Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
import { describe, expect, it } from 'vitest'
|
|
|
|
|
import { Context } from 'cordis'
|
2026-06-17 21:25:47 +08:00
|
|
|
import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm'
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
|
2026-06-19 10:13:33 +08:00
|
|
|
import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop'
|
2026-06-15 23:53:47 +08:00
|
|
|
import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts'
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
async function harness(adapter: MockAdapter) {
|
|
|
|
|
const ctx = new Context()
|
|
|
|
|
await ctx.plugin(LlmService)
|
|
|
|
|
await ctx.plugin(SessionStore)
|
|
|
|
|
await ctx.plugin(SystemPrompt)
|
|
|
|
|
await ctx.plugin(ToolRegistry)
|
|
|
|
|
await ctx.plugin(AgentRegistry)
|
|
|
|
|
await ctx.plugin(AgentLoop, { agents: [] })
|
|
|
|
|
ctx.llm.registerAdapter(['mock'], adapter)
|
|
|
|
|
return ctx
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* Wait for the agent's NEXT transition to idle. Always event-based: callers
|
|
|
|
|
* invoke this right after send(), when the loop hasn't woken yet (status is
|
|
|
|
|
* still 'idle' synchronously), so polling the current status would lie.
|
|
|
|
|
*/
|
2026-06-19 10:13:33 +08:00
|
|
|
function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise<void> {
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
return new Promise((resolve) => {
|
|
|
|
|
const dispose = ctx.on('agent/status', (subject, status) => {
|
|
|
|
|
if (subject === agent && status === 'idle') {
|
|
|
|
|
dispose()
|
|
|
|
|
resolve()
|
|
|
|
|
}
|
|
|
|
|
})
|
|
|
|
|
})
|
|
|
|
|
}
|
|
|
|
|
|
2026-06-19 10:13:33 +08:00
|
|
|
function send(agent: ReactLoopAgent, text: string) {
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
agent.send([{ type: 'text', text }])
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
describe('agent loop', () => {
|
|
|
|
|
it('runs a simple turn: queued message → model → idle, with ordered events', async () => {
|
|
|
|
|
const adapter = new MockAdapter([textResponse('hello there')])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
const order: string[] = []
|
|
|
|
|
for (const name of ['agent/turn-start', 'agent/step-start', 'agent/step-end', 'agent/turn-end'] as const) {
|
|
|
|
|
ctx.on(name, () => void order.push(name))
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
send(agent, 'hi')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(order).toEqual(['agent/turn-start', 'agent/step-start', 'agent/step-end', 'agent/turn-end'])
|
|
|
|
|
|
|
|
|
|
const types = agent.session.events.map(e => e.type)
|
2026-06-15 20:56:17 +08:00
|
|
|
// turn/start opens the turn, THEN the queued user message is recorded inside
|
2026-06-21 10:00:06 +08:00
|
|
|
// it (every event is turn-enclosed), then the assembled message (carrying the
|
|
|
|
|
// step's usage).
|
2026-06-15 20:56:17 +08:00
|
|
|
expect(types[0]).toBe('turn/start')
|
|
|
|
|
expect(types[1]).toBe('user/message')
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
expect(types).toContain('assistant/message')
|
2026-06-21 10:00:06 +08:00
|
|
|
const assistantMessage = agent.session.events.find(e => e.type === 'assistant/message')
|
|
|
|
|
expect(assistantMessage?.type === 'assistant/message' && assistantMessage.data.usage).toEqual({ inputTokens: 10, outputTokens: 'hello there'.length })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
expect(types.at(-1)).toBe('turn/end')
|
|
|
|
|
|
|
|
|
|
// derived history: user + assistant
|
|
|
|
|
const messages = agent.session.deriveMessages()
|
|
|
|
|
expect(messages.map(m => m.role)).toEqual(['user', 'assistant'])
|
Enable maximum-strict TypeScript across our packages
tsconfig.base.json adds noUncheckedIndexedAccess,
exactOptionalPropertyTypes, noImplicitOverride,
noFallthroughCasesInSwitch, noUnusedLocals, and noUnusedParameters on
top of strict. Vendored packages opt out of the new flags locally
(their tsconfigs are ours to regenerate; their source is not), keeping
upstream-sync friendliness.
Our code fixed accordingly: index accesses acknowledge undefined
(assembler flush cursors, lastTurnNumber); optional properties are
omitted instead of set-to-undefined (GenerateResult.usage,
ToolDefinition.strict, GenerateOptions.system/tools, error payloads
via an errorData helper); Session.onAppend is explicitly
`(…) => void | undefined`; tests and examples updated for unused
parameters and indexed access.
2026-06-11 14:02:47 +08:00
|
|
|
expect(messages[1]!.content).toEqual([{ type: 'text', text: 'hello there' }])
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('round-trips tool calls: model requests tool → executes → result in next request', async () => {
|
|
|
|
|
const adapter = new MockAdapter([
|
|
|
|
|
toolCallResponse('c1', 'echo', { text: 'ping' }, 'calling echo'),
|
|
|
|
|
textResponse('done'),
|
|
|
|
|
])
|
|
|
|
|
const ctx = await harness(adapter)
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
ctx.tools.register(defineTool({
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
name: 'echo',
|
|
|
|
|
description: 'echo back',
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
parameters: { text: { type: 'string' } },
|
|
|
|
|
async execute(args) {
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
return [{ type: 'text', text: `echo: ${args.text}` }]
|
|
|
|
|
},
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
}))
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
send(agent, 'use the tool')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
// two model calls happened (tool-call step, then final step)
|
|
|
|
|
expect(adapter.requests).toHaveLength(2)
|
|
|
|
|
|
|
|
|
|
// the second request's derived history contains the tool result
|
Enable maximum-strict TypeScript across our packages
tsconfig.base.json adds noUncheckedIndexedAccess,
exactOptionalPropertyTypes, noImplicitOverride,
noFallthroughCasesInSwitch, noUnusedLocals, and noUnusedParameters on
top of strict. Vendored packages opt out of the new flags locally
(their tsconfigs are ours to regenerate; their source is not), keeping
upstream-sync friendliness.
Our code fixed accordingly: index accesses acknowledge undefined
(assembler flush cursors, lastTurnNumber); optional properties are
omitted instead of set-to-undefined (GenerateResult.usage,
ToolDefinition.strict, GenerateOptions.system/tools, error payloads
via an errorData helper); Session.onAppend is explicitly
`(…) => void | undefined`; tests and examples updated for unused
parameters and indexed access.
2026-06-11 14:02:47 +08:00
|
|
|
const secondMessages = adapter.requests[1]!.messages
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
const toolResultMessage = secondMessages.find(m =>
|
|
|
|
|
m.content.some(b => b.type === 'tool-result'))
|
|
|
|
|
expect(toolResultMessage).toBeDefined()
|
|
|
|
|
const block = toolResultMessage!.content.find(b => b.type === 'tool-result')!
|
|
|
|
|
expect(block).toMatchObject({ toolCallId: 'c1', isError: false })
|
Add ESLint: typescript-eslint strict-type-checked + stylistic formatting
Flat config with two layers. Correctness (type-checked): the headline
rules for this codebase are no-floating-promises / no-misused-promises
(a lost promise in the agent loop is our primary bug class),
switch-exhaustiveness-check (we switch over merge-extensible unions
everywhere), no-unnecessary-condition, require-await, and
no-explicit-any. Style (@stylistic): 2-space, no semicolons, single
quotes, trailing commas, max-len 140 — the existing house style, now
enforced instead of drifting between agents. vendor/ is excluded
(vendored source keeps upstream style); tests relax the rules that
fight test ergonomics (non-null assertions after expects, async mock
signatures, non-Error throws).
Code adjusted to pass: registry disposers wrap ctx.effect's
promise-returning disposer behind a sync () => void (our public API),
BlockAssembler gains an invariant-checking mustGet instead of non-null
assertions, lastTurnNumber uses findLast, waterfall tails return
Promise.resolve instead of async-without-await arrows, and the two
deliberate suppressions (non-exhaustive derivation switch, unbound
execute pass-through) carry justification comments.
yarn lint / yarn lint:fix added.
2026-06-11 14:17:58 +08:00
|
|
|
expect((block).content).toEqual([{ type: 'text', text: 'echo: ping' }])
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
// session log records call + result
|
|
|
|
|
const types = agent.session.events.map(e => e.type)
|
|
|
|
|
expect(types).toContain('tool/call')
|
|
|
|
|
expect(types).toContain('tool/result')
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('passes assembled system prompt and tool schemas into the request', async () => {
|
|
|
|
|
const adapter = new MockAdapter([textResponse('ok')])
|
|
|
|
|
const ctx = await harness(adapter)
|
|
|
|
|
ctx.systemPrompt.section({ name: 'persona', order: 0, text: 'You are a test agent.' })
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
ctx.tools.register(defineTool({
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
name: 'noop',
|
|
|
|
|
description: 'does nothing',
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
parameters: {},
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
async execute() {
|
|
|
|
|
return []
|
|
|
|
|
},
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
}))
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock', systemPrompt: 'Agent-specific suffix.' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
send(agent, 'hi')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
const request = adapter.requests[0]
|
Enable maximum-strict TypeScript across our packages
tsconfig.base.json adds noUncheckedIndexedAccess,
exactOptionalPropertyTypes, noImplicitOverride,
noFallthroughCasesInSwitch, noUnusedLocals, and noUnusedParameters on
top of strict. Vendored packages opt out of the new flags locally
(their tsconfigs are ours to regenerate; their source is not), keeping
upstream-sync friendliness.
Our code fixed accordingly: index accesses acknowledge undefined
(assembler flush cursors, lastTurnNumber); optional properties are
omitted instead of set-to-undefined (GenerateResult.usage,
ToolDefinition.strict, GenerateOptions.system/tools, error payloads
via an errorData helper); Session.onAppend is explicitly
`(…) => void | undefined`; tests and examples updated for unused
parameters and indexed access.
2026-06-11 14:02:47 +08:00
|
|
|
expect(request!.system).toBe('You are a test agent.\n\nAgent-specific suffix.')
|
|
|
|
|
expect(request!.tools?.map(t => t.name)).toEqual(['noop'])
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('records raw chunks for replay and emits agent/stream-chunk', async () => {
|
|
|
|
|
const adapter = new MockAdapter([textResponse('abc')])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
const streamed: StreamChunk[] = []
|
|
|
|
|
ctx.on('agent/stream-chunk', (_agent, _turn, _step, chunk) => void streamed.push(chunk))
|
|
|
|
|
|
|
|
|
|
send(agent, 'hi')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
const chunkEvents = agent.session.events.filter(e => e.type === 'assistant/chunk')
|
|
|
|
|
// textResponse('abc') = block-start + 3 deltas + block-end + usage + finish = 7
|
|
|
|
|
expect(chunkEvents).toHaveLength(7)
|
|
|
|
|
expect(streamed).toHaveLength(7)
|
|
|
|
|
// replay: chunk events alone re-assemble to the recorded assistant message
|
|
|
|
|
const deltaText = chunkEvents
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
.flatMap(e => e.type === 'assistant/chunk' ? [e.data.chunk] : [])
|
|
|
|
|
.filter((c: StreamChunk): c is Extract<StreamChunk, { type: 'text-delta' }> => c.type === 'text-delta')
|
|
|
|
|
.map(c => c.text)
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
.join('')
|
|
|
|
|
expect(deltaText).toBe('abc')
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('injects steering between steps and continues the turn', async () => {
|
|
|
|
|
const adapter = new MockAdapter([
|
|
|
|
|
toolCallResponse('c1', 'slow', {}),
|
|
|
|
|
textResponse('addressed the steering'),
|
|
|
|
|
])
|
|
|
|
|
const ctx = await harness(adapter)
|
|
|
|
|
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
ctx.tools.register(defineTool({
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
name: 'slow',
|
|
|
|
|
description: '',
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
parameters: {},
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
async execute() {
|
|
|
|
|
// steer while the turn is running (during tool execution)
|
|
|
|
|
agent.steer([{ type: 'text', text: 'change of plans' }])
|
|
|
|
|
return [{ type: 'text', text: 'tool done' }]
|
|
|
|
|
},
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
}))
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
send(agent, 'start')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
const types = agent.session.events.map(e => e.type)
|
|
|
|
|
expect(types).toContain('steering/message')
|
|
|
|
|
// steering recorded before the second step's request derived its history
|
|
|
|
|
const steeringSeq = agent.session.events.find(e => e.type === 'steering/message')!.seq
|
|
|
|
|
const secondStepStart = agent.session.events.filter(e => e.type === 'step/start')[1]
|
|
|
|
|
expect(secondStepStart).toBeDefined()
|
|
|
|
|
expect(steeringSeq).toBeLessThan(secondStepStart!.seq)
|
|
|
|
|
|
|
|
|
|
// the second model request saw the steering content
|
|
|
|
|
const secondRequest = adapter.requests[1]
|
Enable maximum-strict TypeScript across our packages
tsconfig.base.json adds noUncheckedIndexedAccess,
exactOptionalPropertyTypes, noImplicitOverride,
noFallthroughCasesInSwitch, noUnusedLocals, and noUnusedParameters on
top of strict. Vendored packages opt out of the new flags locally
(their tsconfigs are ours to regenerate; their source is not), keeping
upstream-sync friendliness.
Our code fixed accordingly: index accesses acknowledge undefined
(assembler flush cursors, lastTurnNumber); optional properties are
omitted instead of set-to-undefined (GenerateResult.usage,
ToolDefinition.strict, GenerateOptions.system/tools, error payloads
via an errorData helper); Session.onAppend is explicitly
`(…) => void | undefined`; tests and examples updated for unused
parameters and indexed access.
2026-06-11 14:02:47 +08:00
|
|
|
const flat = JSON.stringify(secondRequest!.messages)
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
expect(flat).toContain('change of plans')
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('steering while idle behaves like send (starts a turn)', async () => {
|
|
|
|
|
const adapter = new MockAdapter([textResponse('ok')])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
agent.steer([{ type: 'text', text: 'hello' }])
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
expect(agent.session.events.some(e => e.type === 'user/message')).toBe(true)
|
|
|
|
|
})
|
|
|
|
|
|
2026-06-15 20:56:17 +08:00
|
|
|
it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => {
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
const adapter = new MockAdapter([textResponse('ok')])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } })
|
2026-06-15 20:56:17 +08:00
|
|
|
// The idle inject records a self-contained turn (turn/start → context/message
|
|
|
|
|
// → turn/end) so the event stays turn-enclosed, but does NOT run the model.
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
await new Promise(r => setTimeout(r, 20))
|
|
|
|
|
expect(agent.status).toBe('idle')
|
|
|
|
|
expect(adapter.requests).toHaveLength(0)
|
2026-06-15 20:56:17 +08:00
|
|
|
const injectedTurn = agent.session.events.filter(e => e.type === 'turn/start')
|
|
|
|
|
expect(injectedTurn).toHaveLength(1)
|
|
|
|
|
const it0 = injectedTurn[0]!
|
|
|
|
|
expect(it0.type === 'turn/start' && it0.data.trigger.kind).toBe('injection')
|
|
|
|
|
expect(agent.session.events.at(-1)!.type).toBe('turn/end') // turn-enclosed
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
Enable maximum-strict TypeScript across our packages
tsconfig.base.json adds noUncheckedIndexedAccess,
exactOptionalPropertyTypes, noImplicitOverride,
noFallthroughCasesInSwitch, noUnusedLocals, and noUnusedParameters on
top of strict. Vendored packages opt out of the new flags locally
(their tsconfigs are ours to regenerate; their source is not), keeping
upstream-sync friendliness.
Our code fixed accordingly: index accesses acknowledge undefined
(assembler flush cursors, lastTurnNumber); optional properties are
omitted instead of set-to-undefined (GenerateResult.usage,
ToolDefinition.strict, GenerateOptions.system/tools, error payloads
via an errorData helper); Session.onAppend is explicitly
`(…) => void | undefined`; tests and examples updated for unused
parameters and indexed access.
2026-06-11 14:02:47 +08:00
|
|
|
const flat = JSON.stringify(adapter.requests[0]!.messages)
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
expect(flat).toContain('file changed: a.ts')
|
|
|
|
|
expect(flat).toContain('<context source=\\"plugin\\">')
|
|
|
|
|
})
|
|
|
|
|
|
2026-06-15 20:56:17 +08:00
|
|
|
it('inject() while running appends into the open turn (no extra synthetic turn)', async () => {
|
|
|
|
|
const adapter = new MockAdapter([
|
|
|
|
|
toolCallResponse('c1', 'noticer', {}, 'calling'),
|
|
|
|
|
textResponse('done'),
|
|
|
|
|
])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
2026-06-15 20:56:17 +08:00
|
|
|
// A tool that injects mid-execution: at this point the agent is running, so
|
|
|
|
|
// inject must append the context/message into the ALREADY-open turn rather
|
|
|
|
|
// than wrap it in its own one-shot turn.
|
|
|
|
|
ctx.tools.register(defineTool({
|
|
|
|
|
name: 'noticer',
|
|
|
|
|
description: 'injects a notice',
|
|
|
|
|
parameters: {},
|
|
|
|
|
async execute() {
|
|
|
|
|
agent.inject([{ type: 'text', text: 'mid-turn notice' }], { source: { kind: 'plugin', plugin: 'x' } })
|
|
|
|
|
return [{ type: 'text', text: 'ok' }]
|
|
|
|
|
},
|
|
|
|
|
}))
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
// Exactly ONE turn ran (no synthetic injection turn), and the mid-turn
|
|
|
|
|
// context/message sits inside it.
|
|
|
|
|
const turnStarts = agent.session.events.filter(e => e.type === 'turn/start')
|
|
|
|
|
expect(turnStarts).toHaveLength(1)
|
|
|
|
|
const ts0 = turnStarts[0]!
|
|
|
|
|
expect(ts0.type === 'turn/start' && ts0.data.trigger.kind).toBe('message')
|
|
|
|
|
expect(agent.session.events.some(e => e.type === 'context/message')).toBe(true)
|
|
|
|
|
})
|
|
|
|
|
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
it('agent/turn-continuation can force-continue (/loop pattern) and force-stop', async () => {
|
|
|
|
|
// force-continue: model never calls tools, but a plugin forces 3 steps
|
|
|
|
|
const adapter = new MockAdapter([
|
|
|
|
|
textResponse('step 1'),
|
|
|
|
|
textResponse('step 2'),
|
|
|
|
|
textResponse('step 3'),
|
|
|
|
|
])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
let steps = 0
|
|
|
|
|
ctx.on('agent/step-end', () => void steps++)
|
|
|
|
|
ctx.on('agent/turn-continuation', async (_agent, _turn, _defaultDecision, next) => {
|
|
|
|
|
if (steps < 3) return true
|
|
|
|
|
return next()
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
expect(steps).toBe(3)
|
|
|
|
|
expect(adapter.requests).toHaveLength(3)
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('agent/turn-continuation can veto continuation despite tool calls (budget-guard pattern)', async () => {
|
|
|
|
|
const adapter = new MockAdapter([toolCallResponse('c1', 'echo', { text: 'x' })])
|
|
|
|
|
const ctx = await harness(adapter)
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
ctx.tools.register(defineTool({
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
name: 'echo',
|
|
|
|
|
description: '',
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
parameters: { text: { type: 'string' } },
|
|
|
|
|
async execute(args) {
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
return [{ type: 'text', text: String(args.text) }]
|
|
|
|
|
},
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
}))
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
ctx.on('agent/turn-continuation', async () => false as const)
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
// only one model call despite the tool call requesting a follow-up
|
|
|
|
|
expect(adapter.requests).toHaveLength(1)
|
|
|
|
|
// tool still executed before the decision
|
|
|
|
|
expect(agent.session.events.some(e => e.type === 'tool/result')).toBe(true)
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('agent/request waterfall can rewrite the request (model-switch pattern)', async () => {
|
|
|
|
|
const adapter = new MockAdapter([textResponse('ok')])
|
|
|
|
|
const ctx = await harness(adapter)
|
|
|
|
|
ctx.llm.registerAdapter(['other-model'], adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
ctx.on('agent/request', async (_agent, _turn, _step, options, next) => {
|
|
|
|
|
options.model = 'other-model'
|
|
|
|
|
return next()
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
send(agent, 'hi')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
Enable maximum-strict TypeScript across our packages
tsconfig.base.json adds noUncheckedIndexedAccess,
exactOptionalPropertyTypes, noImplicitOverride,
noFallthroughCasesInSwitch, noUnusedLocals, and noUnusedParameters on
top of strict. Vendored packages opt out of the new flags locally
(their tsconfigs are ours to regenerate; their source is not), keeping
upstream-sync friendliness.
Our code fixed accordingly: index accesses acknowledge undefined
(assembler flush cursors, lastTurnNumber); optional properties are
omitted instead of set-to-undefined (GenerateResult.usage,
ToolDefinition.strict, GenerateOptions.system/tools, error payloads
via an errorData helper); Session.onAppend is explicitly
`(…) => void | undefined`; tests and examples updated for unused
parameters and indexed access.
2026-06-11 14:02:47 +08:00
|
|
|
expect(adapter.requests[0]!.model).toBe('other-model')
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
})
|
|
|
|
|
|
simplify(agent): drop the unused public Agent.abort(), keep whenIdle()
The public Agent handle exposed abort() (step-only) and cancel() (queue-aware).
No production caller used abort() — ACP maps session/cancel to cancel(), and
lifecycle owners tear down via AgentHandle.dispose(); the loop's own stop paths
abort their per-step AbortController directly. So abort() is latent generality
that keeps a private loop mechanic public.
RFC-premise correction: the public-agent-stop-surface RFC proposed removing
whenIdle() too. Implementation found whenIdle() load-bearing — a real
quiescence primitive with a deliberate loop contract (settle-without-transition,
the replacement-turn race) and ACP test consumers; its proposed replacement
("observe the running->idle transition") is exactly the async-state race
AGENTS.md warns against. So only abort() is removed; whenIdle() stays. The RFC
is amended on the way to implemented/ to record the narrowed scope, and the new
AGENTS.md "RFCs are proposals, not golden truth" principle (PR1) gets its
worked example.
- Remove Agent.abort() from the interface + the ReactLoopAgent impl; the no-arg
'aborted' default goes with it (cancel() keeps its 'cancelled' default).
- Migrate tests: empty-queue abort() -> cancel(reason); the two review-fixes
tests whose subject is the in-flight step's AbortController drive that
controller directly via the private currentAbort field (cancel() would clear
the inbox and destroy the queued steering one of them proves survives a step
abort). The no-arg-default test is dropped (cancel()'s default is already
covered in cancel.spec.ts).
- Resulting public stop surface: cancel() + whenIdle(). Update agent/agent-loop
READMEs, architecture.md, core.md type-equiv, the extension cookbook, the
lifecycle RFC (short note), and the proposed ACP RFC.
Implements docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md
2026-06-21 05:50:39 +08:00
|
|
|
it('cancel() mid-stream ends the turn with reason aborted', async () => {
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
const adapter = new MockAdapter(['hang'])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
const reasons: TurnEndReason[] = []
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
simplify(agent): drop the unused public Agent.abort(), keep whenIdle()
The public Agent handle exposed abort() (step-only) and cancel() (queue-aware).
No production caller used abort() — ACP maps session/cancel to cancel(), and
lifecycle owners tear down via AgentHandle.dispose(); the loop's own stop paths
abort their per-step AbortController directly. So abort() is latent generality
that keeps a private loop mechanic public.
RFC-premise correction: the public-agent-stop-surface RFC proposed removing
whenIdle() too. Implementation found whenIdle() load-bearing — a real
quiescence primitive with a deliberate loop contract (settle-without-transition,
the replacement-turn race) and ACP test consumers; its proposed replacement
("observe the running->idle transition") is exactly the async-state race
AGENTS.md warns against. So only abort() is removed; whenIdle() stays. The RFC
is amended on the way to implemented/ to record the narrowed scope, and the new
AGENTS.md "RFCs are proposals, not golden truth" principle (PR1) gets its
worked example.
- Remove Agent.abort() from the interface + the ReactLoopAgent impl; the no-arg
'aborted' default goes with it (cancel() keeps its 'cancelled' default).
- Migrate tests: empty-queue abort() -> cancel(reason); the two review-fixes
tests whose subject is the in-flight step's AbortController drive that
controller directly via the private currentAbort field (cancel() would clear
the inbox and destroy the queued steering one of them proves survives a step
abort). The no-arg-default test is dropped (cancel()'s default is already
covered in cancel.spec.ts).
- Resulting public stop surface: cancel() + whenIdle(). Update agent/agent-loop
READMEs, architecture.md, core.md type-equiv, the extension cookbook, the
lifecycle RFC (short note), and the proposed ACP RFC.
Implements docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md
2026-06-21 05:50:39 +08:00
|
|
|
// wait until the stream is hanging, then cancel
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
await new Promise(r => setTimeout(r, 30))
|
|
|
|
|
expect(agent.status).toBe('running')
|
simplify(agent): drop the unused public Agent.abort(), keep whenIdle()
The public Agent handle exposed abort() (step-only) and cancel() (queue-aware).
No production caller used abort() — ACP maps session/cancel to cancel(), and
lifecycle owners tear down via AgentHandle.dispose(); the loop's own stop paths
abort their per-step AbortController directly. So abort() is latent generality
that keeps a private loop mechanic public.
RFC-premise correction: the public-agent-stop-surface RFC proposed removing
whenIdle() too. Implementation found whenIdle() load-bearing — a real
quiescence primitive with a deliberate loop contract (settle-without-transition,
the replacement-turn race) and ACP test consumers; its proposed replacement
("observe the running->idle transition") is exactly the async-state race
AGENTS.md warns against. So only abort() is removed; whenIdle() stays. The RFC
is amended on the way to implemented/ to record the narrowed scope, and the new
AGENTS.md "RFCs are proposals, not golden truth" principle (PR1) gets its
worked example.
- Remove Agent.abort() from the interface + the ReactLoopAgent impl; the no-arg
'aborted' default goes with it (cancel() keeps its 'cancelled' default).
- Migrate tests: empty-queue abort() -> cancel(reason); the two review-fixes
tests whose subject is the in-flight step's AbortController drive that
controller directly via the private currentAbort field (cancel() would clear
the inbox and destroy the queued steering one of them proves survives a step
abort). The no-arg-default test is dropped (cancel()'s default is already
covered in cancel.spec.ts).
- Resulting public stop surface: cancel() + whenIdle(). Update agent/agent-loop
READMEs, architecture.md, core.md type-equiv, the extension cookbook, the
lifecycle RFC (short note), and the proposed ACP RFC.
Implements docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md
2026-06-21 05:50:39 +08:00
|
|
|
agent.cancel('user interrupt')
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }])
|
|
|
|
|
})
|
|
|
|
|
|
2026-06-15 23:53:47 +08:00
|
|
|
it('surfaces max-tokens as the turn-end reason when the last step is cut off', async () => {
|
|
|
|
|
// A single step that ends with a max-tokens finish (no tool calls): the
|
|
|
|
|
// turn stops by default and ends max-tokens, not completed.
|
|
|
|
|
const adapter = new MockAdapter([maxTokensResponse('truncat')])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
2026-06-15 23:53:47 +08:00
|
|
|
|
|
|
|
|
const reasons: TurnEndReason[] = []
|
|
|
|
|
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(adapter.requests).toHaveLength(1)
|
|
|
|
|
expect(reasons).toEqual([{ kind: 'max-tokens' }])
|
|
|
|
|
// and the reason is recorded in the log's turn/end event
|
|
|
|
|
const turnEnd = agent.session.events.findLast(e => e.type === 'turn/end')
|
|
|
|
|
expect(turnEnd!.data.reason).toEqual({ kind: 'max-tokens' })
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('a max-tokens step earlier in a turn still surfaces as max-tokens after a later completed step', async () => {
|
|
|
|
|
// Step 1 is cut off (max-tokens, no tool calls → would stop by default), so
|
|
|
|
|
// continuation must be FORCED to reach step 2 which finishes normally
|
|
|
|
|
// (stop). The rule "any max-tokens step surfaces as max-tokens" means the
|
|
|
|
|
// turn ends max-tokens even though the LAST step completed cleanly.
|
|
|
|
|
const adapter = new MockAdapter([
|
|
|
|
|
maxTokensResponse('first half'),
|
|
|
|
|
textResponse('second half'),
|
|
|
|
|
])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
2026-06-15 23:53:47 +08:00
|
|
|
|
|
|
|
|
let steps = 0
|
|
|
|
|
ctx.on('agent/step-end', () => void steps++)
|
|
|
|
|
// Force exactly one continuation (step 1 → step 2), then defer to default
|
|
|
|
|
// (step 2 is a plain stop with no tool calls → stops).
|
|
|
|
|
ctx.on('agent/turn-continuation', async (_agent, _turn, _defaultDecision, next) => {
|
|
|
|
|
if (steps < 2) return true
|
|
|
|
|
return next()
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
const reasons: TurnEndReason[] = []
|
|
|
|
|
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(steps).toBe(2)
|
|
|
|
|
expect(adapter.requests).toHaveLength(2)
|
2026-06-19 00:37:12 +08:00
|
|
|
expect(adapter.requests[1]!.messages).toEqual([
|
|
|
|
|
{ role: 'user', content: [{ type: 'text', text: 'go' }] },
|
|
|
|
|
{ role: 'assistant', content: [{ type: 'text', text: 'first half' }] },
|
|
|
|
|
])
|
2026-06-15 23:53:47 +08:00
|
|
|
expect(reasons).toEqual([{ kind: 'max-tokens' }])
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('a completed step after no max-tokens keeps the turn completed (max-tokens does not leak across turns)', async () => {
|
|
|
|
|
// Two consecutive turns: turn 1 is cut off (max-tokens), turn 2 is a clean
|
|
|
|
|
// stop. The per-turn reason must be independent — turn 2 ends completed.
|
|
|
|
|
const adapter = new MockAdapter([maxTokensResponse('cut'), textResponse('clean')])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
2026-06-15 23:53:47 +08:00
|
|
|
|
|
|
|
|
const reasons: TurnEndReason[] = []
|
|
|
|
|
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
|
|
|
|
|
|
|
|
|
|
send(agent, 'first')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
send(agent, 'second')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(reasons).toEqual([{ kind: 'max-tokens' }, { kind: 'completed' }])
|
|
|
|
|
})
|
|
|
|
|
|
2026-06-17 21:25:47 +08:00
|
|
|
it('does not dispatch tool calls from a max-tokens-truncated step', async () => {
|
|
|
|
|
const callId = CallId('c1')
|
|
|
|
|
const adapter = new MockAdapter([[
|
|
|
|
|
{ type: 'block-start', index: 0, blockType: 'tool-call' },
|
|
|
|
|
{ type: 'tool-call-delta', index: 0, id: callId, name: 'echo', argumentsDelta: '{"text":"x"}' },
|
|
|
|
|
{ type: 'block-end', index: 0, block: { type: 'tool-call', id: callId, name: 'echo', arguments: '{"text":"x"}' } },
|
|
|
|
|
{ type: 'usage', usage: { inputTokens: 10, outputTokens: 5 } },
|
|
|
|
|
{ type: 'finish', reason: { kind: 'max-tokens' } },
|
|
|
|
|
]])
|
|
|
|
|
const ctx = await harness(adapter)
|
|
|
|
|
let executions = 0
|
|
|
|
|
ctx.tools.register(defineTool({
|
|
|
|
|
name: 'echo',
|
|
|
|
|
description: '',
|
|
|
|
|
parameters: { text: { type: 'string' } },
|
|
|
|
|
async execute() {
|
|
|
|
|
executions += 1
|
|
|
|
|
return [{ type: 'text', text: 'should not run' }]
|
|
|
|
|
},
|
|
|
|
|
}))
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
2026-06-17 21:25:47 +08:00
|
|
|
|
|
|
|
|
const reasons: TurnEndReason[] = []
|
|
|
|
|
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(executions).toBe(0)
|
|
|
|
|
expect(agent.session.events.some(e => e.type === 'tool/call')).toBe(false)
|
2026-06-19 00:37:12 +08:00
|
|
|
expect(agent.session.deriveMessages()).toEqual([{ role: 'user', content: [{ type: 'text', text: 'go' }] }])
|
|
|
|
|
expect(reasons).toEqual([{ kind: 'max-tokens' }])
|
2026-06-21 10:00:06 +08:00
|
|
|
// No-data-loss: a max-tokens step whose only content was a dropped tool call
|
|
|
|
|
// has EMPTY assistant content, but its usage must still be represented. It
|
|
|
|
|
// rides on an (empty-content) assistant/message — there is no standalone
|
|
|
|
|
// usage event — and that empty message is skipped by deriveMessages(), so
|
|
|
|
|
// the derived history above is NOT corrupted by a spurious assistant turn.
|
|
|
|
|
const assistantMessage = agent.session.events.find(e => e.type === 'assistant/message')
|
|
|
|
|
expect(assistantMessage?.type === 'assistant/message' && assistantMessage.data).toEqual({
|
|
|
|
|
turn: 1, step: 1, content: [], usage: { inputTokens: 10, outputTokens: 5 },
|
|
|
|
|
})
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('appends no assistant/message for a max-tokens step with empty content and no usage', async () => {
|
|
|
|
|
// A max-tokens step truncated to a dropped tool call AND with no usage chunk
|
|
|
|
|
// has nothing to record: empty content and no accounting → no assistant/message
|
|
|
|
|
// (the empty-content host exists only to carry usage). The turn still ends
|
|
|
|
|
// max-tokens.
|
|
|
|
|
const callId = CallId('c1')
|
|
|
|
|
const adapter = new MockAdapter([[
|
|
|
|
|
{ type: 'block-start', index: 0, blockType: 'tool-call' },
|
|
|
|
|
{ type: 'tool-call-delta', index: 0, id: callId, name: 'echo', argumentsDelta: '{"text":"x"}' },
|
|
|
|
|
{ type: 'block-end', index: 0, block: { type: 'tool-call', id: callId, name: 'echo', arguments: '{"text":"x"}' } },
|
|
|
|
|
{ type: 'finish', reason: { kind: 'max-tokens' } },
|
|
|
|
|
]])
|
|
|
|
|
const ctx = await harness(adapter)
|
|
|
|
|
ctx.tools.register(defineTool({
|
|
|
|
|
name: 'echo',
|
|
|
|
|
description: '',
|
|
|
|
|
parameters: { text: { type: 'string' } },
|
|
|
|
|
async execute() { return [{ type: 'text', text: 'should not run' }] },
|
|
|
|
|
}))
|
|
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
|
|
|
|
|
|
|
|
|
const reasons: TurnEndReason[] = []
|
|
|
|
|
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(reasons).toEqual([{ kind: 'max-tokens' }])
|
|
|
|
|
expect(agent.session.events.some(e => e.type === 'assistant/message')).toBe(false)
|
|
|
|
|
expect(agent.session.deriveMessages()).toEqual([{ role: 'user', content: [{ type: 'text', text: 'go' }] }])
|
2026-06-19 00:37:12 +08:00
|
|
|
})
|
|
|
|
|
|
2026-06-21 11:08:10 +08:00
|
|
|
it('appends no assistant/message for a normal stop finish with empty content and no usage', async () => {
|
|
|
|
|
// A clean `stop` finish that streamed nothing assembled (no blocks) and
|
|
|
|
|
// carried no usage chunk has nothing to record: the content-or-usage guard
|
|
|
|
|
// on the normal step path suppresses a pure trace-only empty assistant/message.
|
|
|
|
|
const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]])
|
|
|
|
|
const ctx = await harness(adapter)
|
|
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
|
|
|
|
|
|
|
|
|
const reasons: TurnEndReason[] = []
|
|
|
|
|
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(reasons).toEqual([{ kind: 'completed' }])
|
|
|
|
|
expect(agent.session.events.some(e => e.type === 'assistant/message')).toBe(false)
|
|
|
|
|
expect(agent.session.deriveMessages()).toEqual([{ role: 'user', content: [{ type: 'text', text: 'go' }] }])
|
|
|
|
|
})
|
|
|
|
|
|
2026-06-19 00:37:12 +08:00
|
|
|
it('keeps safe max-tokens assistant content while dropping truncated tool calls', async () => {
|
|
|
|
|
const callId = CallId('c1')
|
|
|
|
|
const adapter = new MockAdapter([[
|
|
|
|
|
{ type: 'block-start', index: 0, blockType: 'text' },
|
|
|
|
|
{ type: 'text-delta', index: 0, text: 'partial text' },
|
|
|
|
|
{ type: 'block-end', index: 0, block: { type: 'text', text: 'partial text' } },
|
|
|
|
|
{ type: 'block-start', index: 1, blockType: 'tool-call' },
|
|
|
|
|
{ type: 'tool-call-delta', index: 1, id: callId, name: 'echo', argumentsDelta: '{"text"' },
|
|
|
|
|
{ type: 'finish', reason: { kind: 'max-tokens' } },
|
|
|
|
|
]])
|
|
|
|
|
const ctx = await harness(adapter)
|
|
|
|
|
let stepResults = 0
|
|
|
|
|
ctx.on('agent/step-result', async (_agent, _turn, _step, message, next) => {
|
|
|
|
|
stepResults += 1
|
|
|
|
|
expect(message.content).toEqual([{ type: 'text', text: 'partial text' }])
|
|
|
|
|
return next()
|
|
|
|
|
})
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
2026-06-19 00:37:12 +08:00
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(stepResults).toBe(1)
|
|
|
|
|
expect(agent.session.events.some(e => e.type === 'tool/call')).toBe(false)
|
2026-06-17 21:25:47 +08:00
|
|
|
expect(agent.session.deriveMessages()).toEqual([
|
|
|
|
|
{ role: 'user', content: [{ type: 'text', text: 'go' }] },
|
2026-06-19 00:37:12 +08:00
|
|
|
{ role: 'assistant', content: [{ type: 'text', text: 'partial text' }] },
|
2026-06-17 21:25:47 +08:00
|
|
|
])
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('stops the turn when agent/step-end listener failure has recorded an error', async () => {
|
|
|
|
|
const adapter = new MockAdapter([
|
|
|
|
|
toolCallResponse('c1', 'echo', { text: 'x' }),
|
|
|
|
|
textResponse('should not run'),
|
|
|
|
|
])
|
|
|
|
|
const ctx = await harness(adapter)
|
|
|
|
|
ctx.tools.register(defineTool({
|
|
|
|
|
name: 'echo',
|
|
|
|
|
description: '',
|
|
|
|
|
parameters: { text: { type: 'string' } },
|
|
|
|
|
async execute(args) {
|
|
|
|
|
return [{ type: 'text', text: String(args.text) }]
|
|
|
|
|
},
|
|
|
|
|
}))
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
2026-06-17 21:25:47 +08:00
|
|
|
let threw = false
|
|
|
|
|
ctx.on('agent/step-end', () => {
|
|
|
|
|
if (!threw) { threw = true; throw new Error('bad step-end listener') }
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
send(agent, 'go')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(adapter.requests).toHaveLength(1)
|
|
|
|
|
const turnEnd = agent.session.events.findLast(e => e.type === 'turn/end')
|
|
|
|
|
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('error')
|
|
|
|
|
})
|
|
|
|
|
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
it('chains queued messages into consecutive turns', async () => {
|
|
|
|
|
const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
const turns: number[] = []
|
|
|
|
|
ctx.on('agent/turn-start', (_agent, turn) => void turns.push(turn))
|
|
|
|
|
|
|
|
|
|
// queue two messages while idle — first starts turn 1 immediately;
|
|
|
|
|
// queue the second during turn 1 via a stream-chunk hook
|
|
|
|
|
let queued = false
|
|
|
|
|
ctx.on('agent/stream-chunk', () => {
|
|
|
|
|
if (!queued) {
|
|
|
|
|
queued = true
|
|
|
|
|
send(agent, 'second message')
|
|
|
|
|
}
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
send(agent, 'first message')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(turns).toEqual([1, 2])
|
|
|
|
|
expect(adapter.requests).toHaveLength(2)
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('awaits session/flush at turn end (persistence checkpoint)', async () => {
|
|
|
|
|
const adapter = new MockAdapter([textResponse('ok')])
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
let flushed = 0
|
|
|
|
|
let flushedBeforeIdle = false
|
|
|
|
|
ctx.on('session/flush', async (session) => {
|
|
|
|
|
await new Promise(r => setTimeout(r, 10))
|
|
|
|
|
flushed++
|
|
|
|
|
flushedBeforeIdle = agent.status !== 'idle'
|
|
|
|
|
void session
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
send(agent, 'hi')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
expect(flushed).toBe(1)
|
|
|
|
|
expect(flushedBeforeIdle).toBe(true)
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('errors from the model surface as agent/error and end the turn', async () => {
|
|
|
|
|
const adapter = new MockAdapter([]) // script exhausted → throws
|
|
|
|
|
const ctx = await harness(adapter)
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
|
|
|
|
|
const errors: Error[] = []
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
const reasons: TurnEndReason[] = []
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
|
|
|
|
|
ctx.on('agent/turn-end', (_agent, _turn, reason) => void reasons.push(reason))
|
|
|
|
|
|
|
|
|
|
send(agent, 'hi')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
|
|
|
|
expect(errors).toHaveLength(1)
|
Enable maximum-strict TypeScript across our packages
tsconfig.base.json adds noUncheckedIndexedAccess,
exactOptionalPropertyTypes, noImplicitOverride,
noFallthroughCasesInSwitch, noUnusedLocals, and noUnusedParameters on
top of strict. Vendored packages opt out of the new flags locally
(their tsconfigs are ours to regenerate; their source is not), keeping
upstream-sync friendliness.
Our code fixed accordingly: index accesses acknowledge undefined
(assembler flush cursors, lastTurnNumber); optional properties are
omitted instead of set-to-undefined (GenerateResult.usage,
ToolDefinition.strict, GenerateOptions.system/tools, error payloads
via an errorData helper); Session.onAppend is explicitly
`(…) => void | undefined`; tests and examples updated for unused
parameters and indexed access.
2026-06-11 14:02:47 +08:00
|
|
|
expect(errors[0]!.message).toContain('script exhausted')
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
expect(reasons[0]).toMatchObject({ kind: 'error' })
|
2026-06-21 10:00:06 +08:00
|
|
|
// The durable failure lives entirely on turn/end.reason (with the failing
|
|
|
|
|
// step), not a standalone error event.
|
|
|
|
|
const turnEnd = agent.session.events.find(e => e.type === 'turn/end')
|
|
|
|
|
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toMatchObject({ kind: 'error', step: 1 })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
})
|
|
|
|
|
|
|
|
|
|
it('disposing the loop fiber mid-turn stops the loop (HMR safety)', async () => {
|
|
|
|
|
const adapter = new MockAdapter(['hang'])
|
|
|
|
|
const ctx = await harness(adapter)
|
|
|
|
|
|
2026-06-19 10:13:33 +08:00
|
|
|
let agent!: ReactLoopAgent
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
const fiber = await ctx.plugin(Object.assign((inner: Context) => {
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
}, { inject: ['agentLoop'] }))
|
|
|
|
|
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
expect(ctx.agents.get(AgentId('scoped'))).toBe(agent)
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
send(agent, 'go')
|
|
|
|
|
await new Promise(r => setTimeout(r, 30))
|
|
|
|
|
expect(agent.status).toBe('running')
|
|
|
|
|
|
|
|
|
|
await fiber.dispose()
|
|
|
|
|
await agent.done
|
|
|
|
|
|
|
|
|
|
expect(agent.status).toBe('disposed')
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined()
|
Add ESLint: typescript-eslint strict-type-checked + stylistic formatting
Flat config with two layers. Correctness (type-checked): the headline
rules for this codebase are no-floating-promises / no-misused-promises
(a lost promise in the agent loop is our primary bug class),
switch-exhaustiveness-check (we switch over merge-extensible unions
everywhere), no-unnecessary-condition, require-await, and
no-explicit-any. Style (@stylistic): 2-space, no semicolons, single
quotes, trailing commas, max-len 140 — the existing house style, now
enforced instead of drifting between agents. vendor/ is excluded
(vendored source keeps upstream style); tests relax the rules that
fight test ergonomics (non-null assertions after expects, async mock
signatures, non-Error throws).
Code adjusted to pass: registry disposers wrap ctx.effect's
promise-returning disposer behind a sync () => void (our public API),
BlockAssembler gains an invariant-checking mustGet instead of non-null
assertions, lastTurnNumber uses findLast, waterfall tails return
Promise.resolve instead of async-without-await arrows, and the two
deliberate suppressions (non-exhaustive derivation switch, unbound
execute pass-through) carry justification comments.
yarn lint / yarn lint:fix added.
2026-06-11 14:17:58 +08:00
|
|
|
expect(() => { send(agent, 'too late') }).toThrow('disposed')
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
})
|
|
|
|
|
|
Enforce 100% per-file test coverage on packages/*/src
vitest coverage (v8 provider) with per-file 100% thresholds for
statements, branches, functions, and lines. Scope: our runtime source
only — types-only files, vendor/ (upstream code), and examples/
(exercised by the demo smoke test) are excluded. yarn test:coverage
runs the gate.
59 tests added to close every gap: llm generate-waterfall and adapter
disposal; assembler edge protocol (duplicate block-start, stragglers
after block-end, id fallback, usage omission, invariant violation);
the whole Inbox surface incl. the wakeup-overwrite race; LoopAgent
disposed-state throws and double-stop idempotence; config-driven agent
creation; loop backstop catches (throwing turn-start/turn-end
listeners, non-Error throws, non-JSON tool arguments); system-prompt
dynamic sections and disposer paths; tools errorMessage fallbacks and
the full schema-DSL emission matrix. Genuinely unreachable defensive
guards carry /* v8 ignore */ comments with stated reasons rather than
deletion (132 tests total).
2026-06-11 14:58:36 +08:00
|
|
|
it('creates agents from config on startup', async () => {
|
|
|
|
|
const adapter = new MockAdapter([textResponse('from config')])
|
|
|
|
|
const ctx = new Context()
|
|
|
|
|
await ctx.plugin(LlmService)
|
|
|
|
|
await ctx.plugin(SessionStore)
|
|
|
|
|
await ctx.plugin(SystemPrompt)
|
|
|
|
|
await ctx.plugin(ToolRegistry)
|
|
|
|
|
await ctx.plugin(AgentRegistry)
|
|
|
|
|
await ctx.plugin(AgentLoop, {
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
agents: [{ id: AgentId('config-agent'), model: 'mock', systemPrompt: 'Config prompt' }],
|
Enforce 100% per-file test coverage on packages/*/src
vitest coverage (v8 provider) with per-file 100% thresholds for
statements, branches, functions, and lines. Scope: our runtime source
only — types-only files, vendor/ (upstream code), and examples/
(exercised by the demo smoke test) are excluded. yarn test:coverage
runs the gate.
59 tests added to close every gap: llm generate-waterfall and adapter
disposal; assembler edge protocol (duplicate block-start, stragglers
after block-end, id fallback, usage omission, invariant violation);
the whole Inbox surface incl. the wakeup-overwrite race; LoopAgent
disposed-state throws and double-stop idempotence; config-driven agent
creation; loop backstop catches (throwing turn-start/turn-end
listeners, non-Error throws, non-JSON tool arguments); system-prompt
dynamic sections and disposer paths; tools errorMessage fallbacks and
the full schema-DSL emission matrix. Genuinely unreachable defensive
guards carry /* v8 ignore */ comments with stated reasons rather than
deletion (132 tests total).
2026-06-11 14:58:36 +08:00
|
|
|
})
|
|
|
|
|
ctx.llm.registerAdapter(['mock'], adapter)
|
|
|
|
|
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent
|
Enforce 100% per-file test coverage on packages/*/src
vitest coverage (v8 provider) with per-file 100% thresholds for
statements, branches, functions, and lines. Scope: our runtime source
only — types-only files, vendor/ (upstream code), and examples/
(exercised by the demo smoke test) are excluded. yarn test:coverage
runs the gate.
59 tests added to close every gap: llm generate-waterfall and adapter
disposal; assembler edge protocol (duplicate block-start, stragglers
after block-end, id fallback, usage omission, invariant violation);
the whole Inbox surface incl. the wakeup-overwrite race; LoopAgent
disposed-state throws and double-stop idempotence; config-driven agent
creation; loop backstop catches (throwing turn-start/turn-end
listeners, non-Error throws, non-JSON tool arguments); system-prompt
dynamic sections and disposer paths; tools errorMessage fallbacks and
the full schema-DSL emission matrix. Genuinely unreachable defensive
guards carry /* v8 ignore */ comments with stated reasons rather than
deletion (132 tests total).
2026-06-11 14:58:36 +08:00
|
|
|
expect(agent).toBeDefined()
|
|
|
|
|
expect(agent.id).toBe('config-agent')
|
|
|
|
|
expect(agent.options.model).toBe('mock')
|
|
|
|
|
|
|
|
|
|
// the agent is alive: send triggers a turn
|
|
|
|
|
send(agent, 'hi')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
expect(adapter.requests).toHaveLength(1)
|
|
|
|
|
})
|
|
|
|
|
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
it('replays a session log into an identical derived history', async () => {
|
|
|
|
|
const adapter = new MockAdapter([
|
|
|
|
|
toolCallResponse('c1', 'echo', { text: 'x' }),
|
|
|
|
|
textResponse('done'),
|
|
|
|
|
])
|
|
|
|
|
const ctx = await harness(adapter)
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
ctx.tools.register(defineTool({
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
name: 'echo',
|
|
|
|
|
description: '',
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
parameters: { text: { type: 'string' } },
|
|
|
|
|
async execute(args) {
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
return [{ type: 'text', text: String(args.text) }]
|
|
|
|
|
},
|
Document the codebase thoroughly and tighten type safety
Docs: per-folder README.md for packages/ (family overview + one per
package: service, events, API, extension points, TODOs), examples/,
and examples/echo-agent/; folder-level AGENTS.md (+ CLAUDE.md
symlinks) for packages/ and vendor/; module-level doc comments in
every packages/*/src file; richer JSDoc on all exported API
(event side effects, disposal contracts, error behavior). Root
AGENTS.md gains a "Type Safety and Documentation" policy section:
the codebase aims to be very type-safe and well documented; type
gymnastics are acceptable in core packages when they improve
plugin-author DX; verbose docs are fine as long as they stay strictly
in sync with the code.
Type safety: removed the upstream-inherited "noImplicitAny": false
from tsconfig.base.json — packages/* now compile under full strict
mode; vendor/loader and vendor/include set it locally (vendor/cordis
already did). Eliminated every `: any` / `as any` from packages and
examples (catch clauses use unknown + a CodedError narrowing type;
event data access uses discriminated-union narrowing).
Typed tool schemas: new @deepseek-ai/dsh-tools schema DSL —
SchemaSpec with per-property `required: true` booleans, type-level
InferArgs<S>, a runtime SchemaSpec → JSON Schema converter, and
defineTool() so first-party tools get typed execute(args) with zero
casts (raw JSON Schema still accepted for MCP interop; chosen over
schemastery because it targets JSON Schema generation directly).
echo-tool and all test tools migrated; +7 tests.
2026-06-11 12:39:27 +08:00
|
|
|
}))
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
send(agent, 'run')
|
|
|
|
|
await waitForIdle(ctx, agent)
|
|
|
|
|
|
feat(types): brand bash ids + stop brand erosion; extract Branded to dsh-brand
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
2026-06-21 07:17:25 +08:00
|
|
|
const replayed = ctx.sessions.create(SessionId('replayed'), { seed: [...agent.session.events] })
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
expect(replayed.deriveMessages()).toEqual(agent.session.deriveMessages())
|
|
|
|
|
// event-by-event identity of types
|
|
|
|
|
expect(replayed.events.map(e => e.type)).toEqual(
|
Add ESLint: typescript-eslint strict-type-checked + stylistic formatting
Flat config with two layers. Correctness (type-checked): the headline
rules for this codebase are no-floating-promises / no-misused-promises
(a lost promise in the agent loop is our primary bug class),
switch-exhaustiveness-check (we switch over merge-extensible unions
everywhere), no-unnecessary-condition, require-await, and
no-explicit-any. Style (@stylistic): 2-space, no semicolons, single
quotes, trailing commas, max-len 140 — the existing house style, now
enforced instead of drifting between agents. vendor/ is excluded
(vendored source keeps upstream style); tests relax the rules that
fight test ergonomics (non-null assertions after expects, async mock
signatures, non-Error throws).
Code adjusted to pass: registry disposers wrap ctx.effect's
promise-returning disposer behind a sync () => void (our public API),
BlockAssembler gains an invariant-checking mustGet instead of non-null
assertions, lastTurnNumber uses findLast, waterfall tails return
Promise.resolve instead of async-without-await arrows, and the two
deliberate suppressions (non-exhaustive derivation switch, unbound
execute pass-through) carry justification comments.
yarn lint / yarn lint:fix added.
2026-06-11 14:17:58 +08:00
|
|
|
agent.session.events.map(e => e.type))
|
Implement the agent loop plugin
@deepseek-ai/dsh-agent-loop: LoopAgent (inbox with queued + steering
FIFOs, per-step AbortController) and the streaming-first
session/turn/step loop. Extension seams: agent/request,
agent/step-result, agent/turn-continuation waterfalls; raw chunks
logged for replay while BlockAssembler builds the assembled message;
steering drains between steps; session/flush awaited at turn end.
16 tests with a scripted mock adapter cover turn lifecycle ordering,
tool round-trips, steering, inject(), continuation override/veto,
mid-stream abort, queued turn chaining, replay equivalence, and
mid-turn fiber disposal (HMR safety).
2026-06-11 10:54:31 +08:00
|
|
|
})
|
|
|
|
|
})
|