- Replaces the Notion update mechanism to append content blocks to the task page instead of posting comments.
- A new function, , is implemented to handle the Notion Block API.
- The function now formats the report into a 'heading_2' block for the title and a 'code' block for the detailed content, preserving formatting.
- This provides a much cleaner and more readable changelog directly within the Notion task description.
- Adds a '--summary' parameter to dev_session.py to allow for detailed, narrative descriptions in Notion status updates.
- The Notion comment format is updated to prominently display this summary.
- start-gemini.sh is refactored to be more robust and context-aware.
- It now injects the container name and a strict rule against nested docker commands into the Gemini CLI's initial prompt.
- This prevents operational errors and provides better context for the agent.
Implements the functionality in , allowing the Gemini agent to non-interactively update a Notion task with a detailed progress summary.
The agent can now be prompted to:
- Collect the new task status and any open to-dos.
- Generate a summary of Git changes () and commit messages.
- Post a formatted report as a comment to the Notion task.
- Update the task's status property.
The has been updated to document this new agent-centric workflow, detailing how to start a session, work within it, and use the agent to report progress and push changes seamlessly.
This commit resolves all outstanding issues with the AI Insights feature.
- Corrects the transcript formatting logic in to properly handle the database JSON structure, ensuring the AI receives the correct context.
- Fixes the Gemini API client by using the correct model name ('gemini-2.0-flash') and the proper client initialization.
- Updates to securely pass the API key as an environment variable to the container.
- Cleans up the codebase by removing temporary debugging endpoints.
- Adds script for programmatic updates.
- Updates documentation with troubleshooting insights from the implementation process.
Implements the core functionality for the AI-powered analysis of meeting transcripts in the Transcription Tool.
This commit introduces a new 'AI Insights' feature that allows users to generate various summaries and analyses from a transcript on demand.
- Creates a to manage and version different AI prompts for tasks like generating meeting minutes, extracting action items, and creating sales summaries.
- Adds a new responsible for orchestrating the analysis process: fetching the transcript, calling the Gemini API with the appropriate prompt, and caching the results in the database.
- Extends the FastAPI backend with a new endpoint to trigger the insight generation.
- Updates the React frontend () with a new 'AI Insights' panel, including buttons to trigger the analyses and a modal to display the results.
- Updates the documentation () to reflect the new features, API endpoints, and version.
Ändert die Architektur des -Systems, um die Stabilität der Gemini CLI zu verbessern.
Die Gemini CLI wird nicht mehr als direkter Unterprozess von gestartet. Stattdessen gibt den generierten Kontext auf stdout aus, und das -Skript fängt ihn ab und startet die CLI in einem sauberen, separaten Container.
- ****: Entfernt die Funktion und gibt den Kontext stattdessen über stdout aus.
- ****: Führt jetzt einen zweistufigen Prozess aus. Zuerst wird der Kontext von in einem temporären Container abgerufen und dann die Gemini CLI in einem neuen Container mit dem Kontext als gestartet.
- ****: Dokumentation aktualisiert, um die neue Architektur widerzuspiegeln.
This commit introduces a containerized workflow for the development session manager (dev_session.py).
- Dockerization: Added gemini.Dockerfile to create a self-contained environment with all Python dependencies, removing the need for manual host setup.
- Start Script: Updated start-gemini.sh to build and run the container, executing dev_session.py as the entrypoint.
- Session Management: Implemented --done flag to properly terminate a session, update the Notion task status, and clean up the git hook.
- Notion Integration: Created and integrated notion_commit_hook.py which is automatically installed/uninstalled to post commit messages to the active Notion task.
- Documentation: Updated README_dev_session.md to reflect the new container-based setup, usage, and features.
This commit introduces a comprehensive README.md for the dev_session.py script.
The documentation covers the purpose, features, usage, installation, and important notes for the Notion-integrated development session manager.
It also clarifies the Git branch naming convention suggested by the tool.
The creation of this README.md fulfills task [2f388f42].
- Backend: Added global speaker rename endpoint
- Backend: Hardened JSON parsing and timestamp offsets
- Frontend: Integrated Speaker Management Bar
- Frontend: Added Trim Start/End (Scissors) and Single Line Delete
- Frontend: Fixed various TypeScript and Syntax issues
- Docs: Full documentation of v0.5.0 features
- Added FastAPI backend with FFmpeg and Gemini 2.0 integration
- Added React frontend with upload and meeting list
- Integrated into main docker-compose stack and dashboard
- Restored missing method implementations in ClassificationService (classify, extract_metrics)
- Fixed Standardization Logic not being applied in metric cascade
- Bumped version to v0.7.4 in config.py
- Removed duplicate API endpoint in app.py
- Updated MIGRATION_PLAN.md
- **Standardization & Formula Logic:** Fixed NameError/SyntaxError in formula parser; added support for comments and capitalized placeholders.
- **Source URL Tracking:** Extended DB schema and cascade logic to store and track specific source URLs.
- **Frontend & UI:**
- Added 'Standardized Potential' display in Inspector.
- Added clickable source link with icon.
- Fixed Settings tab layout collapse (flex-shrink-0).
- **Export Capabilities:**
- Single-company JSON export now includes full quantitative metadata.
- New global CSV export endpoint /api/companies/export.
- **System Integrity:**
- Fixed Notion sync typo ('Stanardization').
- Corrected Nginx proxy routing and FastAPI route ordering.
- Ensured DB persistence via explicit docker-compose volume mapping.
- Implemented a "Re-evaluate Wikipedia" button in the UI.
- Added a backend endpoint to trigger targeted Wikipedia metric extraction.
- Hardened the LLM metric extraction prompt to prevent hallucinations.
- Corrected several database path errors that caused data loss.
- Updated application version to 0.6.4 and documented the ongoing issue.
- Implements a 3-tier database architecture (Canonical Products, Portfolio, Companies) to separate product master data from company-specific portfolio information.
- Upgrades import_competitive_radar.py to an intelligent "upsert" script that prevents duplicates by checking for existing entries before importing.
- This enables detailed GTM strategy tracking for RoboPlanet products while monitoring competitor portfolios.
- Updates documentation to reflect the new architecture and import process.
