omnius 1.0.674 → 1.0.676

package/.aiwg/addons/omnius-docs/README.md

@@ -3,10 +3,10 @@
 This project-local addon exposes Omnius documentation as small discoverable skills. It is for agents that need to answer questions about Omnius without loading the entire docs tree.
 
 Start with `omnius-agent-onboarding` when the agent has no Omnius context, or
-`omnius-docs` when it already knows the documentation domain. Then load a more specific skill when the task is
-about inference providers, tools/web search, service integration, version
-compatibility, realtime, sponsors, Telegram, operations, or browser
-interaction validation.
+`omnius-docs` when it already knows the documentation domain. Then load a more
+specific skill when the task is about inference providers, tools/web search,
+evidence-bound adjudication, service integration, version compatibility,
+realtime, sponsors, Telegram, operations, or browser interaction validation.
 
 Documentation-routing skills:
 

package/.aiwg/addons/omnius-docs/skills/omnius-docs/SKILL.md

@@ -40,6 +40,7 @@ Find and use Omnius documentation without loading the whole docs tree.
 - Discovery cascade: `docs/DISCOVERY.md`
 - Bring your own inference: `docs/guides/bring-your-own-inference.md`
 - Tools and web search: `docs/guides/tools-and-web-search.md`
+- Evidence-bound adjudication: `docs/ADJUDICATION.md`
 - Agent integration: `docs/guides/agent-integration.md`
 - Agent system map: `docs/architecture/agent-system-map.md`
 - Service compatibility: `docs/operations/version-compatibility.md`

package/.aiwg/addons/omnius-docs/skills/omnius-tools-docs/SKILL.md

@@ -1,23 +1,30 @@
 ---
 name: omnius-tools-docs
-description: Discover Omnius tools and select the correct direct, agent-loop, external HTTP, or MCP invocation interface.
+description: Discover Omnius tools, including evidence-bound adjudication, and select the exact interactive, agent-loop, direct, external HTTP, or MCP invocation interface.
 compaction_strategy: structured
 ---
 
 # omnius-tools-docs
 
-Use for built-in tools, web search, direct tool calls, external tools, MCP,
-tool security, and tool profiles.
+Use for built-in tools, web search, evidence-bound adjudication, direct tool
+calls, external tools, MCP, tool security, and tool profiles.
 
 ## Workflow
 
 1. Read `docs/guides/tools-and-web-search.md`.
-2. Inspect the stable catalog entry and live `GET /v1/tools/{name}` metadata.
+2. Inspect the stable catalog entry. Inspect live `GET /v1/tools/{name}`
+   metadata only when the entry documents daemon registry exposure.
 3. Use a direct call only when `direct_callable` is true.
-4. Route agent-bound tools through `/v1/run`, `/v1/chat`, or
-   `/v1/chat/completions`.
+4. Follow the exact agent-bound interface in the catalog. Most daemon tools use
+   `/v1/run`, `/v1/chat`, or `/v1/chat/completions`; `adjudicate` currently uses
+   only the top-level interactive TUI agent.
 5. Preserve auth scope, profile, origin, network, and risk gates.
 
 `web_search` is agent-bound. Its schema can be discovered, but it should be
 offered to an Omnius agent loop instead of assumed callable at the direct tool
 route.
+
+`adjudicate` is available only to the top-level interactive TUI agent. Read
+`docs/ADJUDICATION.md` for its evidence, panel, quorum, verdict, receipt, and
+harness contracts. Do not infer a daemon direct-call route or offer it to a
+sub-agent.

package/README.md

@@ -57,6 +57,8 @@ omnius show store.project
 omnius show provider.anthropic
 omnius show provider.gemini
 omnius show tool.web-search
+omnius discover "evidence-bound decision impasse"
+omnius show tool.adjudicate
 omnius discover "osint research"
 omnius show capability.osint-research
 omnius capabilities --json
@@ -73,12 +75,17 @@ agent or service, and use the [agent system map](docs/architecture/agent-system-
 to trace layers, modules, runtimes, and state ownership. Use [bring-your-own inference](docs/guides/bring-your-own-inference.md)
 for provider protocols and keys, and [tools and web search](docs/guides/tools-and-web-search.md)
 for the distinction between direct tools and agent-bound tools. The
+[evidence-bound adjudication guide](docs/ADJUDICATION.md) explains how the
+top-level interactive agent isolates a genuine decision impasse, fans review
+out across independent constituents, validates evidence citations and quorum,
+and produces a durable verdict receipt. The
 [categorized OSINT research guide](docs/guides/osint-research.md) documents
 the local discover → exact expansion → explicit web-tool workflow.
 
 ## What Omnius Does
 
 - Runs autonomous coding tasks, edits files, executes tools, tests changes, and iterates on failures.
+- Resolves genuine decision impasses through isolated evidence-scoped constituent review, host-validated citations, quorum, preserved dissent, and durable verdict receipts.
 - Provides a dense terminal UI for model selection, endpoint routing, task control, shell output, voice, sponsors, Telegram, and system telemetry.
 - Exposes a REST daemon with OpenAI/Ollama-compatible inference, agentic task execution, memory, skills, tools, MCP, events, voice, projects, and governance endpoints.
 - Routes models through local, cloud, sponsor, and peer-to-peer endpoints without assuming local Ollama is the only source.
@@ -123,6 +130,7 @@ omnius serve
 | Agent discovery | [Discovery cascade](docs/DISCOVERY.md), [machine catalog](docs/DISCOVERY.json), [agent integration](docs/guides/agent-integration.md) |
 | Bring your own inference | [Provider protocols and keys](docs/guides/bring-your-own-inference.md) |
 | Tools and web search | [Tool discovery and invocation](docs/guides/tools-and-web-search.md) |
+| Evidence-bound adjudication | [Adjudication tool, panel workflow, verdict contract, and harness](docs/ADJUDICATION.md) |
 | Terminal workflows | [TUI workflows](docs/guides/tui-workflows.md), [Slash commands](docs/reference/slash-commands.md) |
 | Web dashboard | [All dashboard routes, workspaces, sessions, Voice, Generate, updates, and observability](docs/guides/dashboard.md) |
 | REST daemon | [REST reference](docs/reference/rest-api.md), [REST quickref](docs/rest/QUICKREF.md), [OpenAPI source](docs/rest/openapi-source.md) |