iguowz/dsh-cortexx

Cortex — Multi-Model Orchestration & Evaluation for DeepSeek-Harness

English | 中文 | npm package | GitHub

Cortex is a DeepSeek-Harness plugin that turns the host's primary (strong) model into a high-leverage supervisor. The supervisor plans, decomposes, verifies and accepts; routed executor models (small/cheap models such as Qwen3.8-9B) and tools do the heavy lifting. With a recursive task tree, dynamic routing, four-stage quality gates, budget control, failure recovery, policy reuse and per-dimension model evaluation, Cortex keeps quality stable while driving the unit cost of successful tasks down.

The supervisor is the host primary model that drives the cortex_* tools (e.g. deepseek-v4-pro in the bundled registry), and executors are the models the dynamic router picks per subtask (L1/L2 tiers, e.g. Qwen3.8-9B).

Suggested repository topics (GitHub): dsh-plugin · dsh · cordis · llm-orchestration · multi-model · model-routing · quality-gate

---

Highlights

Recent Changes

A condensed log of the capabilities added after the initial release (full per-round evidence lives in docs/开发任务清单.md):

• Organization mode — department probes & governance (cortex_probe, cortex_start.organization_mode): the mode is a task property (standard / department / auto = engine decides by difficulty = max(complexity, scale, risk), threshold organizationAutoThreshold 0.75; an explicit declaration always wins; domain/capability tags deliberately do not count as difficulty signals). Department mode adds 8 built-in probes (append-only custom), authority tiers P0–P4, Rule-First fail-closed governance (pass/review/veto, veto freezes the node and its downstream, cleared only by an explicit lift), a hash-chained ledger (governance.jsonl, verify-able), event bus × subscriptions → deterministic to-dos, adversarial governance review, a critical-op approval chain (veto-lift / P4 grant / enabling governance suspend until approved), a probe budget hard quota, priority dispatch and ROI ranking. Department mode is a layer on top of standard mode — it never introduces its own model pool, filter or routing criterion.
• Human-in-the-loop: questions the rules say a human must answer (critical-op approval / veto confirmation / arbitration / human review / supervisor escalation / probe budget) are recorded with options + a suggested action, and on unattended paths the engine wakes the conversation so the supervisor asks the user — deduped, batched, delivery recorded; the console deliberately keeps no second to-do inbox (questions are asked in the conversation; data plane /api/interactions and cortex_probe interactions remain for scripts).
• Phase-3 control plane: admission queue (global + per-task, round-robin), workflow control (pause/resume/terminate/per-node isolate), review protocols & prompt templates (versioned, append-only, contract-gap self-check), self-tuning proposals with guardrails + ledger, routing-weight learning, budget rebalancing and audit snapshots — all observable in the console's “Learn chain” tab and reachable from /cortex control|tune|org|gate|protocols.
• Console language follows DSH General settings: lib/locale.js reads the host locale preference (settings service first, settings.yaml read-only fallback) and writes it back through the official settings service; the header button switches it, every open console follows over SSE (with a storage-event/heartbeat fallback so a missing host event can never silently strand the page), and the first paint already carries the language. The session “Tasks” panel registers one cortex dictionary (zh+en) and renders every label/status/button through it.
• Console simplification: the global organization-mode switch and the “default mode” badge are gone (mode is per task; each task row still shows its own mode badge), the “needs your action” block is gone, and the remaining panels (probes / responsibility matrix / authority / ledger / dispatch / to-dos / ROI / learning chain / L0 / evaluation) are all business-worded with no raw JSON and no framework names.
• Quality & routing depth: Gate3.5 red-team, per-dimension capability profiles (dims_profile, EMA) fed by evaluation and production Gate2/review, drift monitoring with automatic routing penalties, value score + Pareto frontier, static-baseline reset, effective price override (3-tier priority), L1/L2/L3 cache, deterministic statistics via type:"compute" engine nodes, and an L0 deterministic tool library that is generated and sandbox-verified at runtime.
• Maintainability pass: shared numeric helpers (lib/engine/util.js) replace nine sets of duplicated implementations; the browser bundle's UI text lives in one dictionary (a regression test forbids hard-coded Chinese in the bundle); dead exports/CSS/scripts were removed with evidence.

Install & Auto-Enable

dsh plugin is the supported way: it installs the package into the profile, and because this package declares dsh.bundle.patch (= cordis.patch.yml), it is automatically appended to dsh.profile.bundles — enabled on next boot with no manual profile edits.

From npm (published):

# install the plugin package as a dependency
yarn add dsh-cortex            # or: npm install dsh-cortex

# register it into a DSH profile and boot
npx @deepseek-ai/dsh plugin --profile web add dsh-cortex
npx @deepseek-ai/dsh web        # boot — the 13 cortex_* tools are live

From a local checkout (development):

cd <repo-path>                                   # the repo root
npx @deepseek-ai/dsh plugin --profile web add .  # anchors to this dir (or pass the absolute path)
npx @deepseek-ai/dsh web

Remove: npx @deepseek-ai/dsh plugin --profile web remove dsh-cortex.

The shipped bundle patch inserts the cortex row with uiEnabled: true, uiPort: 8788 (console listens on loopback only). stateDir and modelsFile use built-in defaults ($DSH_HOME/storages/cortex and the bundled config/models.yaml) — anything can be overridden by an - id: cortex config row in your profile's own cordis.patch.yml (it applies after bundle layers).

Typical Flow (agent view)

cortex_start → (cortex_strategy_match) → cortex_decompose T0 → cortex_execute [node_ids | recursive]
→ cortex_review (batch accept) → cortex_recover (on failures) → cortex_report (KPI) → cortex_policy (settle)

Operations & Commands

1. Agent tools (14 — the supervisor calls them autonomously)

2. Slash commands (/cortex <subcommand>)

3. Console REST (127.0.0.1:8788)

GET  /api/overview · /api/timeline?hours=all|24|168 · /api/rate · /api/models
     /api/matrix · /api/evaluations · /api/eval-cases · /api/capabilities
     /api/evaluate/status · /api/task/<id> · /api/tasks?limit&session · /api/events (SSE live)
     /api/organization[?dispatch=<taskId>] · /api/interactions · /api/control
     /api/protocols[?task=<id>] · /api/tune · /api/budget · /api/routing
     /api/kpi-snapshots · /api/lang · /api/watchdog/calibration
POST /api/models/<id>            {enabled?: boolean, preferred?: boolean, reason?: string}   // reason = preference content (required on the page)
     /api/matrix/reset           (clear evaluation feedback)
     /api/eval-cases             {action: add|remove|save, ...}
     /api/capabilities           {name, description?}
     /api/evaluate               {models?, cases?, use_saved?} (real background run)
     /api/tasks/<id>             (DELETE — remove a history task with its nodes/attempts)
     /api/tasks/<id>/control     {action: pause|resume|terminate|isolate|unisolate}
     /api/control/purge          {kinds?, reason?}        (audit-purge, itself ledgered)
     /api/organization           {action: mode|assign|approve|intent-ack|intent-resolve|interaction-ack|interaction-resolve, ...} (whitelisted)
     /api/interactions           {action: ack|resolve, id, note?}
     /api/protocols              {protocol?|template?}   (versioned append-only writes)

     /api/lang                   GET  → {value, writable, pushed, settingsFile}   (console language follows DSH General settings)
                                 POST {lang} → writes the host `locale` setting through the official settings service
     /api/watchdog               {action: add-task|add-goal|pause|resume|remove|run|window-set|window-clear|ws-add, ...} (whitelisted)
GET  /watchdog · /api/watchdog/rules|runs?limit=50|targets|windows   (watchdog page, uses /api/events SSE)

4. Runtime lifecycle