deepseek-harness/examples/coding-agent/cordis.yml

139 lines
4.8 KiB
YAML
Raw Normal View History

# Readline coding REPL with swappable DeepSeek and local-bash backends.
# `dsh-stdio-demo` supplies the agent spine, workspace instructions, generic
# task controls, JSONL persistence, the line-oriented front door, and `main`.
# HMR remains a leaf because it requires Loader internals; `demo:repl` passes
# `--expose-internals`. The app bin loads the gitignored root `.env`; this file
# reads `DEEPSEEK_API_KEY` and optional `DEEPSEEK_BASE_URL` through `!!js`.
refactor(examples): extract the app spine into dsh-agent-core + app packages Implements docs/rfc/.../2026-06-20-extract-example-app-packages.md. Each example was thick — a hand-rolled start.ts, an infra preamble, nested base.yml/base-core.yml/acp-tail.yml includes, and a coupled front-door cluster enforced only by prose. This moves the composition into packages so each example is a thin leaf cordis.yml: pick the swappable backends, load one app package. New packages: - @deepseek-ai/dsh-agent-core (packages/core/agent-core): one bundle plugin that loads the providerless/executor-less/UI-less spine (timer + llm + sessions + system-prompt + tools + agents + invariants + tool-bash + agent-loop) via ctx.plugin(...) inside apply(), and forwards agent-loop's `agents` list as its own Config (export const Config = AgentLoop.Config, default []). - @deepseek-ai/dsh-stdio-agent (packages/ui/stdio-agent): terminal chat APP — agent-core + console logger + readline UI + a pre-created `main` agent, with a bin. The demo:echo/coding front door. - @deepseek-ai/dsh-acp-agent (packages/ui/acp-agent): ACP server APP — agent-core + JSONL persistence + the acp bridge, NO stdout logger, with a bin. The stdout-purity footgun is structurally unreachable from the leaf. Amendment to the RFC: hmr stays a LEAF cordis.yml entry, not baked into dsh-stdio-agent. hmr is a Loader-only dev plugin (throws without --expose-internals; the in-process test tier can't even import its decorator form), so a package statically importing it could never carry the per-file coverage gate. Unlike the console logger, a stray hmr is not a stdout-purity footgun, so leaving it at the leaf costs no safety. With hmr out, all three new packages carry in-process unit specs at 100%. Boot glue (Loader tail, .env load, snapshot-mode selection, stdin-dispose lifecycle) moves into each app's bin; start.ts and base.yml/base-core.yml/ acp-tail.yml are deleted. Each app package gets a keyless real-load-path test that boots through its bin + the cordis Loader (guarding the unwrapExports export-shape bug class, postmortem 0001). ACP snapshot replay stays green against the existing committed goldens (pure boot restructuring). RFC moved proposed->implemented with the amendment recorded; package/example/architecture docs and the module graph updated.
2026-06-21 12:03:44 +08:00
# Hot-module reload for the dev/demo loop (needs `node --expose-internals`).
- id: hmr
name: '@cordisjs/plugin-hmr'
config:
root: ['.']
2026-07-14 21:57:52 +08:00
# The native DeepSeek adapter.
refactor(examples): extract the app spine into dsh-agent-core + app packages Implements docs/rfc/.../2026-06-20-extract-example-app-packages.md. Each example was thick — a hand-rolled start.ts, an infra preamble, nested base.yml/base-core.yml/acp-tail.yml includes, and a coupled front-door cluster enforced only by prose. This moves the composition into packages so each example is a thin leaf cordis.yml: pick the swappable backends, load one app package. New packages: - @deepseek-ai/dsh-agent-core (packages/core/agent-core): one bundle plugin that loads the providerless/executor-less/UI-less spine (timer + llm + sessions + system-prompt + tools + agents + invariants + tool-bash + agent-loop) via ctx.plugin(...) inside apply(), and forwards agent-loop's `agents` list as its own Config (export const Config = AgentLoop.Config, default []). - @deepseek-ai/dsh-stdio-agent (packages/ui/stdio-agent): terminal chat APP — agent-core + console logger + readline UI + a pre-created `main` agent, with a bin. The demo:echo/coding front door. - @deepseek-ai/dsh-acp-agent (packages/ui/acp-agent): ACP server APP — agent-core + JSONL persistence + the acp bridge, NO stdout logger, with a bin. The stdout-purity footgun is structurally unreachable from the leaf. Amendment to the RFC: hmr stays a LEAF cordis.yml entry, not baked into dsh-stdio-agent. hmr is a Loader-only dev plugin (throws without --expose-internals; the in-process test tier can't even import its decorator form), so a package statically importing it could never carry the per-file coverage gate. Unlike the console logger, a stray hmr is not a stdout-purity footgun, so leaving it at the leaf costs no safety. With hmr out, all three new packages carry in-process unit specs at 100%. Boot glue (Loader tail, .env load, snapshot-mode selection, stdin-dispose lifecycle) moves into each app's bin; start.ts and base.yml/base-core.yml/ acp-tail.yml are deleted. Each app package gets a keyless real-load-path test that boots through its bin + the cordis Loader (guarding the unwrapExports export-shape bug class, postmortem 0001). ACP snapshot replay stays green against the existing committed goldens (pure boot restructuring). RFC moved proposed->implemented with the amendment recorded; package/example/architecture docs and the module graph updated.
2026-06-21 12:03:44 +08:00
- id: llm-deepseek
name: '@deepseek-ai/dsh-llm-deepseek'
config:
refactor(examples): extract the app spine into dsh-agent-core + app packages Implements docs/rfc/.../2026-06-20-extract-example-app-packages.md. Each example was thick — a hand-rolled start.ts, an infra preamble, nested base.yml/base-core.yml/acp-tail.yml includes, and a coupled front-door cluster enforced only by prose. This moves the composition into packages so each example is a thin leaf cordis.yml: pick the swappable backends, load one app package. New packages: - @deepseek-ai/dsh-agent-core (packages/core/agent-core): one bundle plugin that loads the providerless/executor-less/UI-less spine (timer + llm + sessions + system-prompt + tools + agents + invariants + tool-bash + agent-loop) via ctx.plugin(...) inside apply(), and forwards agent-loop's `agents` list as its own Config (export const Config = AgentLoop.Config, default []). - @deepseek-ai/dsh-stdio-agent (packages/ui/stdio-agent): terminal chat APP — agent-core + console logger + readline UI + a pre-created `main` agent, with a bin. The demo:echo/coding front door. - @deepseek-ai/dsh-acp-agent (packages/ui/acp-agent): ACP server APP — agent-core + JSONL persistence + the acp bridge, NO stdout logger, with a bin. The stdout-purity footgun is structurally unreachable from the leaf. Amendment to the RFC: hmr stays a LEAF cordis.yml entry, not baked into dsh-stdio-agent. hmr is a Loader-only dev plugin (throws without --expose-internals; the in-process test tier can't even import its decorator form), so a package statically importing it could never carry the per-file coverage gate. Unlike the console logger, a stray hmr is not a stdout-purity footgun, so leaving it at the leaf costs no safety. With hmr out, all three new packages carry in-process unit specs at 100%. Boot glue (Loader tail, .env load, snapshot-mode selection, stdin-dispose lifecycle) moves into each app's bin; start.ts and base.yml/base-core.yml/ acp-tail.yml are deleted. Each app package gets a keyless real-load-path test that boots through its bin + the cordis Loader (guarding the unwrapExports export-shape bug class, postmortem 0001). ACP snapshot replay stays green against the existing committed goldens (pure boot restructuring). RFC moved proposed->implemented with the amendment recorded; package/example/architecture docs and the module graph updated.
2026-06-21 12:03:44 +08:00
apiKey: !!js process.env.DEEPSEEK_API_KEY
baseURL: !!js process.env.DEEPSEEK_BASE_URL
# Local executor for the app bundle's bash tool.
refactor(examples): extract the app spine into dsh-agent-core + app packages Implements docs/rfc/.../2026-06-20-extract-example-app-packages.md. Each example was thick — a hand-rolled start.ts, an infra preamble, nested base.yml/base-core.yml/acp-tail.yml includes, and a coupled front-door cluster enforced only by prose. This moves the composition into packages so each example is a thin leaf cordis.yml: pick the swappable backends, load one app package. New packages: - @deepseek-ai/dsh-agent-core (packages/core/agent-core): one bundle plugin that loads the providerless/executor-less/UI-less spine (timer + llm + sessions + system-prompt + tools + agents + invariants + tool-bash + agent-loop) via ctx.plugin(...) inside apply(), and forwards agent-loop's `agents` list as its own Config (export const Config = AgentLoop.Config, default []). - @deepseek-ai/dsh-stdio-agent (packages/ui/stdio-agent): terminal chat APP — agent-core + console logger + readline UI + a pre-created `main` agent, with a bin. The demo:echo/coding front door. - @deepseek-ai/dsh-acp-agent (packages/ui/acp-agent): ACP server APP — agent-core + JSONL persistence + the acp bridge, NO stdout logger, with a bin. The stdout-purity footgun is structurally unreachable from the leaf. Amendment to the RFC: hmr stays a LEAF cordis.yml entry, not baked into dsh-stdio-agent. hmr is a Loader-only dev plugin (throws without --expose-internals; the in-process test tier can't even import its decorator form), so a package statically importing it could never carry the per-file coverage gate. Unlike the console logger, a stray hmr is not a stdout-purity footgun, so leaving it at the leaf costs no safety. With hmr out, all three new packages carry in-process unit specs at 100%. Boot glue (Loader tail, .env load, snapshot-mode selection, stdin-dispose lifecycle) moves into each app's bin; start.ts and base.yml/base-core.yml/ acp-tail.yml are deleted. Each app package gets a keyless real-load-path test that boots through its bin + the cordis Loader (guarding the unwrapExports export-shape bug class, postmortem 0001). ACP snapshot replay stays green against the existing committed goldens (pure boot restructuring). RFC moved proposed->implemented with the amendment recorded; package/example/architecture docs and the module graph updated.
2026-06-21 12:03:44 +08:00
- id: bash
name: '@deepseek-ai/dsh-bash-local'
config:
refactor(examples): extract the app spine into dsh-agent-core + app packages Implements docs/rfc/.../2026-06-20-extract-example-app-packages.md. Each example was thick — a hand-rolled start.ts, an infra preamble, nested base.yml/base-core.yml/acp-tail.yml includes, and a coupled front-door cluster enforced only by prose. This moves the composition into packages so each example is a thin leaf cordis.yml: pick the swappable backends, load one app package. New packages: - @deepseek-ai/dsh-agent-core (packages/core/agent-core): one bundle plugin that loads the providerless/executor-less/UI-less spine (timer + llm + sessions + system-prompt + tools + agents + invariants + tool-bash + agent-loop) via ctx.plugin(...) inside apply(), and forwards agent-loop's `agents` list as its own Config (export const Config = AgentLoop.Config, default []). - @deepseek-ai/dsh-stdio-agent (packages/ui/stdio-agent): terminal chat APP — agent-core + console logger + readline UI + a pre-created `main` agent, with a bin. The demo:echo/coding front door. - @deepseek-ai/dsh-acp-agent (packages/ui/acp-agent): ACP server APP — agent-core + JSONL persistence + the acp bridge, NO stdout logger, with a bin. The stdout-purity footgun is structurally unreachable from the leaf. Amendment to the RFC: hmr stays a LEAF cordis.yml entry, not baked into dsh-stdio-agent. hmr is a Loader-only dev plugin (throws without --expose-internals; the in-process test tier can't even import its decorator form), so a package statically importing it could never carry the per-file coverage gate. Unlike the console logger, a stray hmr is not a stdout-purity footgun, so leaving it at the leaf costs no safety. With hmr out, all three new packages carry in-process unit specs at 100%. Boot glue (Loader tail, .env load, snapshot-mode selection, stdin-dispose lifecycle) moves into each app's bin; start.ts and base.yml/base-core.yml/ acp-tail.yml are deleted. Each app package gets a keyless real-load-path test that boots through its bin + the cordis Loader (guarding the unwrapExports export-shape bug class, postmortem 0001). ACP snapshot replay stays green against the existing committed goldens (pure boot restructuring). RFC moved proposed->implemented with the amendment recorded; package/example/architecture docs and the module graph updated.
2026-06-21 12:03:44 +08:00
timeoutMs: 60000
# The app bundle pre-creates the REPL's `main` agent.
refactor(examples): extract the app spine into dsh-agent-core + app packages Implements docs/rfc/.../2026-06-20-extract-example-app-packages.md. Each example was thick — a hand-rolled start.ts, an infra preamble, nested base.yml/base-core.yml/acp-tail.yml includes, and a coupled front-door cluster enforced only by prose. This moves the composition into packages so each example is a thin leaf cordis.yml: pick the swappable backends, load one app package. New packages: - @deepseek-ai/dsh-agent-core (packages/core/agent-core): one bundle plugin that loads the providerless/executor-less/UI-less spine (timer + llm + sessions + system-prompt + tools + agents + invariants + tool-bash + agent-loop) via ctx.plugin(...) inside apply(), and forwards agent-loop's `agents` list as its own Config (export const Config = AgentLoop.Config, default []). - @deepseek-ai/dsh-stdio-agent (packages/ui/stdio-agent): terminal chat APP — agent-core + console logger + readline UI + a pre-created `main` agent, with a bin. The demo:echo/coding front door. - @deepseek-ai/dsh-acp-agent (packages/ui/acp-agent): ACP server APP — agent-core + JSONL persistence + the acp bridge, NO stdout logger, with a bin. The stdout-purity footgun is structurally unreachable from the leaf. Amendment to the RFC: hmr stays a LEAF cordis.yml entry, not baked into dsh-stdio-agent. hmr is a Loader-only dev plugin (throws without --expose-internals; the in-process test tier can't even import its decorator form), so a package statically importing it could never carry the per-file coverage gate. Unlike the console logger, a stray hmr is not a stdout-purity footgun, so leaving it at the leaf costs no safety. With hmr out, all three new packages carry in-process unit specs at 100%. Boot glue (Loader tail, .env load, snapshot-mode selection, stdin-dispose lifecycle) moves into each app's bin; start.ts and base.yml/base-core.yml/ acp-tail.yml are deleted. Each app package gets a keyless real-load-path test that boots through its bin + the cordis Loader (guarding the unwrapExports export-shape bug class, postmortem 0001). ACP snapshot replay stays green against the existing committed goldens (pure boot restructuring). RFC moved proposed->implemented with the amendment recorded; package/example/architecture docs and the module graph updated.
2026-06-21 12:03:44 +08:00
- id: stdio-agent
name: '@deepseek-ai/dsh-stdio-demo'
refactor(examples): extract reusable logic into tested packages Logic that lived under examples/ was outside the per-file 100% coverage gate (examples/ are not workspaces) and, in the stdio-UI case, duplicated across two examples. Move it into packages/ so it is gated and de-duped. - packages/ui-stdio (new): unify the two diverged stdio-chat.ts copies into one @deepseek-ai/dsh-ui-stdio plugin (welcome/agent Config). A test-only I/O seam (createStdioChat(ctx, config, runtime)) keeps process streams out of the serializable config and makes every render/EOF/disposal branch unit-testable. Per-file 100%. echo/coding cordis.yml now load the package; both src/stdio-chat.ts deleted. - packages/llm-replay (new): move examples/acp-agent/src/llm-replay.ts (+ its spec) here so its derive/parse/replay branches fall under the coverage gate. cordis.snapshot.yml + README rewired to the package name; added apply/env /assertNever/abort tests to reach per-file 100%. - examples/{echo,coding}-agent: keyless Loader-path e2e smokes that boot the real cordis.yml (no key) — the guard a hand-mounted unit test cannot be for the unwrapExports/export-shape class (postmortem 0001). examples/AGENTS.md codifies the keyless+with-key smoke convention (keyless-by-nature exception for echo-agent). - AGENTS.md: a scoped, removal-triggered pre-release stance (foundation over blast radius). packages/README.md: new rows + a FIXME to later regroup ALL packages into a hierarchy. Wiring: tsconfig paths/refs, publint, knip, module-graph. Verified: typecheck, lint, test:coverage (887 tests, 100%), build, hygiene, doc-sync, test:snapshot (10), test:e2e (6 keyless pass, with-key self-skip).
2026-06-19 12:42:28 +08:00
config:
2026-07-14 21:57:52 +08:00
provider: deepseek
refactor(examples): extract the app spine into dsh-agent-core + app packages Implements docs/rfc/.../2026-06-20-extract-example-app-packages.md. Each example was thick — a hand-rolled start.ts, an infra preamble, nested base.yml/base-core.yml/acp-tail.yml includes, and a coupled front-door cluster enforced only by prose. This moves the composition into packages so each example is a thin leaf cordis.yml: pick the swappable backends, load one app package. New packages: - @deepseek-ai/dsh-agent-core (packages/core/agent-core): one bundle plugin that loads the providerless/executor-less/UI-less spine (timer + llm + sessions + system-prompt + tools + agents + invariants + tool-bash + agent-loop) via ctx.plugin(...) inside apply(), and forwards agent-loop's `agents` list as its own Config (export const Config = AgentLoop.Config, default []). - @deepseek-ai/dsh-stdio-agent (packages/ui/stdio-agent): terminal chat APP — agent-core + console logger + readline UI + a pre-created `main` agent, with a bin. The demo:echo/coding front door. - @deepseek-ai/dsh-acp-agent (packages/ui/acp-agent): ACP server APP — agent-core + JSONL persistence + the acp bridge, NO stdout logger, with a bin. The stdout-purity footgun is structurally unreachable from the leaf. Amendment to the RFC: hmr stays a LEAF cordis.yml entry, not baked into dsh-stdio-agent. hmr is a Loader-only dev plugin (throws without --expose-internals; the in-process test tier can't even import its decorator form), so a package statically importing it could never carry the per-file coverage gate. Unlike the console logger, a stray hmr is not a stdout-purity footgun, so leaving it at the leaf costs no safety. With hmr out, all three new packages carry in-process unit specs at 100%. Boot glue (Loader tail, .env load, snapshot-mode selection, stdin-dispose lifecycle) moves into each app's bin; start.ts and base.yml/base-core.yml/ acp-tail.yml are deleted. Each app package gets a keyless real-load-path test that boots through its bin + the cordis Loader (guarding the unwrapExports export-shape bug class, postmortem 0001). ACP snapshot replay stays green against the existing committed goldens (pure boot restructuring). RFC moved proposed->implemented with the amendment recorded; package/example/architecture docs and the module graph updated.
2026-06-21 12:03:44 +08:00
model: deepseek-v4-flash
# Set RESUME_SESSION_ID to continue a prior persisted session (the ids live
# under ./.sessions); unset starts a fresh session each run.
resumeSessionId: !!js process.env.RESUME_SESSION_ID
persistenceRoot: './.sessions'
workspaceContext:
maxBytes: 65536
welcome: 'agent REPL ready. Give it a coding task.'
ui:
mode: readline
# Keep the persona to identity and behavior; tool plugins own tool guidance.
# The loop resolves {{model}} from this agent's configuration.
persona: |
You are coding-agent, a coding assistant powered by the {{model}} model.
refactor(examples): extract the app spine into dsh-agent-core + app packages Implements docs/rfc/.../2026-06-20-extract-example-app-packages.md. Each example was thick — a hand-rolled start.ts, an infra preamble, nested base.yml/base-core.yml/acp-tail.yml includes, and a coupled front-door cluster enforced only by prose. This moves the composition into packages so each example is a thin leaf cordis.yml: pick the swappable backends, load one app package. New packages: - @deepseek-ai/dsh-agent-core (packages/core/agent-core): one bundle plugin that loads the providerless/executor-less/UI-less spine (timer + llm + sessions + system-prompt + tools + agents + invariants + tool-bash + agent-loop) via ctx.plugin(...) inside apply(), and forwards agent-loop's `agents` list as its own Config (export const Config = AgentLoop.Config, default []). - @deepseek-ai/dsh-stdio-agent (packages/ui/stdio-agent): terminal chat APP — agent-core + console logger + readline UI + a pre-created `main` agent, with a bin. The demo:echo/coding front door. - @deepseek-ai/dsh-acp-agent (packages/ui/acp-agent): ACP server APP — agent-core + JSONL persistence + the acp bridge, NO stdout logger, with a bin. The stdout-purity footgun is structurally unreachable from the leaf. Amendment to the RFC: hmr stays a LEAF cordis.yml entry, not baked into dsh-stdio-agent. hmr is a Loader-only dev plugin (throws without --expose-internals; the in-process test tier can't even import its decorator form), so a package statically importing it could never carry the per-file coverage gate. Unlike the console logger, a stray hmr is not a stdout-purity footgun, so leaving it at the leaf costs no safety. With hmr out, all three new packages carry in-process unit specs at 100%. Boot glue (Loader tail, .env load, snapshot-mode selection, stdin-dispose lifecycle) moves into each app's bin; start.ts and base.yml/base-core.yml/ acp-tail.yml are deleted. Each app package gets a keyless real-load-path test that boots through its bin + the cordis Loader (guarding the unwrapExports export-shape bug class, postmortem 0001). ACP snapshot replay stays green against the existing committed goldens (pure boot restructuring). RFC moved proposed->implemented with the amendment recorded; package/example/architecture docs and the module graph updated.
2026-06-21 12:03:44 +08:00
Verify your work by running the code or tests. Keep answers brief and
factual.
# Replay-aware request pressure with one service-wide context window.
- id: token-meter
name: '@deepseek-ai/dsh-token-meter'
# Summarize an older range when measured history approaches the context window.
# Service-wide policy provides the ordinary threshold and retained-tail defaults.
refactor(compact): turn-agnostic retention + dedicated agent/pre-request seam Reform the compaction blueprint so a runaway turn survives and the design stops drifting across review rounds: - Drop in-flight-turn protection ("layer 2"). Retention is a uniform tail→head whole-unit walk; the only structural guard is step-alignment. A single turn that alone exceeds the window now compacts its own early closed steps instead of being retained verbatim (the failure mode that motivated this). - Move auto-compaction off the agent/request waterfall onto a new awaited agent/pre-request loop seam, fired before history derivation. Compaction mutates the surface; the loop derives once from the result — no double-derive, and a listener structurally cannot act on not-yet-derived messages. - Tighten compactIfNeeded to required (session, system, model, signal). - Enforce a single-pass convergence invariant in resolveConfig: reject configs where summarizationMaxTokens + retainTokens exceeds the threshold, so a compaction can never immediately re-trigger. - Document the crash vs recoverable failure taxonomy; core session repair stays compaction-agnostic (a log-only orphaned compact/start is inert). - Wire dsh-compact-basic into examples/coding-agent and add a with-key compaction e2e (compaction's first real-world exercise + runaway net). - Rewrite the RFC to encode the blueprint and move it to implemented/. The runaway-turn snapshot is a named deferred follow-up: dsh-llm-replay cannot yet serve the interleaved summarization model call.
2026-06-26 08:59:33 +08:00
- id: compact-basic
name: '@deepseek-ai/dsh-compact-basic'
# Expose fresh-child `spawn` and completed-prefix `fork` through independent
# in-process backends. Each tool instance needs a distinct `toolName`; the registry
# rejects duplicates. These leaves follow the app because it provides `ctx.agents` and `ctx.tools`.
Add in-process subagent backends: spawn (fresh) and fork (seeded) The second PR of the subagent seam: the two in-process backends that run a child agent on the same cordis context, reusing the agent factory's quiescent AgentHandle teardown. Both register on ctx.subagents (PR1's named-provider registry) and share one run driver. - dsh-subagent-spawn: a FRESH child via ctx.agents.create — own session, the parent's model by default (overridable), zero inherited conversation. Also exports the shared in-process run driver (startInProcessRun): mint ids, stamp cwd/parentSession-lineage/depth, drive the one-shot (send → whenIdle), read the last assistant/message + turn/end reason, dispose to quiescence. - dsh-subagent-fork: a child SEEDED with the parent's balanced completed-turn prefix (the log up to and including its last turn/end), so the child inherits context. The in-flight unbalanced turn is excluded — a raw seed would fail the invariants replay. Proven: a regression test goes red if the boundary seeds the open turn. - Seam extension: CreateAgentOptions.seed, threaded through AgentLoop.createAgent → ctx.sessions.prepare({ seed }) (the primitive resume already used). This is the fork-lineage path the TODO(sub-agents) markers anticipated. - Depth: a merge-extensible AgentOptions.subagentDepth (0 top-level, parent+1 for a child); the depthLimit capability refuses a spawn past request.maxDepth. Tests: real-loop unit tests for both backends (mock MODEL only, real loop + invariants), a multi-subagent test (one parent drives a fork AND a spawn child then keeps working), and a with-key e2e (a real parent delegates via the `subagent` tool to a real child that writes a file on disk — world-verified). 100% per-file coverage. The coding-agent demo wires the spawn backend + tool. Snapshot coverage of nested agents is deferred to a stacked follow-up (TODO(subagent-snapshots)): dsh-llm-replay is a single global positional cursor that cannot route calls to a parent vs. a child on one context. Recorded in the RFC's deferrals and a new AGENTS.md rule: designing a subsystem must design its test infrastructure END TO END up front, verifying the snapshot/e2e harness can express the new shape — a gap this plan hit.
2026-06-22 05:58:40 +08:00
- id: subagent
name: '@deepseek-ai/dsh-subagent'
- id: subagent-spawn
name: '@deepseek-ai/dsh-subagent-spawn'
config:
providerName: spawn
- id: subagent-fork
name: '@deepseek-ai/dsh-subagent-fork'
config:
providerName: fork
Add in-process subagent backends: spawn (fresh) and fork (seeded) The second PR of the subagent seam: the two in-process backends that run a child agent on the same cordis context, reusing the agent factory's quiescent AgentHandle teardown. Both register on ctx.subagents (PR1's named-provider registry) and share one run driver. - dsh-subagent-spawn: a FRESH child via ctx.agents.create — own session, the parent's model by default (overridable), zero inherited conversation. Also exports the shared in-process run driver (startInProcessRun): mint ids, stamp cwd/parentSession-lineage/depth, drive the one-shot (send → whenIdle), read the last assistant/message + turn/end reason, dispose to quiescence. - dsh-subagent-fork: a child SEEDED with the parent's balanced completed-turn prefix (the log up to and including its last turn/end), so the child inherits context. The in-flight unbalanced turn is excluded — a raw seed would fail the invariants replay. Proven: a regression test goes red if the boundary seeds the open turn. - Seam extension: CreateAgentOptions.seed, threaded through AgentLoop.createAgent → ctx.sessions.prepare({ seed }) (the primitive resume already used). This is the fork-lineage path the TODO(sub-agents) markers anticipated. - Depth: a merge-extensible AgentOptions.subagentDepth (0 top-level, parent+1 for a child); the depthLimit capability refuses a spawn past request.maxDepth. Tests: real-loop unit tests for both backends (mock MODEL only, real loop + invariants), a multi-subagent test (one parent drives a fork AND a spawn child then keeps working), and a with-key e2e (a real parent delegates via the `subagent` tool to a real child that writes a file on disk — world-verified). 100% per-file coverage. The coding-agent demo wires the spawn backend + tool. Snapshot coverage of nested agents is deferred to a stacked follow-up (TODO(subagent-snapshots)): dsh-llm-replay is a single global positional cursor that cannot route calls to a parent vs. a child on one context. Recorded in the RFC's deferrals and a new AGENTS.md rule: designing a subsystem must design its test infrastructure END TO END up front, verifying the snapshot/e2e harness can express the new shape — a gap this plan hit.
2026-06-22 05:58:40 +08:00
- id: tool-subagent
name: '@deepseek-ai/dsh-tool-subagent'
config:
provider: spawn
toolName: subagent
- id: tool-subagent-fork
name: '@deepseek-ai/dsh-tool-subagent'
config:
provider: fork
toolName: subagent_fork
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
# The worker-thread workflow engine fans a model-written JavaScript script's
# `agent()` calls out through the spawn backend; the adjacent tool exposes it to the model.
- id: workflow-workerthread
name: '@deepseek-ai/dsh-workflow-workerthread'
workflow: dynamic workflows — script-driven multi-agent orchestration A new capability family at packages/workflow/ in the bash seam shape, modeled on Claude Code's dynamic workflows: the model writes a JavaScript orchestration script (export const meta = {...} + plain-JS body), a runtime executes it, and the script — not the conversation — holds the loop, the branching, and the intermediate results. - dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary (WorkflowRun whose result NEVER rejects) + observe-only workflow/* events carrying data snapshots (id + meta, never the live run), per-listener contained like subagent/*. - dsh-workflow-vm: in-process node:vm engine. Meta extraction via a string/comment-aware scanner (template interpolation rejected; literal evaluated alone in an empty timed context; statement blanked line- preservingly so stacks keep script line numbers). Hooks: agent(prompt, {label, phase, schema, model}) over ctx.subagents, parallel(), pipeline() (no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline: hook misuse (unknown/deferred options, bad arguments, unsupported schemas, tripped caps, seam start failures, cancellation) throws fatal WorkflowErrors the combinators RE-THROW — never dissolved into the per-item null reserved for child failures. Realm boundary: inbound values materialized by descriptor walks that never invoke accessors (defineProperty copies, __proto__-safe); outbound values rebuilt in-realm via the context's own JSON.parse. Determinism bans (Date.now/Math.random/argless new Date) kept so future resume support cannot break scripts. Caps and timeouts are validated Config. Every hook promise carries a no-op rejection consumer (app-boot exits on unhandled rejections). - dsh-tool-workflow: the model-facing workflow tool, synchronous like dsh-tool-subagent (start → await → try/finally dispose; abort bridged; non-completed → isError). Generic render card titled by a textual meta.name sniff. The tool description carries the authoring contract. Wired into examples/{coding-agent,acp-agent} with explicit-ask-only guidance. Coverage at every tier: unit (meta scanner, materializer incl. counting-getter and __proto__ regressions, combinator semantics, concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon), integration over the real spawn stack, with-key e2e (real two-phase run + the tool through the registry pipeline), and a recorded ACP snapshot scenario (workflow-run, 1 child session). RFC: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's layout line.
2026-07-05 13:29:35 +08:00
config:
provider: spawn
- id: tool-workflow
name: '@deepseek-ai/dsh-tool-workflow'
# `todo_write` replaces the logged whole list and renders as a stdio checklist or ACP plan.
- id: tool-todo
name: '@deepseek-ai/dsh-tool-todo'
# Policy loads before the model-facing filesystem tools so writes and edits require
# an observed file. This single-session app resolves relative paths from the process cwd.
- id: fs-local
name: '@deepseek-ai/dsh-fs-local'
config:
cwd: !!js process.cwd()
- id: fs-policy
name: '@deepseek-ai/dsh-fs-policy'
- id: tool-fs
name: '@deepseek-ai/dsh-tool-fs'
# Bash-backed discovery tools (glob/grep): fixed ripgrep commands through the
# local bash executor above — not ctx.fs. Capped results save the complete
# formatted list through the spill backend below (ctx.spillStore, optional).
- id: tool-fs-search
name: '@deepseek-ai/dsh-tool-fs-search'
# The tool-call timeout enforcer: arms each declared ToolDefinition.timeoutMs
# (the search tools above declare 30s) as a deadline on exec.signal. Without
# it a declared budget is advisory and only the bash executor's own timeout
# backstop applies.
- id: timeout-policy
name: '@deepseek-ai/dsh-timeout-policy'
# Tool-output spill stack: a local backend that saves oversized tool text under
# a private session-scoped dir, and the tools/post-execute policy that replaces
# an over-budget plain-text result with a preview + the spill locator/retrieval
# hint. A leaf pair after the app (needs ctx.tools). The policy is a no-op until
# a tool returns more than maxInlineBytes of plain text.
- id: spill-local
name: '@deepseek-ai/dsh-spill-local'
- id: spill-policy
name: '@deepseek-ai/dsh-spill-policy'
config:
maxInlineBytes: 50000