Files
deepseek-harness/packages/support/invariants
Tianyi Cui 2489402610 Merge origin/master: scope-aware fusion of the tools/execute seam, session-prefix, and tool-cordis
Master brought 50 commits (the tool-cordis group, dsh-code-runtime + worker,
the tools/execute around-dispatch seam + timeout-policy, repeat-tool-guard,
agent/session-prefix, the ui reorganization). Beyond the ten textual
conflicts, the merge reconciles master's new seams with this branch's
scoped-registration world:

- tools/execute (new waterfall around core dispatch): dispatched with the
  SAME exec.agent carrier as the pre/post waterfalls — an agent.ctx wrapper
  times/retries only its own agent's calls — and its base thunk resolves the
  tool through the caller's visible view (get(exec.name, exec.agent)), so a
  scoped/shadowed tool dispatches and a restricted-away global stays
  UNKNOWN_TOOL. Declared this: Scoped<ToolRegistry> with the scope-filtered
  doc sentence; invariants table + verify-scoped-dispatch pin it (21 events).
- agent/session-prefix (new waterfall, once per loop instance): composed via
  the fused agentEvents dispatcher (scope-filtered like every agent-subject
  event), declared this: Scoped<Agent>, table-pinned. agent/pre-step keeps
  master's new sessionPrefix parameter with this branch's Scoped this.
- timeout-policy reads the budget through the caller's visible view
  (get(exec.name, exec.agent)): a scoped tool's own timeoutMs governs its
  calls; a global name-twin's budget is never misapplied to a shadowing
  per-agent variant.
- tool-cordis: cordis_inspect's tools section lists the CALLING agent's view
  (its description promises "what you can call"); the sandbox tool façade's
  reads resolve through the mount's own scope, mirroring where its register
  lands writes; sandboxRegisterTool's return type carries the exact-disposer
  union honestly. dsh-scope declared as peer+dev with the project reference.
- doc-sync chain unions master's verify-cordis-api with this branch's
  verify-scoped-dispatch; the generated catalogs, event matrix (the
  zero-dispatcher guard passes over master's new events), module graph, and
  the cordis api-catalog are regenerated on the merged surface.

Full gate sequence green on the merged tree: typecheck, lint, per-file 100%
coverage (2668 tests), snapshots (38), doc-sync, module graph, build,
hygiene, demo smoke.
2026-07-09 23:24:42 +08:00
..

dsh-invariants

Dev-mode event-contract invariants and session-log freeze. A pure-listener plugin (everything is a plugin) that asserts the harness event contract at runtime and, optionally, freezes logged session-event data so any code that mutates history throws instead of corrupting silently.

Off in production. Enable it in tests and the demos, where a contract violation should fail loudly. It costs nothing when not registered, and doubles as executable documentation of the event taxonomy — the assertions are the contract.

Plugin

A functional plugin — register the module namespace (this is what loading by name in cordis.yml does):

import type { Context } from 'cordis'
import * as Invariants from '@deepseek-ai/dsh-invariants'

declare const ctx: Context

await ctx.plugin(Invariants)                     // freeze on (default)
await ctx.plugin(Invariants, { freeze: false })  // assert contract, don't freeze

inject: ['sessions'] — it reads ctx.sessions.list() at apply time to rebuild trace state for sessions that already exist (so a hot reload mid-turn doesn't falsely reject the next event). It listens on session/created, session/event, and agent/status.

Config

Key Default Meaning
freeze true Deep-freeze each logged event's data so mutating a logged event throws. Set false to assert the contract without freezing.

Invariants asserted

Session log (per session):

  • seq strictly increases — the spine of replay equivalence.
  • turns pair and nestturn/start opens a turn, turn/end closes the matching one; no overlapping turns.
  • steps nest in turnsstep/start opens a step in the open turn; step/end closes the matching step.
  • chunks belong to an open stepstep/start precedes its assistant/chunks.
  • a tool/result needs a prior tool/call — but NOT the converse: a tool/call may have no result (a thrown tool-execution pipeline step ends the turn with no tool/result, which is legal).

Agent status (per agent):

  • legal transitions onlyidle↔running and (idle|running)→disposed. A no-op transition (setStatus dedups, so it never fires) and leaving the terminal disposed state are violations.

Model requests (on llm/stream):

  • a loop-built request is exactly what the log reconstructs — a frozen request with a live sessionId (the loop-built marker; hand-built one-shots like compaction's summarize are unfrozen and skipped) must carry frozen messages deep-equal to the derivation over the log prefix strictly before the in-flight step's step/start (rebuilt through a FRESH Session, so the live cache cannot vouch for itself — and boundary-correct: content logged after step/start legitimately belongs to the next request), and every non-content field must equal the fold of the log's request/header* events (see the reconstructability RFC). Registered with prepend: true so a short-circuiting llm/stream listener (the replay adapter) cannot silence it; prepend orders it against append-registered listeners only — correctness rests on the seq-bounded rebuild, never listener timing.

On any violation it throws InvariantError (code: 'INVARIANT').

Why runtime, not deep-readonly types

A DeepReadonly<SessionEvent> is high type-noise across every log consumer, and a plugin can cast straight through it. A dev-mode freeze plus these assertions catch real corruption at zero production cost and zero type noise. The always-on half of that defense — cloning derived messages so request/adapter mutation can't reach back into the log — lives in dsh-session's deriveMessages. This package is the dev-mode tripwire. See dev-mode invariants.

Seeded sessions

A seeded/forked session arrives with events already in its log (the Session constructor copies the seed without emitting session/event). On session/created the plugin replays the existing log through the checker and freezes those entries, so seeded history is held to the same contract.