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.

docs/cordis-catalog/events-and-services.md

@@ -332,7 +332,7 @@ list(): Agent[]
 
 Types: [Agent](../core-data-structures/core.md)
 
-Source: [`packages/core/agent/src/index.ts:105`](../../packages/core/agent/src/index.ts)
+Source: [`packages/core/agent/src/index.ts:116`](../../packages/core/agent/src/index.ts)
 
 ### `ctx.bash` — `BashExecutor` (abstract seam)
 

docs/core-data-structures/subagent.md

@@ -86,3 +86,10 @@ interface SubagentProvider {
 ```
 
 The service (`ctx.subagents`) emits `subagent/start` when a run begins and `subagent/end` when it settles (see the [events catalog](../cordis-catalog/events-and-services.md)). Both emits contain a thrown listener **per listener** (logged, never propagated): one bad subscriber can neither strand a live run, surface as an unhandled rejection on the detached settle hook, nor starve the listeners registered after it.
+
+## In-process backends: depth and seed
+
+The two in-process backends ([dsh-subagent-spawn](../../packages/subagent/subagent-spawn) fresh, [dsh-subagent-fork](../../packages/subagent/subagent-fork) seeded) run the child as a child `Agent` on the same context via `ctx.agents.create`. Two pieces of vocabulary ride on the existing agent/session types rather than new core types:
+
+- **Delegation depth** is a merge-extensible `AgentOptions.subagentDepth` field (`0` for a top-level agent, parent + 1 for a child). The seam owns it — the loop neither sets nor reads it — so a nested spawn reads its parent's depth from `parent.options.subagentDepth` and the `depthLimit` capability caps the tree by refusing a child whose depth would exceed `request.maxDepth`.
+- **Fork seeding** uses `CreateAgentOptions.seed` (a `SessionEvent[]` prefix threaded through `AgentLoop.createAgent` → `ctx.sessions.prepare({ seed })`, the same primitive `resume` uses). The fork backend passes a *balanced completed-turn prefix* of the parent's log — the parent's events up to and including its last `turn/end` — so the seed is contiguous-from-0 and the [invariants](../../packages/support/invariants) replay accepts it (the in-flight, unbalanced turn is excluded).

docs/module-graph.md

@@ -63,6 +63,10 @@ graph TD
   subagent-mock --> agent
   subagent-mock --> llm
   subagent-mock --> subagent
+  subagent-spawn --> agent
+  subagent-spawn --> llm
+  subagent-spawn --> session
+  subagent-spawn --> subagent
   tool-subagent --> agent
   tool-subagent --> llm
   tool-subagent --> subagent
@@ -75,6 +79,10 @@ graph TD
   stdio-agent --> session
   stdio-agent --> session-persistence-jsonl
   stdio-agent --> ui-stdio
+  subagent-fork --> agent
+  subagent-fork --> session
+  subagent-fork --> subagent
+  subagent-fork --> subagent-spawn
 ```
 
 | Package | Depends on |
@@ -101,6 +109,8 @@ graph TD
 | `tool-bash` | `agent`, `bash`, `llm`, `tools` |
 | `agent-core` | `agent`, `agent-loop`, `invariants`, `llm`, `session`, `system-prompt`, `tool-bash`, `tools` |
 | `subagent-mock` | `agent`, `llm`, `subagent` |
+| `subagent-spawn` | `agent`, `llm`, `session`, `subagent` |
 | `tool-subagent` | `agent`, `llm`, `subagent`, `tools` |
 | `acp-agent` | `acp`, `agent-core`, `session-persistence-jsonl` |
 | `stdio-agent` | `agent`, `agent-core`, `session`, `session-persistence-jsonl`, `ui-stdio` |
+| `subagent-fork` | `agent`, `session`, `subagent`, `subagent-spawn` |

docs/rfc/proposed/feature/2026-06-21-subagent-capability-seam.md

@@ -70,3 +70,4 @@ The `dsh-tool-subagent` consumer awaits `run.result` and returns the child's fin
 - **Blocking the parent turn.** Synchronous collect holds the parent's `runStep` open for the child's full duration. This is acceptable for the first cut; **background / poll / spill semantics are deferred to a future redesign that unifies long-running-tool handling across subagents AND bash** (a sub-agent and a long `bash` background task pose the same "the model started something slow, how does it collect later" problem, and should share one mechanism rather than each inventing its own).
 - **Live progress.** This cut surfaces only lifecycle + final result; a per-chunk child→parent update stream is deferred with the background redesign.
 - **ACP client surface.** Proxying `fs`/`terminal` from the ACP child back to the parent (a shared-workspace mode) is future work; the first cut advertises neither, so the child self-serves in its own process.
+- **Snapshot coverage of nested agents.** The snapshot tier (`pnpm run test:snapshot`) replays a recorded session through `dsh-llm-replay`, whose dispatch is a single GLOBAL positional cursor (the Nth `llm/stream` call serves the Nth recorded entry) and whose harness harvests a single session log file. A subagent runs as a *second* agent with its own session log, so a parent→child scenario needs per-session-keyed replay (or a call-ordered merge of both logs, sound because subagent execution is strictly nested/non-concurrent — the parent blocks on the child) plus harvest-all-logs and plural-session-id plumbing in the harness. This is self-contained infrastructure orthogonal to the backends, so it lands as a **dedicated stacked follow-up** rather than in the in-process-backends PR. Until it lands, in-process subagents are covered by real-loop unit tests (a parent driving a fork AND a spawn child) and a with-key e2e (a parent delegating to a child that writes a file), not by the snapshot transcript tier. Tracked by `TODO(subagent-snapshots)`.