Propose multi-agent work graph v1

dev/ACTIVE_TASK.json

@@ -1,5 +1,5 @@
 {
-  "task_file": "dev/tasks/DEV-000104-agent-execution-plane-proposal.json",
-  "task_id": "DEV-000104",
+  "task_file": "dev/tasks/DEV-000105-multi-agent-work-graph-proposal.json",
+  "task_id": "DEV-000105",
   "task_revision": 1
 }

dev/tasks/DEV-000105-multi-agent-work-graph-proposal.json

@@ -0,0 +1,23 @@
+{
+  "task_id": "DEV-000105",
+  "task_revision": 1,
+  "architecture_revision": "ADR-0018",
+  "base_repo_revision": "82ee6e5",
+  "risk_tier": "E",
+  "intent": "Prepare the proposed ADR-0021 Multi-Agent Work Graph boundary for review without implementing a scheduler, graph schema, workers or production changes.",
+  "requirement_ids": ["WP-400", "DAG revision and budgets", "Fan-out/fan-in conflict and independent verification"],
+  "allowed_change_scope": {"modules": ["work-graph-governance"], "paths": ["docs/proposals/ADR-0021-multi-agent-work-graph-v1.md", "dev/ACTIVE_TASK.json", "dev/tasks/DEV-000105-multi-agent-work-graph-proposal.json"]},
+  "forbidden_change_scope": {"paths": ["architecture/**", "contracts/**", "database/**", "migrations/**", "modules/**", "cmd/**", "runtime/**", "adapters/**", "deploy/**", ".gitea/**"]},
+  "allowed_architecture_delta": {"new_cross_module_dependencies": 0, "new_canonical_owners": 0, "new_privileges": 0, "new_third_party_dependencies": 0, "new_database_owner_roles": 0},
+  "contracts": {"consume": ["ADR-0017 delegation ownership", "Proposed ADR-0020 Agent Execution Plane", "Proposed ADR-0019 Truth V1 provenance", "Core Work/Capability/Artifact/Continuity ownership"], "may_change": ["Proposed ADR-0021 only; no accepted contract changes"]},
+  "semantic_owner": "work-graph-proposal-only",
+  "canonical_state": [],
+  "state_transitions": ["graph draft -> admitted -> running -> verifying -> completed/partial/failed", "node prerequisite blocked -> ready -> leased/running -> result or recovery", "candidate disagreement -> conflict set -> verified synthesis or unresolved conflict"],
+  "side_effects_and_privileges": ["No runtime side effects, external mutation, connector access, credential access or authority expansion"],
+  "persistence_and_migrations": ["No graph schema, scheduler, queue, lease or migration implementation changes"],
+  "failure_retry_restart": ["Graph revisions are immutable; restart/replay uses durable history; unknown outcomes block unsafe replay"],
+  "assumptions": ["Work remains canonical graph owner", "Roles are capability profiles without authority", "Independent verification is required before Work completion"],
+  "acceptance_scenarios": ["Cycles are rejected before admission", "Budgets cover graph/user/resource concurrency and attempts", "Fan-out/fan-in and partial failure preserve attribution", "Cancellation/pause/resume/restart semantics are explicit", "Conflicts retain dissent and verifier identity is distinct", "No implementation or registry delta is introduced"],
+  "required_tests": ["go test ./...", "go vet ./...", "go run ./cmd/devctl preflight -active dev/ACTIVE_TASK.json", "go run ./cmd/devctl check-diff -active dev/ACTIVE_TASK.json", "go run ./cmd/devctl check-architecture", "go run ./cmd/devctl/independent", "git diff --check", "proposal scope and required-section review"],
+  "terminal_gap_states": ["BLOCKED_BY_ARCHITECTURE_GAP", "BLOCKED_BY_SPEC_GAP", "BLOCKED_BY_CONFLICT"]
+}

docs/proposals/ADR-0021-multi-agent-work-graph-v1.md

@@ -0,0 +1,80 @@
+# Proposal ADR-0021 — Multi-Agent Work Graph V1
+
+Status: Proposed
+Task: DEV-000105
+
+## Problem and evidence
+
+The audit found durable Work and Delegation records but no multi-agent DAG,
+fan-out/fan-in scheduler, budgets, leases, conflict resolution or independent
+verifier. Adding parallel agents without those controls would create duplicate
+work, unbounded cost, hidden disagreement and false completion.
+
+## Decision proposed
+
+1. `work` owns the durable graph: `WorkGraph`, `GraphRevision`, `WorkNode`,
+   `NodeDependency`, `ResultCandidate`, `ConflictSet` and synthesis/verification
+   gating. Capability remains the source of eligible agent implementations;
+   Artifact owns result metadata; Continuity owns human attention.
+2. A graph is immutable by revision. Each revision contains typed nodes,
+   dependency edges, requested capabilities, budgets, cancellation policy,
+   synthesis policy and verifier requirements. Acyclicity and ownership are
+   validated before dispatch; edits create a new revision rather than mutating
+   a running graph.
+3. Node identity and idempotency are stable within a revision. Independent
+   nodes may fan out only after graph admission checks. A dependent node is
+   dispatchable only when all required prerequisites have accepted results.
+   Partial results and failed nodes remain attributable and do not erase
+   sibling results.
+4. Scheduling enforces durable per-goal, per-user, per-resource and per-graph
+   budgets for concurrency, attempts, time, tokens and external mutation
+   class. Backpressure and starvation detection are explicit; a role or agent
+   cannot bypass a budget.
+5. Assignment uses the Agent Execution Plane lease/fencing rules. Pause,
+   cancel, reprioritize and resume are durable graph decisions propagated to
+   eligible nodes. Restart/replay rebuilds from graph revision and execution
+   events, not process-local queues.
+6. Agent outputs are `ResultCandidate` records with author run, node, graph
+   revision, artifact refs, evidence and claims. Conflicting candidates form a
+   `ConflictSet`; dissent and unresolved conflict remain visible.
+7. Synthesis is a candidate, never an authority shortcut. A verifier with a
+   distinct run/identity from the author consumes declared evidence and emits
+   a typed verification result. Work completion requires the graph's verifier
+   policy and does not occur from fan-in text alone.
+8. Specialized roles are capability profiles and evidence-based selection
+   hints, not hardcoded authority classes. One agent may hold multiple roles;
+   role selection never grants credentials or permission.
+
+## Lifecycle and failure semantics
+
+Graph states are `DRAFT`, `ADMITTED`, `RUNNING`, `PAUSED`, `CANCELLING`,
+`PARTIAL`, `VERIFYING`, `COMPLETED`, `FAILED`, `UNKNOWN` and `RECOVERING`.
+Node states distinguish `BLOCKED_PREREQUISITE`, `READY`, `LEASED`, `RUNNING`,
+`SUCCEEDED`, `FAILED`, `CANCELLED`, `UNKNOWN` and `RECOVERING`. A failed node
+may trigger policy-defined retry or human attention; it never deletes other
+node evidence. Unknown external outcomes block unsafe replay until reconciled.
+
+## Alternatives and rationale
+
+- A shared in-memory task queue was rejected because restart loses graph state
+  and violates durable scheduling semantics.
+- A flat list of independent agents was rejected because dependencies,
+  fan-in, cycle rejection and partial completion cannot be represented safely.
+- Majority vote without provenance was rejected because disagreement and
+  source quality would be hidden.
+- Agent roles as privileged classes were rejected because capability evidence,
+  not labels, must determine eligibility and authority remains separate.
+
+## Consequences, migration and rollback
+
+The graph enables bounded parallel work and attributable synthesis, at the
+cost of durable event ordering, budget accounting and verifier capacity. No
+runtime, schema or scheduler is included in this proposal. Implementation
+must begin with a deterministic fake graph harness, cycle/budget/conflict
+tests and opt-in dispatch. Rollback disables new graph admission and drains
+or recovers active leases without deleting graph history or artifacts.
+
+Revisit if a graph node needs authority outside its capability, if cross-owner
+joins become necessary, if synthesis cannot preserve dissent, or if the
+verifier cannot be made independent of the author run.
+