Skip to content

feat(agent-term): state-integrity ChatOps, graph binding, reasoning-run, ops-history CLI#89

Merged
mdheller merged 1 commit into
mainfrom
feat/state-integrity-graph-reasoning-stubs
Jul 18, 2026
Merged

feat(agent-term): state-integrity ChatOps, graph binding, reasoning-run, ops-history CLI#89
mdheller merged 1 commit into
mainfrom
feat/state-integrity-graph-reasoning-stubs

Conversation

@mdheller

Copy link
Copy Markdown
Contributor

Summary

  • state_integrity.py — State Integrity ChatOps surface: agent-term state-integrity status [--json] + conflicts [--json]. Probes sourceos-syncd if available, stubs otherwise. Typed: StateIntegrityStatus, ConflictQueue, RepairApproval.
  • graph_binding.py — Agentic graph ChatOps: agent-term graph status|agents|leases [--json]. Governed query surface — Agent Registry, Policy Fabric, capability leases — no bypass. Stubs until live services are reachable.
  • reasoning_run.py — Superconscious ReasoningRun trace console: agent-term reasoning-run list|show [--json]. Typed: ReasoningRunTrace, ReasoningStep, ReasoningRunIndex. Stubs until evidence store is live.
  • cli.py — Wires all four subcommands; fixes ops-history policy to use --profile flag + adds context-pack subcommand matching existing test expectations.

Test results

164 passing (up from 162), 24 pre-existing failures unchanged. All 6 test_ops_history.py tests now pass.

Closes

Note: #9 (Textual TUI) and #18 (Agent Machine workspace) depend on upstream services and are tracked separately.

🤖 Generated with Claude Code

…un, ops-history CLI (closes #33, #36, #37, #38)

- state_integrity.py: StateIntegrityStatus + ConflictQueue + RepairApproval with sourceos-syncd probe;
  `agent-term state-integrity status [--json]` and `state-integrity conflicts [--json]`
- graph_binding.py: AgentRegistryEntry + CapabilityLease + PolicyFabricDecision + GraphSnapshot stubs;
  `agent-term graph status|agents|leases [--json]` — governed query surface, no bypass of Agent Registry
- reasoning_run.py: ReasoningRunTrace + ReasoningStep + ReasoningRunIndex stubs;
  `agent-term reasoning-run list|show [--json]` — Superconscious trace operator console
- cli.py: wire all four new subcommands; fix ops-history policy to use --profile flag + add
  context-pack subcommand — all 6 ops_history tests now pass (164 total passing, 24 pre-existing failures)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant