feat(capabilities): add claude-orchestration capability (Workflow backend) (#1143)

Default-off, BETA, claude-only capability adopting Claude Code's Workflow tool
(/effort ultracode, Agent SDK >= v0.3.149) as an optional parallel-execution
backend for the GSD loop. Restores the wave parallelism + plan-checker + verifier
that #853 forces inline on Claude Code, and folds gsd-ultraplan-phase under one
runtime gate.

- Pure fail-closed core (src/claude-orchestration.cts): detectWorkflowBackend
  (gate ladder: enabled -> Claude -> backend != inline -> nested+background host
  -> valid Agent SDK -> SDK >= floor; every miss degrades to inline) and
  emitWorkflowScript (waves -> parallel() barriers, plans -> gsd-executor +
  worktree, files_modified overlap -> separate stages, resumeFromRunId, budget).
  All interpolated identifiers validated script-safe; briefs JSON-quoted.
- claude-orchestration command family (gsd-tools claude-orchestration
  detect-backend|emit-workflow) for orchestrator invocation.
- Two gated loop contributions at wired points (execute:wave:post, plan:post);
  federated config keys (enabled/execution_backend/min_agent_sdk_version).
- ADR-1143 implementation amendment; CONTEXT.md glossary entry; explanation doc.

On any runtime lacking the Workflow tool, behaviour is byte-identical to today.

closes #1143
This commit is contained in:
Tom Boucher
2026-07-06 15:18:23 -04:00
parent d01eec4358
commit e3262d94d3
19 changed files with 2357 additions and 9 deletions

View File

@@ -306,6 +306,8 @@
"capability-writer.cjs",
"check-command-router.cjs",
"cjs-command-router-adapter.cjs",
"claude-orchestration-command-router.cjs",
"claude-orchestration.cjs",
"cli-exit.cjs",
"cli-skew-check.cjs",
"clock.cjs",

View File

@@ -86,3 +86,39 @@ These existing multi-model features (`execute-phase` `cross_ai_delegation`, the
- **Neutral:** no effect on non-Claude runtimes by construction; no behavior change until explicitly enabled.
> **Governance note:** This ADR is a *draft design* accompanying feature request #1143. Per CONTRIBUTING, it is PR'd only after the issue receives `approved-feature`, and the capability is implemented only after #857 is released.
## Amendment (2026-07-06): BETA v1 implementation landed
#857 is **released** (CLOSED); the capability infrastructure is live. The BETA v1
of this capability has shipped as `capabilities/claude-orchestration/` with the
scope agreed in the Decision, refined to the lowest-risk first slice:
- **Detection + emission** live as pure, fail-closed functions in
`gsd-core/bin/lib/claude-orchestration.cjs` (source `src/claude-orchestration.cts`):
`detectWorkflowBackend` (gate ladder: enabled → Claude runtime →
execution_backend ≠ inline → host dispatch nested+background → valid Agent SDK
→ SDK ≥ `claude_orchestration.min_agent_sdk_version`, default `0.3.149`) and
`emitWorkflowScript` (waves → `parallel()` stage barriers, plans →
`agent({ agentType: 'gsd-executor', isolation: 'worktree' })`, `files_modified`
overlap → separate sequential stages, `resumeFromRunId` wired to the phase run
id, shared `budget(tokens)` pool). All interpolated values are validated as
script-safe identifiers or JSON-quoted (review Finding 1).
- **Loop registration** is at the two **wired** points the loop host contract
actually renders: `execute:wave:post into:executor` (Workflow-backend guidance)
and `plan:post into:planner` (ultraplan ownership declaration). `execute:wave:pre`
and `execute:pre` are declared in the contract but **not wired** today, so the
capability registers at `wave:post` (the constraint `external-job` also documents).
- **Config** is federated (`claude_orchestration.enabled` default false /
`activationKey`, `execution_backend` enum `auto|workflow|inline` default `auto`,
`min_agent_sdk_version`); the keys live only in the registry, so uninstall
removes them cleanly.
- **ultraplan ownership** is declared in the manifest (`plan:post` contribution);
full install-profile migration of the `gsd-ultraplan-phase` skill into the
capability's `skills[]` is deferred to a follow-up (it triggers the CLUSTERS /
profile membership gate and is a heavier, install-machinery change).
Status remains **Proposed** — the BETA is default-off and the end-to-end Workflow
execution path (actual orchestration via the Workflow tool inside Claude Code) is
not verifiable outside that runtime. The capability is structurally complete and
tested at the contract level; flipping to Accepted follows maintainer sign-off on
the E2E behaviour once exercised on Claude Code with the Workflow tool present.

View File

@@ -0,0 +1,94 @@
# Claude orchestration capability (BETA)
> **Explanation** — *why this capability exists and how it fits the loop.* For the
> step-by-step, see the [capability reference](../reference/capability-matrix.md);
> for the design record, see [ADR-1143](../adr/1143-claude-orchestration-capability.md).
## The problem
GSD's `execute-phase` is wave-based: plans carry a wave number, waves run
sequentially, and plans *within* a wave run in parallel when their
`files_modified` sets don't overlap. On most runtimes GSD realizes that by
fanning out one backgrounded `gsd-executor` agent (in a worktree) per plan.
On **Claude Code** that fan-out degrades. Backgrounded agents on Claude Code have
no `Agent`/`Task` tool, so they cannot nest subagents ([#853]). The autonomous
loop therefore falls back to **inline sequential execution** — and with it
silently drops wave parallelism, the plan-checker, and the verifier — on the one
runtime most GSD users run.
Claude Code ships an orchestration primitive that sidesteps exactly this: the
**Workflow tool** (the engine behind `/effort ultracode`, Agent SDK ≥ v0.3.149).
A Workflow script *is* the orchestrator — it runs from the main loop and spawns
subagents itself via `agent()`, `parallel()` (barrier), `pipeline()`, and
`phase()`, with `isolation: 'worktree'`, a shared token `budget`, and
`resumeFromRunId`.
## The capability
`claude-orchestration` is a **default-off, BETA, claude-only** capability that
adopts the Workflow tool as an optional, runtime-gated parallel-execution
backend, and folds the existing `gsd-ultraplan-phase` plan-offload under the same
gate. It is blocked-on-nothing now that the ADR-857 capability system is released.
- **`role: feature`**, `runtimeCompat.supported: ["claude"]`, `tier: full`.
- **`activationKey: claude_orchestration.enabled`** — default `false`. Nothing
changes until you opt in.
- Registers at two **wired** loop points: `execute:wave:post` (into the executor)
and `plan:post` (into the planner). Both are `onError: skip` and gated by the
`enabled` key.
## How it decides whether to activate
Detection is a pure, **fail-closed** function — `detectWorkflowBackend`. The
Workflow backend activates only when *every* gate passes; any miss degrades to
`inline` (today's behaviour):
1. `claude_orchestration.enabled` is true.
2. The runtime is Claude (the Workflow tool is Claude / Agent SDK-specific).
3. `claude_orchestration.execution_backend` is `auto` or `workflow` (not `inline`).
4. The host descriptor advertises `dispatch.nested` **and** `dispatch.background`
(the nesting-capable Claude-Code shape — a proxy for Workflow-tool presence,
meaningful only after gate 2).
5. The Agent SDK reports a valid semver version.
6. That version is `>= claude_orchestration.min_agent_sdk_version`
(default `0.3.149`). A pre-release of the floor (e.g. `0.3.149-rc.1`) compares
*below* the GA release per SemVer, so the preview backend stays off.
## What the executor runs when the backend is active
`emitWorkflowScript` maps the phase's wave/plan model onto Workflow primitives:
| GSD concept | Workflow primitive |
|---|---|
| Wave | `parallel()` stage barrier |
| Plan | `agent(brief, { agentType: 'gsd-executor', isolation: 'worktree' })` |
| `files_modified` overlap | forces the plans into separate sequential stages |
| Phase run id | `resumeFromRunId("<id>")` |
| Phase token cap | `budget(<tokens>)` |
Because the emitted script composes the **same** `gsd-executor` agent and
**worktree isolation** the inline path uses, it produces the same `SUMMARY.md`
artifacts and commits — the only difference is the execution vehicle.
## The fallback contract
On any runtime lacking the Workflow tool — or when the capability is disabled,
the SDK is too old, or detection fails for any reason — execute-phase proceeds
with the standard inline wave dispatch. This is a release gate, not a nicety: a
regression test asserts the inline fallback on every non-capable combination, so
the capability is default-off and low-risk by construction.
## BETA scope (v1)
The first slice ships **detection + emission + declarative ultraplan ownership**.
The emitter is exercised at the contract level (structure, overlap splitting,
resume, budget, anti-injection). End-to-end execution through the Workflow tool
is verifiable only inside Claude Code with the tool present. Full install-profile
migration of the `gsd-ultraplan-phase` skill into the capability's `skills[]`
array is a follow-up (it touches the cluster/profile machinery); for v1 the
manifest *declares* ultraplan ownership at `plan:post` and the existing skill's
own runtime gate continues to no-op on non-Claude runtimes.
[#853]: https://github.com/open-gsd/gsd-core/issues/853
[#1143]: https://github.com/open-gsd/gsd-core/issues/1143

View File

@@ -44,7 +44,7 @@ Core package and are stamped with the package version at release (per
ADR-1244 D6). They are not subject to the consent or integrity-pin flow applied
to third-party capabilities.
### Feature capabilities (role: feature) — 18
### Feature capabilities (role: feature) — 19
Feature capabilities extend what the loop does — contributing research,
planning, execution, verification, or ship artefacts at the loop extension
@@ -55,6 +55,7 @@ points.
| `ai-integration` | feature | full | `>=1.6.0` | `plan:pre` | step | first-party |
| `assumption-delta` | feature | full | `>=1.6.0` | `plan:pre` | contribution | first-party |
| `audit` | feature | full | `>=1.6.0` | — | — | first-party |
| `claude-orchestration` | feature | full | `>=1.7.0` | `plan:post`, `execute:wave:post` | contribution | first-party |
| `code-review` | feature | full | `>=1.6.0` | `execute:post` | step | first-party |
| `drift` | feature | full | `>=1.6.0` | `plan:pre`, `execute:wave:post` | gate | first-party |
| `external-job` | feature | full | `>=1.7.0` | `plan:post`, `execute:wave:post` | contribution | first-party |