dsh-observation-journal
Run the following command in DeepSeek Harness:
dsh plugin install Cavan-Ou/dsh-observation-journal
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command 'dsh plugin install Cavan-Ou/dsh-observation-journal', or visit the full source address at https://github.com/Cavan-Ou/dsh-observation-journal.
About this plugin
In DeepSeek Harness, while failures are documented by plugins like dsh-fail-logger, successful run facts and telemetry often remain unrecorded, making it challenging to fully assess session performance and behavioral patterns. dsh-observation-journal fills this gap as a pure observer plugin that zero-touch automatically logs key session facts such as task details, model tier, tool usage, failures, duration, and status into a human-readable journal with an auto-updated stats section. It is designed for developers and project managers who need to monitor session performance and conduct post-mortem analysis without disrupting the agent workflow, offering passive and reliable data capture to ensure transparency and traceability in operations.
Use Cases
- Monitor performance and status of each session
- Generate auto-updated report cards for project auditing
- Analyze tool usage and failures to optimize workflows
Best For
- Developers who need details on session runs
- Project managers requiring transparent operation logs
- Operations personnel for post-mortem analysis and troubleshooting
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.