LeemanCheung/dsh-agent-preset-recommender

English | 中文

A persistent, host-side DeepSeek Harness bundle that privately summarizes local Codex, Claude Code, and WorkBuddy/CodeBuddy activity and recommends a built-in DSH agent preset. It is advisory only: there is no LLM call, installation, preset mutation, or network request.

Install

dsh plugin --profile web add github:LeemanCheung/dsh-agent-preset-recommender

Restart the selected DSH profile after installation. The package declares dsh.bundle.patch and mounts one host plugin.

What it recommends

Observed aggregate behavior is mapped to:

• capability presets: minimal or standard.

code is a Code Mode presentation variant of standard, so this scanner never infers it from local activity volume or silently recommends it as a capability tier.

• optional capabilities: Codex delegation, Claude Code delegation, workflows, web, MCP, and LSP.

Every recommendation includes confidence and numerical evidence. Thresholds are deterministic and local; results never automatically change DSH.

Architecture

cordis.patch.yml → src/index.js (Cordis lifecycle + raw model tools)
                    ├─ scanner.js (bounded traversal and aggregation)
                    ├─ extractors.js (selected JSON/JSONL metadata fields)
                    ├─ recommender.js (deterministic rules)
                    ├─ store.js (atomic private report file)
                    └─ render.js (bounded readable tool output)

Runtime code is plain ESM JavaScript for Node.js 20+. It uses Node built-ins plus @deepseek-ai/schemastery for plugin configuration validation. Tool definitions are registered directly through ctx.tools.register and do not import unpublished DSH tool runtime helpers.

Privacy

The scanner persists aggregate metadata only:

• source and installation-keyed project identifier;
• categorized tool counts;
• session, workflow, and project-metadata counts;
• first/last observation dates (day-level);
• recommendation, confidence, and evidence counts;
• an explicit machine-readable privacy declaration.

It never persists prompts, responses, commands, tool arguments, raw events, absolute paths, usernames, secrets, or file contents. Project identifiers are derived with a random installation-local HMAC key, so report IDs cannot be dictionary-matched without the private key. WorkBuddy/CodeBuddy memory metadata is counted from file presence and modification time only; workflow/plan files are likewise never opened. The scanner makes no network requests and runs no discovered command.

Cache, dependency, build, output, coverage, virtual-environment, and .git directories are skipped. Symbolic links are not followed.

The default report is:

$DSH_HOME/state/agent-preset-recommender/report.json

If DSH_HOME is unset, ~/.dsh is used. The directory also holds a private random identity.key used only to derive project IDs. Report writes use a same-directory temporary file and atomic rename; restrictive permissions are requested where the platform supports them.

Supported locations and formats

Source	Defaults	Read behavior
Codex	$CODEX_HOME/sessions, $CODEX_HOME/archived_sessions or ~/.codex/*	Bounded .jsonl/.json; selected session/project and tool-name fields
Claude Code	$CLAUDE_CONFIG_DIR/projects or ~/.claude/projects	Bounded .jsonl/.json; selected project and tool_use name fields; workflow sidecars, journals, task/session/plan stores, and global history are excluded
Claude personal workflows	$CLAUDE_CONFIG_DIR/workflows or ~/.claude/workflows	.js file presence and day only; scripts are never opened. Add project-local <repo>/.claude/workflows explicitly to claudeWorkflowRoots if desired
Claude transcripts	Disabled	Scanned only when claudeTranscriptRoots is explicitly configured
CodeBuddy CLI	$CODEBUDDY_CONFIG_DIR/projects or ~/.codebuddy/projects	Bounded canonical project .jsonl records; ~/.codebuddy/workflows/*.js and project-local workflow scripts are inventoried by presence only. Process maps, tool-result/blob directories, and workflow runtime sidecars are excluded
WorkBuddy	$WORKBUDDY_CONFIG_DIR/projects or ~/.workbuddy/projects, ~/.workbuddy-ai/projects	Heuristic, version-sensitive project .jsonl inventory; native session layout is not vendor-contracted, so it is never treated as proof of CodeBuddy session equivalence
Project-local CodeBuddy/WorkBuddy metadata	<project>/.codebuddy or <project>/.workbuddy memory, workflows, plans, or automations	Count and day only, including workflow .js; content is not read; memory never becomes workflow evidence

Formats vary between product releases. CodeBuddy paths/workflow scripts are documented; WorkBuddy session-file detection is an observed heuristic. Unknown fields are ignored, malformed records are skipped, and malformed files are counted as errors without stopping the scan.

Configuration

Configure the inserted agent-preset-recommender row in a DSH patch:

- id: agent-preset-recommender
  config:
    scanOnStart: true
    intervalMinutes: 360      # 0 disables scheduled scans
    maxFilesPerSource: 500
    maxBytesPerFile: 1048576
    recentDays: 90
    stateDirectory: ''        # empty = $DSH_HOME/state/agent-preset-recommender
    codexRoots:
      - ~/.codex/sessions
      - ~/.codex/archived_sessions
    claudeRoots:
      - ~/.claude/projects
    claudeTranscriptRoots: [] # opt in explicitly
    claudeWorkflowRoots:
      - ~/.claude/workflows   # inventory only; script content is never read
    workbuddyRoots:
      - ~/.codebuddy
      - ~/.workbuddy
      - ~/.workbuddy-ai
      - ~/WorkBuddy
      - ~/CodeBuddy

Defaults honor CODEX_HOME, CLAUDE_CONFIG_DIR, CODEBUDDY_CONFIG_DIR, and WORKBUDDY_CONFIG_DIR when DSH starts. Supplying an explicit root list in the plugin configuration takes precedence over those defaults.

Bounds are validated: file counts, file bytes, recency, and interval are finite. Missing/inaccessible roots are skipped. Startup, scheduled, and tool-triggered scans share one serialized queue and are aborted on plugin disposal.

Model tools

scan_agent_projects

Runs and persists a fresh scan. Optionally refresh only selected sources:

{ "sources": ["codex", "claude"] }

Unselected source aggregates from the previous report remain intact.

get_agent_preset_recommendations

Reads the persisted report without scanning:

{}

Or retrieve one keyed project:

{ "project_id": "codex-0123456789abcdef" }

Both tools return bounded readable text strings.

Limitations

• Metadata schemas are intentionally conservative; unrecognized tool events may be undercounted.
• Keyed IDs are stable only while the private state directory remains available; deleting identity.key intentionally creates a new identifier set.
• A recommendation reflects observed local frequency, not task quality or organizational policy.
• The plugin does not verify that optional products or capabilities are installed or authenticated.
• JSONL files above the byte cap are prefix-sampled within the byte/record bounds; their remaining data, oversized JSON files, old files, and older files beyond a source limit are intentionally omitted. Compressed Codex .jsonl.zst rollouts are not read in 0.1.6. Claude workflow scripts and dynamic workflow sidecars are deliberately not parsed.

Development

npm install
npm test

Tests use synthetic temporary fixtures and Node's built-in node:test; no local product data is read. See SECURITY.md for private vulnerability reporting guidance.

License

MIT