open-agents-ai 0.187.260 → 0.187.263

package/README.md

@@ -40,6 +40,32 @@ An autonomous multi-turn tool-calling agent that reads your code, makes changes,
   - [JSON Output Mode](#json-output-mode)
   - [Process Management](#process-management)
   - [REST API Service (Port 11435)](#rest-api-service-port-11435)
+    - [Access Policy & Binding](#access-policy--binding)
+    - [Working Directory](#working-directory)
+    - [Health & Observability](#health--observability)
+    - [OpenAI-Compatible Inference](#openai-compatible-inference)
+    - [Agentic Task Execution](#agentic-task-execution)
+    - [Configuration](#configuration-1)
+    - [Slash Commands via REST](#slash-commands-via-rest)
+    - [Auth Scopes](#auth-scopes)
+    - [Tool-Use Profiles](#tool-use-profiles)
+    - [Parallelism & Concurrency](#parallelism--concurrency)
+    - [Endpoint Reference](#endpoint-reference)
+    - [Stateful Chat — `/v1/chat` + `/api/chat` (OpenAI drop-in with full agent under the hood)](#stateful-chat--v1chat--apichat-openai-drop-in-with-full-agent-under-the-hood)
+    - [Live Comparison: Ollama vs OA Full Agent](#live-comparison-ollama-vs-oa-full-agent)
+    - [One-Off Completions — `/api/generate` + `/v1/generate`](#one-off-completions--apigenerate--v1generate)
+    - [Embeddings — `/v1/embeddings` + `/api/embed`](#embeddings--v1embeddings--apiembed)
+    - [Memory Recall + Knowledge Graph — `/v1/memory/*`](#memory-recall--knowledge-graph--v1memory)
+    - [Generate/Embed/Memory Test Harness](#generateembedmemory-test-harness)
+    - [AIWG Cascade — `/v1/aiwg/*`](#aiwg-cascade--v1aiwg)
+    - [ISO/IEC 42001:2023 AIMS — `/v1/aims/*`](#isoiec-420012023-aims--v1aims)
+    - [Event Bus — `/v1/events` (SSE fanout)](#event-bus--v1events-sse-fanout)
+    - [Memory + Skills + MCP + Tools + Engines (parity surface)](#memory--skills--mcp--tools--engines-parity-surface)
+    - [Sessions, Context, Cost, Sponsors, Nexus](#sessions-context-cost-sponsors-nexus)
+    - [RFC 7807 Problem Details (error envelope)](#rfc-7807-problem-details-error-envelope)
+    - [Pagination envelope](#pagination-envelope)
+    - [ETag + Conditional GET](#etag--conditional-get)
+    - [Web Interface](#web-interface)
 - [Architecture](#architecture)
 - [Context Engineering](#context-engineering)
 - [Model-Tier Awareness](#model-tier-awareness)
@@ -72,6 +98,7 @@ An autonomous multi-turn tool-calling agent that reads your code, makes changes,
   - [Cross-Modal Binding](#cross-modal-binding)
   - [Gist Compression](#gist-compression)
   - [Near-Critical Cognitive Architecture](#near-critical-cognitive-architecture)
+  - [Cross‑Modality Identity & Association (CLIP + Voice)](#crossmodality-identity--association-clip--voice)
 - [Ralph Loop — Iteration-First Design](#ralph-loop--iteration-first-design)
 - [Task Control](#task-control)
   - [Pause, Stop, Resume, Destroy](#pause-stop-resume-destroy)
@@ -423,6 +450,14 @@ OA_API_KEYS="key1:admin:alice:30:50000:5,key2:run:ci:60::3,key3:read:grafana" oa
 
 > **Every example below is verified against `open-agents-ai@0.187.189` on a live daemon.** Examples from earlier versions are deprecated.
 
+#### Access Policy & Binding
+
+Control who can reach the daemon and where it binds:
+
+- TUI commands: `/access loopback|lan|any`, `/host <host[:port]>`, `/network config` (interactive), `--local` to save per‑project.
+- Environment: `OA_ACCESS=loopback|lan|any`, `OA_HOST=host[:port]`.
+- See Configuration → [Network Access & Binding](#network-access--binding) for full details and security guidance.
+
 #### Working Directory
 
 Pass `X-Working-Directory` header to run commands in your current terminal directory:
@@ -3636,6 +3671,18 @@ Post-task, the [ReadAgent](https://arxiv.org/abs/2402.09727) gist compressor cre
 
 ### Near-Critical Cognitive Architecture
 
+### Cross‑Modality Identity & Association (CLIP + Voice)
+
+Open Agents binds entities across image, audio, and text using joint‑embedding models:
+
+- CLIP‑based visual ID: person/object embeddings extracted from frames are matched to persistent entity nodes; cosine similarity > τ promotes to identity with temporal smoothing. Supports multi‑appearance tracking and re‑identification across sessions.
+- Voiceprint linkage: speaker embeddings (x‑vector/ECAPA) are associated with entities when co‑occurring in time with a visual track and a transcribed utterance; robust to background noise via median pooling across windows.
+- Text label fusion: natural‑language labels (names, roles, tags) are bound to the same entity when co‑referents appear in proximate context windows (heuristics + clustering).
+- Association graph: cross‑modal edges (image↔voice↔text) consolidate into a unified entity node with provenance (model, score, timestamp) and decay‑based confidence.
+- Privacy & safety: raw media never leaves the machine; embeddings are stored locally under `.oa/memory/`. Redaction controls can drop embeddings by label or recency.
+
+This enables queries like: “Find where Alex spoke about deployment,” “Show files edited after the person in the red sweater approved the PR,” or “Summarize conversations where Speaker‑B and Alice appear together.”
+
 The associative memory integrates with a near-critical cognitive framework inspired by [Beggs & Plenz (2003)](https://doi.org/10.1523/JNEUROSCI.23-35-11167.2003) neuronal avalanche dynamics:
 
 - **Auto-consolidation**: At task boundaries, the system writes consolidation snapshots to `.oa/consolidations/` with lessons learned and key patterns