Updated the to reflect the definitive conclusion that Moltbot (requiring Node.js v22+) cannot be installed on Synology NAS systems (due to Docker/kernel incompatibility with modern Node.js images, and Moltbot's hard requirement).
- Added a prominent warning about the unresolvable "Catch-22" at the beginning of the guide.
- Documented the and that represented the final, most advanced attempt to bypass the issues, including using Node.js v20, named Docker volumes, and aggressive patching attempts.
- Updated the troubleshooting section to clearly explain the unresolvable conflict and its implications, offering alternative solutions outside of Synology.
This commit introduces the necessary files for installing Moltbot as a Docker container, specifically targeting a Synology NAS setup.
- Created to define the Moltbot service, including image build from source, port mapping (18789), and persistent data volume ( to ).
- Added which provides a comprehensive, step-by-step guide for deploying Moltbot on a Synology NAS using , covering initial setup and the interactive command.
Die GEMINI.md wurde aktualisiert, um den neuen #fertig-Befehl und den damit verbundenen Workflow zu dokumentieren. Diese Konvention stellt sicher, dass das Abschließen von Arbeitspaketen zuverlässig erkannt wird.
Abschließende Überprüfung des /fertig-Workflows. Es wurden keine neuen Code-Änderungen festgestellt. Der Status wird in Notion aktualisiert, um den Task formal abzuschließen.
Der 'fertig'-Workflow wurde erfolgreich repariert und getestet. Ein veralteter post-commit-Hook, der Fehler verursachte, wurde entfernt. Der gesamte Prozess von der Zeiterfassung über den automatisierten Commit bis zum interaktiven Push funktioniert nun wie erwartet. Ein Test-Kommentar wurde zur Validierung hinzugefügt.
Implementierung der UI-Anpassungen zur Anzeige von ausstehenden Fehlerberichten (rote Flagge in der Unternehmensliste, Anzeige im Inspector) und zur Ermöglichung weiterer Fehlerberichte. Backend-APIs wurden entsprechend erweitert.
Der 'fertig'-Workflow wurde weiter gehärtet. Eine Prüfung stellt nun sicher, dass ein On branch main
Your branch is up to date with 'origin/main'.
nothing to commit, working tree clean nur dann versucht wird, wenn auch tatsächlich Änderungen im Arbeitsverzeichnis vorhanden sind. Dies verhindert Fehler bei der Ausführung, wenn der Task-Abschluss nur der Status-Aktualisierung dient.
Implemented a full time tracking feature. The system now displays the previously recorded time in hh:mm format when a session starts. When a work unit is completed, the invested time is automatically calculated, added to the total in Notion, and included in the status report. Various bugs were fixed during this process.
- 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.
