ChatGPT Business may not expose the same export flow, so this format is supported when available but not required.
+
+### Normalized JSON
+
+```json
+[
+  {
+    "user_label": "alice",
+    "conversation_id": "abc123",
+    "title": "Migration notes",
+    "url": "https://chatgpt.com/c/abc123",
+    "messages": [
+      {"author": "user", "text": "Project Atlas rollout plan..."},
+      {"author": "assistant", "text": "Decision: use staged rollout..."}
+    ]
+  }
+]
+```
+
+### Markdown/Text
+
+Markdown and text files are ingested as one chat per file. The file name becomes the chat title.
+
+## Safety
+
+Only run this on chats you are authorized to process. Review the generated files before uploading them into a ChatGPT Project or sharing them with teammates.
+
+The `auto-move` command is best-effort UI automation. ChatGPT can change labels or menus without notice, so run `project-chats auto-move --dry-run` first, then use `--limit 1` for a supervised first move.
+
+## Hack on It
+
+The install above already gives you an editable checkout. To run the tests:
+
+```bash
+python3 -m unittest discover -s tests
+```
+
+If you want to reinstall from scratch (e.g. after pulling changes):
+
+```bash
+python3 scripts/install.py
+```

project_chats-0.2.0/README.md

@@ -0,0 +1,161 @@
+# Project Chats
+
+Project Chats is a local desktop tool that finds project-related ChatGPT conversations, helps you review them, and moves approved chats into a shared ChatGPT Project. It is designed for one-off ChatGPT Business/Team cleanup work where each user can only access their own chats — each person runs it on their own account, reviews the results, and ships the approved chats into a shared Project.
+
+The GUI is the primary interface. A CLI is available for scripting.
+
+## Install
+
+```bash
+git clone https://github.com/michaeljeisner/project-chats.git
+cd project-chats
+python3 scripts/install.py
+```
+
+That creates a `.venv` in the repo, installs everything including Playwright, and writes `./project-chats-gui` and `./project-chats` launchers at the repo root. On macOS you can also double-click `Project Chats.command` after the script finishes.
+
+Then launch the GUI:
+
+```bash
+./project-chats-gui
+```
+
+The GUI will offer to install browser automation (Playwright + Chromium) if it wasn't included, and the first run of Auto-Move will prompt you to sign into ChatGPT in the opened browser window.
+
+> **PyPI release coming.** Once the package is published you'll be able to install with `pipx install 'project-chats[browser]'` and skip the clone.
+
+## What It Does
+
+- Imports a ChatGPT export (`conversations.json`), normalized JSON, Markdown, or text files.
+- Scores conversations against a project profile (name + terms).
+- Lets you review high-confidence and possible matches in-app, with snippets.
+- Generates project memory files from approved chats:
+  - `project_brief.md`
+  - `decisions.md`
+  - `requirements.md`
+  - `open_questions.md`
+  - `source_chats.csv`
+- Generates `move_queue.html` with links and per-chat move instructions.
+- Optionally drives ChatGPT in a browser to move approved chats into the selected Project.
+- Creates a handoff zip for teammates or a project coordinator.
+
+## What It Does Not Do
+
+- Does not scrape workspace-wide chats — only what your account can see.
+- Does not read browser cookies, passwords, or ChatGPT session storage.
+- Does not use undocumented ChatGPT APIs.
+- Does not use a ChatGPT Project API (OpenAI does not expose one). The optional `auto-move` step drives the visible ChatGPT UI in a browser.
+
+## Using the GUI
+
+Launch:
+
+```bash
+project-chats-gui
+```
+
+The GUI walks you through four steps:
+
+1. **New Project** — name it and add terms (project names, aliases, people, repos, clients, domains, or any words that identify relevant chats).
+2. **Import Chats** — drop a `conversations.json`, normalized JSON, Markdown, or text. Classification runs automatically.
+3. **Review** — check the candidates, approve the right ones, hit Save & Continue.
+4. **Move** — open the move queue HTML for manual moving, or use Auto-Move to drive ChatGPT in a real browser.
+
+The browser used by Auto-Move is a separate Playwright profile, not your everyday Chrome — sign into the ChatGPT account you want to use the first time. You can point at a different profile directory from Settings to use a different account.
+
+## Quick Start (CLI)
+
+The CLI mirrors what the GUI does and is useful for scripting or headless runs:
+
+```bash
+project-chats init --project-name "Project Atlas" \
+  --term "Atlas" --term "launch" --term "fidelity"
+
+project-chats ingest ~/Downloads/conversations.json --user-label michael
+project-chats classify
+project-chats build
+project-chats bundle
+```
+
+This writes everything under `./project-chat-run/`:
+
+```text
+project-chat-run/outputs/review_queue.html
+project-chat-run/outputs/move_queue.html
+```
+
+Edit `project-chat-run/outputs/review_queue.csv` and set `approved=true` only for chats you want moved, then rerun `project-chats build`. The GUI does this in-app.
+
+To move approved chats automatically through the ChatGPT UI:
+
+```bash
+project-chats auto-move
+```
+
+The first run opens a real browser profile at `project-chat-run/browser-profile`. Sign into ChatGPT there when prompted. The command writes `project-chat-run/outputs/move_log.csv`.
+
+To use a specific browser profile/account from the CLI:
+
+```bash
+project-chats auto-move --user-data-dir ./profiles/alice
+```
+
+## Multi-User Workflow
+
+1. Project coordinator creates a profile:
+
+   ```bash
+   project-chats init --project-name "Shared Project" --term "client" --term "repo-name"
+   ```
+
+2. Send `project-chat-run/project_profile.json` to each participant.
+3. Each participant runs the same workflow on their own account.
+4. Each participant reviews and either uses the move queue HTML manually or runs `project-chats auto-move` while signed in.
+5. Participants send the generated zip to the coordinator if a consolidated memory pack is needed.
+
+## Inputs
+
+### ChatGPT Export
+
+Personal ChatGPT exports include `conversations.json`. ChatGPT Business may not expose the same export flow, so this format is supported when available but not required.
+
+### Normalized JSON
+
+```json
+[
+  {
+    "user_label": "alice",
+    "conversation_id": "abc123",
+    "title": "Migration notes",
+    "url": "https://chatgpt.com/c/abc123",
+    "messages": [
+      {"author": "user", "text": "Project Atlas rollout plan..."},
+      {"author": "assistant", "text": "Decision: use staged rollout..."}
+    ]
+  }
+]
+```
+
+### Markdown/Text
+
+Markdown and text files are ingested as one chat per file. The file name becomes the chat title.
+
+## Safety
+
+Only run this on chats you are authorized to process. Review the generated files before uploading them into a ChatGPT Project or sharing them with teammates.
+
+The `auto-move` command is best-effort UI automation. ChatGPT can change labels or menus without notice, so run `project-chats auto-move --dry-run` first, then use `--limit 1` for a supervised first move.
+
+## Hack on It
+
+The install above already gives you an editable checkout. To run the tests:
+
+```bash
+python3 -m unittest discover -s tests
+```
+
+If you want to reinstall from scratch (e.g. after pulling changes):
+
+```bash
+python3 scripts/install.py
+```

project_chats-0.2.0/project_chats/__init__.py

@@ -0,0 +1,3 @@
+"""Project Chats CLI package."""
+
+__version__ = "0.1.0"

project_chats-0.2.0/project_chats/__main__.py

@@ -0,0 +1,5 @@
+from .cli import main
+
+
+if __name__ == "__main__":
+    main()

project_chats-0.2.0/project_chats/browser_move.py

@@ -0,0 +1,242 @@
+from __future__ import annotations
+
+import csv
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from pathlib import Path
+
+from .core import load_profile, read_review_rows, workspace_paths
+
+
+MOVE_FIELDS = [
+    "timestamp",
+    "user_label",
+    "conversation_id",
+    "title",
+    "url",
+    "status",
+    "detail",
+]
+
+
+@dataclass
+class MoveOptions:
+    workspace: Path
+    user_label: str | None = None
+    project_name: str | None = None
+    user_data_dir: Path | None = None
+    channel: str = "chrome"
+    headless: bool = False
+    dry_run: bool = False
+    limit: int | None = None
+    slow_mo_ms: int = 150
+
+
+def auto_move(options: MoveOptions) -> Path:
+    profile = load_profile(options.workspace)
+    project_name = options.project_name or profile["project_name"]
+    rows = approved_rows(options.workspace, options.user_label, options.limit)
+    output_path = workspace_paths(options.workspace)["outputs"] / "move_log.csv"
+
+    if options.dry_run:
+        records = [
+            move_record(row, "dry_run", f"Would move to project: {project_name}")
+            for row in rows
+        ]
+        append_move_records(output_path, records)
+        return output_path
+
+    try:
+        from playwright.sync_api import TimeoutError as PlaywrightTimeoutError
+        from playwright.sync_api import sync_playwright
+    except ImportError as exc:
+        raise SystemExit(
+            "Browser automation requires Playwright. Install with: "
+            "python3 -m pip install 'project-chats[browser]' && python3 -m playwright install chromium"
+        ) from exc
+
+    records = []
+    user_data_dir = options.user_data_dir or (options.workspace / "browser-profile")
+    user_data_dir.mkdir(parents=True, exist_ok=True)
+
+    with sync_playwright() as p:
+        context = p.chromium.launch_persistent_context(
+            str(user_data_dir),
+            channel=options.channel,
+            headless=options.headless,
+            slow_mo=options.slow_mo_ms,
+        )
+        page = context.pages[0] if context.pages else context.new_page()
+        page.goto("https://chatgpt.com/", wait_until="domcontentloaded")
+        wait_for_login(page)
+
+        for row in rows:
+            url = row.get("url") or ""
+            if not url:
+                records.append(move_record(row, "skipped", "No chat URL available."))
+                continue
+            try:
+                page.goto(url, wait_until="domcontentloaded")
+                page.wait_for_timeout(1000)
+                status, detail = move_one_chat(page, project_name, PlaywrightTimeoutError)
+                records.append(move_record(row, status, detail))
+            except Exception as exc:  # noqa: BLE001 - log per-row failures and continue.
+                records.append(move_record(row, "ui_failed", str(exc)[:500]))
+
+        context.close()
+
+    append_move_records(output_path, records)
+    return output_path
+
+
+def approved_rows(workspace: Path, user_label: str | None, limit: int | None) -> list[dict]:
+    rows = [
+        row
+        for row in read_review_rows(workspace)
+        if str(row.get("approved", "")).lower() == "true"
+    ]
+    if user_label:
+        rows = [row for row in rows if row.get("user_label") == user_label]
+    rows = [
+        row
+        for row in rows
+        if row.get("move_status") not in {"moved", "already_in_project"}
+    ]
+    return rows[:limit] if limit else rows
+
+
+def wait_for_login(page) -> None:
+    if page.get_by_role("textbox").count() or page.get_by_role("button", name="Search chats").count():
+        return
+    print("Sign into ChatGPT in the opened browser window, then press Enter here.")
+    input()
+    page.goto("https://chatgpt.com/", wait_until="domcontentloaded")
+
+
+def move_one_chat(page, project_name: str, timeout_error_type) -> tuple[str, str]:
+    if page.get_by_text(project_name, exact=True).count():
+        return "already_in_project", f"Project name already visible on page: {project_name}"
+
+    open_chat_menu(page, timeout_error_type)
+    click_menu_item(page, ["Move to project", "Move to Project", "Add to project", "Add to Project"], timeout_error_type)
+    choose_project(page, project_name, timeout_error_type)
+    confirm_if_needed(page)
+    page.wait_for_timeout(1200)
+
+    if page.get_by_text(project_name, exact=True).count():
+        return "moved", f"Moved to project: {project_name}"
+    return "unknown", "Move flow completed, but project name was not visible afterward."
+
+
+def open_chat_menu(page, timeout_error_type) -> None:
+    labels = [
+        "Open conversation options",
+        "Open chat options",
+        "Conversation options",
+        "Chat options",
+        "More",
+        "More options",
+    ]
+    for label in labels:
+        locator = page.get_by_role("button", name=label)
+        if click_first_visible(locator):
+            return
+
+    buttons = page.locator("button").all()
+    for button in reversed(buttons[-20:]):
+        try:
+            text = (button.inner_text(timeout=500) or "").strip()
+            aria = button.get_attribute("aria-label", timeout=500) or ""
+            if "⋯" in text or "…" in text or aria.lower() in {"more", "more options"}:
+                button.click(timeout=1500)
+                return
+        except timeout_error_type:
+            continue
+
+    raise RuntimeError("Could not find the chat options menu.")
+
+
+def click_menu_item(page, labels: list[str], timeout_error_type) -> None:
+    for label in labels:
+        for role in ("menuitem", "button"):
+            locator = page.get_by_role(role, name=label)
+            if click_first_visible(locator):
+                return
+        locator = page.get_by_text(label, exact=True)
+        if click_first_visible(locator):
+            return
+    raise RuntimeError(f"Could not find any menu item: {', '.join(labels)}")
+
+
+def choose_project(page, project_name: str, timeout_error_type) -> None:
+    candidates = [
+        page.get_by_role("option", name=project_name),
+        page.get_by_role("menuitem", name=project_name),
+        page.get_by_role("button", name=project_name),
+        page.get_by_text(project_name, exact=True),
+    ]
+    for locator in candidates:
+        if click_first_visible(locator):
+            return
+
+    search_boxes = [
+        page.get_by_placeholder("Search projects"),
+        page.get_by_placeholder("Search projects..."),
+        page.get_by_role("textbox"),
+    ]
+    for box in search_boxes:
+        if fill_first_visible(box, project_name):
+            page.wait_for_timeout(600)
+            if click_first_visible(page.get_by_text(project_name, exact=True)):
+                return
+
+    raise RuntimeError(f"Could not select project: {project_name}")
+
+
+def confirm_if_needed(page) -> None:
+    for label in ("Move", "Add", "Confirm", "Done"):
+        locator = page.get_by_role("button", name=label)
+        if click_first_visible(locator):
+            return
+
+
+def click_first_visible(locator) -> bool:
+    count = min(locator.count(), 8)
+    for idx in range(count):
+        item = locator.nth(idx)
+        if item.is_visible():
+            item.click(timeout=3000)
+            return True
+    return False
+
+
+def fill_first_visible(locator, value: str) -> bool:
+    count = min(locator.count(), 8)
+    for idx in range(count):
+        item = locator.nth(idx)
+        if item.is_visible():
+            item.fill(value, timeout=3000)
+            return True
+    return False
+
+
+def move_record(row: dict, status: str, detail: str) -> dict:
+    return {
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "user_label": row.get("user_label", ""),
+        "conversation_id": row.get("conversation_id", ""),
+        "title": row.get("title", ""),
+        "url": row.get("url", ""),
+        "status": status,
+        "detail": detail,
+    }
+
+
+def append_move_records(path: Path, records: list[dict]) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    exists = path.exists()
+    with path.open("a", newline="") as f:
+        writer = csv.DictWriter(f, fieldnames=MOVE_FIELDS)
+        if not exists:
+            writer.writeheader()
+        writer.writerows(records)