rig expand payload that needs to start a new managed seat from a prior runtime conversation source — session_source: { mode: fork, ref: { kind, value } }. v1 supports mode: fork with ref.kind: native_id for Claude and Codex. The new seat persists a NEW post-fork token; the parent token is NEVER written onto the new seat. NOT for restoring an existing seat or for artifact-backed mental-model rebuild.\nmetadata:\nopenrig:\nstage: factory-approved\nsibling_skills:\n- claude-compaction-restore\n- mental-model-ha\n- scope-recovery\n- session-compaction-and-restore\n- agent-startup-and-context-ingestion\n- agent-starters\n- composable-priming-packs\n- seat-continuity-and-handover\n- claude-compact-in-place\n- pre-maintenance-agent-preservationsession_source is a member-level OpenRig field that declares how a\nnewly-launched managed seat should derive its initial conversation\ncontinuity from a prior runtime conversation source.
v1 supports one mode: fork — start a new managed seat from a\nprior native runtime conversation source without claiming the original\nseat continued.
The schema is runtime-neutral; implementation is runtime-specific (Claude\nand Codex have their own native fork commands).
\nrig expand payload with session_sourcefork vs rebuild vs resume vs fresh for a new seatseat-continuity-and-handover skillmode: rebuild (see seat-continuity-and-handover for the rebuild surface) — do NOT collapse fork into artifact-backed reentry; the distinction is load-bearing.terminal. Terminal runtime rejects session_source.members:\n - id: reviewer-2\n runtime: claude-code # or \"codex\"; not valid on terminal\n agent_ref: specs/agents/reviewer.yaml\n profile: reviewer\n cwd: .\n session_source:\n mode: fork\n ref:\n kind: native_id # v1 fork mode supports native_id only\n value: \"0b0165d7-cb4d-4650-90de-15c0a1ede9e6\"\nRules:
\nmode v1 only valid value: fork.ref.kind v1 supports native_id only. Schema rejects artifact_path, name, last, and artifact_set pre-launch with explicit deferred/weaker/wrong-mode error messages (see packages/daemon/src/domain/rigspec-schema.ts validateSessionSourceFork). Adapter-level refusal exists as defensive handling but should not be reachable in v1 because schema rejects first.value required for ref.kind: native_id in v1 (the only schema-accepted kind). Future-state value semantics for artifact_path / name / last are not active in v1 because schema rejects those kinds pre-launch.rig expand accepts the same shape so dynamically-added members can carry session-source attribution.The primitive does NOT introduce a new top-level command. It flows\nthrough existing rig spec and expansion pathways.
\nsession_source is a launch-time input, not a long-lived stateful field:
ref against the runtimeOnce realized, session_source is essentially history. Restoring the\nseat later is restore of the new seat, not re-fork-from-parent.
native_id. Action: emit error naming runtime + missing id; do NOT silently launch fresh. (Future-state note: when artifact_path is supported in a follow-up slice, it could become a candidate fallback for Claude; in v1 schema rejects artifact_path pre-launch so no fallback path exists.)ref.kind: artifact_path becomes schema-accepted. v1 schema rejects this kind pre-launch.native_id kinds upfront. Adapter-level refusal exists as defensive handling but is not reached in v1.claude --resume <parent> --fork-session or codex fork <id>) returned non-zero or hung. Preserve runtime stderr; do not record new seat as launched; do not write parent token onto seat.The primitive must NOT report \"restored the original agent\" or \"resumed\nthe original seat\" or \"snapshot.\" The correct framing is \"forked from\nsource session\" / \"started from prior conversation source.\"
\nNegative-grep over adapter source confirms ZERO restored / resumed /\nsnapshot strings in fork code paths.
rig fork <source-session> has since shipped as a thin convenience verb that COMPOSES the existing agent-image fork path — this honors the boundary; it is not a divergent primitive. The rule now reads: no NEW fork mechanics outside the spec / expansion / agent-image pathways.)session_source to AgentSpec. It's a member-level launch-time input.restore semantics. session_source creates a seat; restore continues an existing managed seat.| Runtime | \nCommand shape | \n
|---|---|
Claude (mode: fork + ref.kind: native_id) | \nclaude --resume <parent-id> --fork-session | \n
Codex (mode: fork + ref.kind: native_id) | \ncodex... fork <parent-id> | \n
| Terminal | \nRejected at schema level | \n
Mutual exclusion between resumeToken (restore path) and forkSource\n(fork path) is enforced at three layers in the daemon.
| Outcome | \nWhen | \n
|---|---|
forked | \nFork succeeded; new seat has new native token; parent never written onto new seat | \n
fresh | \nFresh launch (no session_source declared) | \n
resumed | \nRestore of existing managed seat | \n
failed | \nResolution or fork failed | \n
For seat handover over fork composition, the binding outcome is\nindependent (see seat-continuity-and-handover skill).
2026-04-30 live scale-out dogfood found: source checkout contained fork\nsupport, but active daemon was running from a pre-fork commit. Verify\nthe active daemon/runtime commit contains the fork path before live\nproof. Isolated daemon proof at the target commit can prove the\nfeature safely; live forked scale-out remains unproven until the active\ndaemon parity is verified.
\nShipped at openrig c7b6df1 (2026-04-30):
session_source faithfully)rig expand member-inputnative_idresume_token is the NEW post-fork token; parent token NEVER written)continuityOutcome: forked)Deferred:
\nartifact_path mode (schema currently refuses with deferred message)parent_native_id / created_via for queryable RSI consumer)cross-host-rig-commandsseat-continuity-and-handover skill — sibling occupant-creation primitives (resume / fork / rebuild / fresh) + seat-binding (handover composes with fork)agent-starters skill — composes session_source fork into named reusable starting pointscross-host-rig-commands skill — multi-host fork (deferred)