dsh-fail-logger
Automated tool failure recorder for DeepSeek Harness that dedupes and counts errors into skill logs.
Install
$ dsh plugin --profile web add dsh-fail-loggerPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Captures tool execution failures from native tools, PTC run_code, and nested code tool dispatches via session event observation
- Normalizes paths and numbers to deduplicate and count recurring failure causes
- Redacts sensitive credentials, tokens, URLs, and private IP addresses automatically with support for custom regexes
- Maintains deterministically sorted and categorized failure entries directly in SKILL.md with TTL archiving
- Offers three-tier failure prevention including static rule injection, recurring error solidification into system prompts, and skill-loading fallback
- Includes static timeout governance rules to mitigate over-wide glob, grep, or prolonged run_code operations
- Ensures safe multi-process concurrency with atomic file writes and lock-merge handling
Useful For
- Building an automated failure memory skill so the agent encounters fewer repetitive tool invocation errors over time
- Preventing costly timeout loops during wide file searches and lengthy run_code scripts
- Tracking failure trends across headless and web DSH profiles without modifying runtime execution or introducing external telemetry services
Who It Fits
- DeepSeek Harness developers seeking automated skill-based error self-healing
- Agent workflow engineers running complex multi-step code execution or batch tasks
Documented Limitations
- Only captures failures that surface as isError:true in session logs; process crashes before logging or non-zero exit codes (like exit 1) without thrown errors are not recorded
- Deduplication relies on heuristic keying over normalized lines, which may occasionally split varied wordings of the same root cause
- Prompt injection adds step token overhead unless disabled with injectInstructions: false
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- Areium/dsh-fail-logger
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- bce6c99 · 2026-09-24
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 10GitHub stars
- Forks
- 0
- Open issues
- 1
- Last commit
- 2026-09-20
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Turns ideas, plans, and codebases into interactive architecture and workflow diagrams.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed verdicts and audit logging.
View plugin →Multi-model workflow teams and DAG orchestration GUI for DeepSeek Harness Web profile.
View plugin →