open-agents-ai 0.185.71 → 0.185.72

package/README.md

@@ -1286,7 +1286,7 @@ The voice narration system produces **zero static phrase pools** — every spoke
 | 2 | Contextual opener | "Moving to voice.ts" |
 | 3 | Gerund-led | "Taking a deeper look at voice.ts now" |
 
-**Ring buffer deduplication** ([Moshi inner monologue, arXiv:2410.00037](https://arxiv.org/abs/2410.00037)): A sliding window of the last 8 utterances catches near-duplicates via Jaccard word-level similarity (threshold 0.7). When a near-duplicate is detected, **DITTO adaptive rotation** ([arXiv:2206.02369](https://arxiv.org/abs/2206.02369), NeurIPS 2022) advances the structure pattern by 2 positions to break self-reinforcing repetition loops.
+**Ring buffer deduplication** ([Moshi inner monologue, [arXiv:2410.00037](https://arxiv.org/abs/2410.00037)](https://arxiv.org/abs/2410.00037)): A sliding window of the last 8 utterances catches near-duplicates via Jaccard word-level similarity (threshold 0.7). When a near-duplicate is detected, **DITTO adaptive rotation** ([arXiv:2206.02369](https://arxiv.org/abs/2206.02369), NeurIPS 2022) advances the structure pattern by 2 positions to break self-reinforcing repetition loops.
 
 **State-computed emotion interjections**: Instead of word pools, emotion interjections are computed from real session metrics. The emotion quadrant (from ADV coordinates) determines *which* metrics to surface:
 
@@ -1299,7 +1299,7 @@ The voice narration system produces **zero static phrase pools** — every spoke
 
 ### Emotion-Driven Prosody (SEST)
 
-The voice engine modulates **three prosodic dimensions** from the emotion state — text vocabulary stays factual, emotion is expressed through *how* it sounds, not *what* it says ([EmoShift, arXiv:2601.22873](https://arxiv.org/abs/2601.22873)):
+The voice engine modulates **three prosodic dimensions** from the emotion state — text vocabulary stays factual, emotion is expressed through *how* it sounds, not *what* it says ([EmoShift, [arXiv:2601.22873](https://arxiv.org/abs/2601.22873)](https://arxiv.org/abs/2601.22873)):
 
 | Dimension | Source | Effect | Range |
 |-----------|--------|--------|-------|
@@ -1307,7 +1307,7 @@ The voice engine modulates **three prosodic dimensions** from the emotion state
 | **Speed** | Arousal (primary) + Dominance (secondary) | High arousal = faster, high dominance = more deliberate | [0.85x, 1.15x] |
 | **Volume** | Speaker role | Primary = 100%, subordinate (sub-agent) = 55% | [0.55, 1.0] |
 
-Pitch and speed use **nonlinear tanh squashing** ([UDDETTS, arXiv:2505.10599](https://arxiv.org/abs/2505.10599)) — moderate emotions get amplified for expressiveness, extreme emotions saturate gracefully instead of clipping.
+Pitch and speed use **nonlinear tanh squashing** ([UDDETTS, [arXiv:2505.10599](https://arxiv.org/abs/2505.10599)](https://arxiv.org/abs/2505.10599)) — moderate emotions get amplified for expressiveness, extreme emotions saturate gracefully instead of clipping.
 
 Each narration also emits a **ProsodyHint** metadata object following the RLAIF-SPA SEST schema ([arXiv:2510.14628](https://arxiv.org/abs/2510.14628)) — Structure/Emotion/Speed/Tone — which downstream consumers (WebSocket voice sessions, Telegram TTS) can use independently:
 
@@ -2533,7 +2533,7 @@ The eval runner supports `--runs N` for pass^k reliability measurement (consiste
 
 ### REST API Enterprise Evaluation (v0.185.68)
 
-35 test cases executed against the real REST API (`oa serve` on port 11435) across **10 industries** and **3 model tiers**. Each case sends a domain-specific prompt via `/v1/chat/completions` and verifies correctness against expected patterns.
+35 test cases executed against the oa REST API (`oa serve` on port 11435) across **10 industries** and **3 model tiers**. Each case sends a domain-specific prompt via `/v1/chat/completions` and verifies correctness against expected patterns.
 
 ```bash
 node eval/api-enterprise-eval.mjs                    # Run all 85 tests (35 cases × 3 models)
@@ -2572,7 +2572,7 @@ node eval/api-enterprise-eval.mjs                    # Run all 85 tests (35 case
 | 9B + PoT hint | 13% | **100%** | Models write correct Python but chat API can't execute it |
 | 27B + PoT hint | 47% | **100%** | Larger models can trace code mentally; full accuracy requires `repl_exec` in agentic mode |
 
-The PoT (Program-of-Thought) guidance achieves **100% code generation rate** — every model writes Python instead of computing in-head. Full correctness is realized in agentic mode where `repl_exec` executes the code. Research basis: PAL (arXiv:2211.10435), PoT (arXiv:2211.12588), ToRA (arXiv:2309.17452), START (arXiv:2503.04625).
+The PoT (Program-of-Thought) guidance achieves **100% code generation rate** — every model writes Python instead of computing in-head. Full correctness is realized in agentic mode where `repl_exec` executes the code. Research basis: PAL ([arXiv:2211.10435](https://arxiv.org/abs/2211.10435)), PoT ([arXiv:2211.12588](https://arxiv.org/abs/2211.12588)), ToRA ([arXiv:2309.17452](https://arxiv.org/abs/2309.17452)), START ([arXiv:2503.04625](https://arxiv.org/abs/2503.04625)).
 
 **Key architectural findings:**
 - API proxy timeout of 10s caused **100% failure** for cold model loads (Ollama needs 15-115s to load models). Fixed to 120s in v0.185.60.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "open-agents-ai",
-  "version": "0.185.71",
+  "version": "0.185.72",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/index.js",