dsh-outcome-loop
Local-first task outcome ledger and mechanical acceptance verification plugin for DeepSeek Harness.
Install
$ dsh plugin --profile <name> add ./dsh-outcome-loop-0.1.0-beta.8.tgzPlugin 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
- Defines structured task contracts with custom acceptance criteria (command exit codes, test reports, artifact checks, diagnostics)
- Executes passive fact observation or gated active sandboxed verification runs
- Separates mechanical verification results from user disposition (accept, reject, revise, abandon)
- Maintains multi-axis state tracking (execution status, verification status, user disposition, label strength, data eligibility)
- Supports two-phase export workflows with preview digests and realpath workspace confinement
- Integrates into DSH via Cordis services and `/outcome` slash commands
Useful For
- Mechanically verifying DSH coding session outcomes using test suites, exit codes, and build artifacts
- Auditing and recording task completion evidence locally without leaking raw code or session prompts
- Tracking LLM token costs alongside verifiable task completion records
- Exporting sanitized task outcome datasets with user consent gates
Who It Fits
- DSH developers requiring objective verification of agent tasks
- Teams needing local-first audit trails and outcome ledgers for LLM workflows
- Engineers evaluating task completion benchmarks and test pass rates
Documented Limitations
- Requires the storageDomain service (available via @deepseek-ai/dsh-storage-domain or web bundles)
- Active verifiers are strictly sandboxed and require explicit policy enablement
- Dataset contribution mode is disabled by default and requires manual configuration
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 2 runtime, 18 development, 5 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
- victorzhong0110/dsh-outcome-loop
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- d119d0d · 2026-09-22
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
- 2GitHub stars
- Forks
- 1
- Open issues
- 1
- Last commit
- 2026-09-06
- Last release
- 2026-08-18
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed fallback and session audit logging.
View plugin →Multi-engine search and evidence verification plugin bundle for AI agents in DeepSeek Harness.
View plugin →