open-agents-ai 0.35.0 → 0.35.1

package/README.md

@@ -38,7 +38,8 @@ An autonomous multi-turn tool-calling agent that reads your code, makes changes,
 - **Ralph Loop** — iterative task execution that keeps retrying until completion criteria are met
 - **Dream Mode** — creative idle exploration modeled after real sleep architecture (NREM→REM cycles)
 - **Live Listen** — bidirectional voice communication with real-time Whisper transcription
-- **Neural TTS** — hear what the agent is doing via GLaDOS or Overwatch ONNX voices
+- **Neural TTS** — hear what the agent is doing via GLaDOS or Overwatch ONNX voices, with personality-driven expressiveness
+- **Personality Core** — SAC framework-based style control (concise/balanced/verbose/pedagogical) that shapes agent response depth, voice expressiveness, and system prompt behavior
 - **Human expert speed ratio** — real-time `Exp: Nx` gauge comparing agent speed to a leading human expert, calibrated across 47 tool baselines
 - **Cost tracking** — real-time token cost estimation for 15+ cloud providers
 - **Work evaluation** — LLM-as-judge scoring with task-type-specific rubrics
@@ -134,6 +135,26 @@ Compaction thresholds scale dynamically with model size:
 | Medium (8-29B) | 24,000 tokens (or 75% of context) | 8 messages |
 | Small (≤7B) | 12,000 tokens (or 75% of context) | 4-6 messages |
 
+### Status Bar Context Tracking (`Ctx:`)
+
+The status bar displays a live `Ctx:` gauge showing estimated context window usage:
+
+```
+In: 12,345 | Out: 4,567 | Ctx: 18,000/131,072 86% | Exp: 4.2x
+                           ^^^^^^^^^^^^^^^^^^^^^^^^
+                           Estimated tokens used / total context window
+```
+
+This gauge reflects the **post-compaction** token count — when compaction fires, the `Ctx:` value drops to match the actual compressed message history. The compaction warning message shows the before/after:
+
+```
+⚠ Context compacted: Compacted 70 messages | ~40,279 → ~22,754 tokens (saved ~17,525)
+```
+
+After this compaction, `Ctx:` updates to reflect ~22,754 tokens (not the pre-compaction ~40,279). Both the main inference loop and the brute-force re-engagement path calculate context tokens from the compacted message array, ensuring the status bar always represents the true context state sent to the model.
+
+The percentage shows context **remaining** (not used) — green when >50% free, yellow at 25-50%, red below 25%.
+
 ### Memex Experience Archive
 
 During compaction, large tool outputs (file reads, grep results, command output) are archived with a short hash ID. The agent can recover any archived result using `memex_retrieve`:
@@ -402,6 +423,8 @@ The TUI features an animated multilingual phrase carousel, live metrics bar with
 | `/stream` | Toggle streaming token display with pastel syntax highlighting |
 | `/bruteforce` | Toggle brute-force mode (auto re-engage on turn limit) |
 | `/verbose` | Toggle verbose mode |
+| `/style [preset]` | Set personality style: `concise`, `balanced`, `verbose`, `pedagogical` |
+| `/personality [preset]` | Alias for `/style` |
 | **Tools & Skills** | |
 | `/tools` | List agent-created custom tools |
 | `/skills [keyword]` | List/search available AIWG skills |
@@ -558,6 +581,66 @@ All context-dependent values scale automatically with the actual context window
 
 Auto-downloads the ONNX voice model (~50MB) on first use. Install `espeak-ng` for best quality (`apt install espeak-ng` / `brew install espeak-ng`).
 
+### Personality-Aware Voice
+
+Voice output adapts to the active personality style — the same tool call sounds different depending on the `/style` preset:
+
+| Style | Example (file_read) | Example (npm test) |
+|-------|--------------------|--------------------|
+| **concise** | "Reading app.ts" | "Running tests" |
+| **balanced** | "Let me take a look at app.ts" | "Let's run the tests and see how we're doing" |
+| **verbose** | "Alright, let's crack open app.ts and see what we're working with" | "Alright, moment of truth, let's see if the tests pass" |
+
+Task completion, tool failures, and all TTS announcements follow the same personality tier. Set the style with `/style verbose` and the voice output becomes conversational rather than robotic.
+
+## Personality Core — SAC Framework Style Control
+
+The personality system controls how the agent communicates — from silent operator to teacher mode. It's based on the **SAC framework** (arXiv:2506.20993) which models personality along five behavioral intensity dimensions rather than binary trait toggles.
+
+```bash
+/style concise       # Silent operator — acts without explaining
+/style balanced      # Default — moderate narration
+/style verbose       # Thorough explainer — narrates reasoning
+/style pedagogical   # Teacher mode — maximum explanation with alternatives
+```
+
+### How It Works
+
+Each personality preset maps to a `PersonalityProfile` with five dimensions scored 1-5:
+
+| Dimension | What It Controls | concise | balanced | verbose | pedagogical |
+|-----------|-----------------|---------|----------|---------|-------------|
+| **Frequency** | How often the agent narrates actions | 1 | 3 | 5 | 5 |
+| **Depth** | Reasoning detail exposed in output | 1 | 3 | 4 | 5 |
+| **Threshold** | When to speak vs. act silently | 1 | 3 | 4 | 5 |
+| **Effort** | Response formatting quality | 2 | 3 | 4 | 5 |
+| **Willingness** | Proactive suggestions beyond the task | 1 | 3 | 4 | 5 |
+
+The profile is compiled into a system prompt suffix (max 80 tokens) injected at the end of the base prompt. This follows research showing prompt-level steering dominates activation-level interventions (arXiv:2512.17639) and uses positive framing ("Be concise") over negation ("Don't be verbose") per KAIST findings.
+
+### What Changes Per Style
+
+| Aspect | concise | balanced | verbose | pedagogical |
+|--------|---------|----------|---------|-------------|
+| System prompt | "Act silently, raw results only" | No override | "Explain reasoning, summarize" | "Thorough explanations, alternatives" |
+| Voice TTS | Terse: "Reading file.ts" | Conversational: "Let me take a look" | Chatty: "Alright, let's crack it open" | Chatty + context |
+| Tool calls observed | Same behavior | Same behavior | More exploration, diagnostics | Maximum exploration |
+| Response length | Minimal | Moderate | Detailed | Comprehensive |
+
+### Persistence
+
+The style is saved to `.oa/settings.json` (with `--local`) or `~/.open-agents/config.json` (global) and persists across sessions. Change it anytime with `/style <preset>` — takes effect on the next task.
+
+### Research Provenance
+
+The personality system draws on:
+
+- **SAC Framework** (arXiv:2506.20993) — Five behavioral intensity dimensions with adjective-based semantic anchoring for stable trait expression
+- **Lost in the Middle** (arXiv:2307.03172) — U-shaped attention bias; personality suffix placed at prompt boundaries, not middle
+- **Same Task, More Tokens** (arXiv:2402.14848) — LLM reasoning degrades at ~3K system prompt tokens; personality suffix stays under 80 tokens
+- **Linear Personality Probing** (arXiv:2512.17639) — Prompt-level steering completely dominates activation-level interventions
+- **The Prompt Report** (arXiv:2406.06608) — Positive framing outperforms negated instructions for behavioral control
+
 ## Human Expert Speed Ratio
 
 The status bar displays a real-time `Exp: Nx` gauge estimating how fast the agent is working relative to a leading human expert performing equivalent tasks.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "open-agents-ai",
-  "version": "0.35.0",
+  "version": "0.35.1",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/index.js",