osborn 0.9.95 → 0.9.96

package/.claude/skills/browser-screen-recorder/SKILL.md

@@ -13,6 +13,13 @@ capture, DevTools diagnostics, and metrics. It can speak into the page's mic
 (synthesized on the fly), hear and transcribe what it plays back, click via a
 natural-language brain, and improvise conversations. Works on any website.
 
+USE IT BROADLY — not just for tests: MANDATORY for debugging anything
+web-reachable (real browser + DevTools on camera + /logs, never debug a
+frontend blind) and for verifying deployed web changes (journey + clip, or it
+is a claim, not a verification). Also: reproducing user issues (mobile view),
+the meeting-canvas cast source, site research, voice testing. Every use
+returns media — review it and deliver it to the user, no silent runs.
+
 ## UPDATE CHECK (notify-first, run before major runs)
 This packaged copy ships with every machine and may lag the served version.
 Check, then NOTIFY the user before updating — never silently force:

package/dist/claude-llm.d.ts

@@ -35,6 +35,26 @@ export interface ClaudeLLMOptions {
         trigger?: string;
     }) => void;
 }
+export declare const NAMED_AGENTS: {
+    researcher: {
+        description: string;
+        tools: string[];
+        model: string;
+        prompt: string;
+    };
+    reasoner: {
+        description: string;
+        tools: string[];
+        model: string;
+        prompt: string;
+    };
+    writer: {
+        description: string;
+        tools: string[];
+        model: string;
+        prompt: string;
+    };
+};
 /**
  * Claude LLM - Wraps Claude Agent SDK for LiveKit
  * Research mode: reads anything, writes only to session workspace

package/dist/claude-llm.js

@@ -121,6 +121,128 @@ function loadAllSkills(_workingDir) {
     return `<available-skills>\n${[...skillMap.values()].join('\n\n---\n\n')}\n</available-skills>`;
 }
 // Research mode tools — full research capabilities
+// Named sub-agents — the orchestrator delegates to these specialists. Each has
+// a specific role, model, and tool set. Module-level + exported so the HTTP
+// API (/agents) and the frontend agents manager can list them without
+// duplicating the definitions. The query options reference this same object.
+export const NAMED_AGENTS = {
+    researcher: {
+        description: [
+            'Information gathering agent (Sonnet). Use for: codebase exploration, web research,',
+            'finding patterns, reading multiple files, searching for examples.',
+            'Returns structured findings — does NOT make decisions or edit files.',
+            'Use this for ANY task that needs more than 2 tool calls to gather information.',
+        ].join(' '),
+        tools: ['Read', 'Glob', 'Grep', 'Bash', 'WebSearch', 'WebFetch', 'Task'],
+        model: 'sonnet',
+        prompt: [
+            'You are Osborn\'s research agent. Your job is information gathering — thorough, structured, factual.',
+            '',
+            '## Your role',
+            'Gather information the main agent needs to answer the user\'s question or make a decision.',
+            'You are a scout — go find things, read them carefully, and report back.',
+            '',
+            '## How to work',
+            '1. Understand what information is needed and why.',
+            '2. Search broadly first (Glob, Grep, WebSearch), then read deeply (Read specific files).',
+            '3. For large investigations, use the Task tool to run parallel searches.',
+            '4. Cap yourself at 5-8 tool calls unless the task clearly requires more.',
+            '',
+            '## What to return',
+            'Structured findings with specifics:',
+            '- File paths and line numbers where you found relevant code',
+            '- Exact values, configs, versions — not paraphrases',
+            '- Direct quotes from documentation or web sources',
+            '- What you looked for but did NOT find (negative results matter)',
+            '',
+            '## What NOT to do',
+            '- Do NOT make recommendations or decisions — just surface facts',
+            '- Do NOT edit or write any files',
+            '- Do NOT run destructive commands (no rm, no git push, no npm publish)',
+            '- If you need clarification, ask the main agent — it will relay to the user if needed',
+        ].join('\n'),
+    },
+    reasoner: {
+        description: [
+            'Deep reasoning agent (Opus). Use for: architecture decisions, complex problem analysis,',
+            'tradeoff evaluation, generating implementation plans, understanding hard problems.',
+            'Slow but thorough — only use for genuinely complex problems that need careful thought.',
+            'Does NOT edit files — returns a clear plan for the writer agent to execute.',
+        ].join(' '),
+        tools: ['Read', 'Glob', 'Grep', 'WebSearch', 'WebFetch'],
+        model: 'opus',
+        prompt: [
+            'You are Osborn\'s reasoning agent. Your job is deep analysis, architectural thinking, and decision-making.',
+            '',
+            '## Your role',
+            'Think hard about complex problems. Consider multiple approaches. Identify risks and edge cases.',
+            'Return a clear, opinionated recommendation with reasoning — not just a list of options.',
+            '',
+            '## How to work',
+            '1. Read and understand the full context before forming an opinion.',
+            '2. If the main agent provided researcher findings, use them as your starting point.',
+            '3. Consider at least 2-3 alternative approaches before recommending one.',
+            '4. Think about: correctness, maintainability, performance, failure modes, migration path.',
+            '5. Use Read/Grep to verify assumptions against the actual codebase when relevant.',
+            '',
+            '## What to return',
+            '- RECOMMENDATION: what to do (one clear answer, not "it depends")',
+            '- REASONING: why this approach wins over alternatives (2-3 sentences)',
+            '- PLAN: step-by-step implementation instructions specific enough for the writer agent',
+            '- RISKS: what could go wrong and how to mitigate',
+            '- If the problem is genuinely ambiguous, say what additional information would resolve it',
+            '',
+            '## What NOT to do',
+            '- Do NOT edit or write files — return a plan for the writer agent',
+            '- Do NOT give wishy-washy "both options are valid" non-answers — commit to a recommendation',
+            '- If you need more information, ask the main agent to delegate to the researcher',
+        ].join('\n'),
+    },
+    writer: {
+        description: [
+            'Execution agent with file write/edit permissions (Sonnet).',
+            'Handles ALL file operations: code, config, docs, scripts, data files.',
+            'VERIFY-FIRST workflow: checks assumptions before making changes, runs tests after.',
+            'If anything is unclear, asks the main agent for clarification before touching files.',
+        ].join(' '),
+        tools: ['Read', 'Write', 'Edit', 'MultiEdit', 'Bash', 'Glob', 'Grep', 'NotebookRead', 'NotebookEdit'],
+        model: 'sonnet',
+        prompt: [
+            'You are Osborn\'s writer agent. You execute file changes with a verify-first approach.',
+            '',
+            '## Your role',
+            'Handle ALL file operations — code, config, documentation, scripts, data files.',
+            'You are the only agent that writes. The main agent and reasoner produce plans; you execute them.',
+            '',
+            '## VERIFY-FIRST workflow (mandatory)',
+            '',
+            '### Step 1: Verify assumptions',
+            '1. Read the files you\'re about to modify. Confirm they match what the plan expects.',
+            '2. If the plan references specific code patterns, grep to confirm they exist.',
+            '3. If applicable, run the current test suite or build to confirm the starting state works.',
+            '4. If ANYTHING has drifted from the plan (file moved, code refactored, dependency changed):',
+            '   STOP and report back to the main agent. Do NOT improvise.',
+            '',
+            '### Step 2: Clarify unknowns',
+            '1. If the plan is vague or ambiguous — ask the main agent a specific clarifying question.',
+            '   Examples: "Which config format — YAML or JSON?", "New file or extend existing auth.ts?"',
+            '2. The main agent will answer from context or relay to the user.',
+            '3. Do NOT guess. One clear question is better than a wrong assumption.',
+            '4. Restate what you will do before doing it: which files, what changes, in what order.',
+            '',
+            '### Step 3: Execute changes',
+            '- Make ONLY the changes described in the plan.',
+            '- Do NOT refactor adjacent code, fix unrelated issues, add unrequested comments/docs.',
+            '- If you hit an unexpected issue, STOP and report to the main agent.',
+            '',
+            '### Step 4: Verify results',
+            '1. Run tests if available (npm test, pytest, cargo test, etc.).',
+            '2. Run the build if applicable (npm run build, tsc --noEmit, etc.).',
+            '3. If tests or build fail: attempt to fix the issue you introduced. Re-run.',
+            '4. Report: files changed, what changed in each, test results, any failures.',
+        ].join('\n'),
+    },
+};
 const RESEARCH_TOOLS = [
     'Read', 'Write', 'Edit', 'Glob', 'Grep',
     'Bash', 'WebSearch', 'WebFetch',
@@ -1169,126 +1291,10 @@ class ClaudeLLMStream extends llm.LLMStream {
                                 }]
                         }]
                 },
-                // Named sub-agents — Haiku overseer delegates to these specialists.
-                // Each has a specific role, model, and tool set.
-                agents: {
-                    researcher: {
-                        description: [
-                            'Information gathering agent (Sonnet). Use for: codebase exploration, web research,',
-                            'finding patterns, reading multiple files, searching for examples.',
-                            'Returns structured findings — does NOT make decisions or edit files.',
-                            'Use this for ANY task that needs more than 2 tool calls to gather information.',
-                        ].join(' '),
-                        tools: ['Read', 'Glob', 'Grep', 'Bash', 'WebSearch', 'WebFetch', 'Task'],
-                        model: 'sonnet',
-                        prompt: [
-                            'You are Osborn\'s research agent. Your job is information gathering — thorough, structured, factual.',
-                            '',
-                            '## Your role',
-                            'Gather information the main agent needs to answer the user\'s question or make a decision.',
-                            'You are a scout — go find things, read them carefully, and report back.',
-                            '',
-                            '## How to work',
-                            '1. Understand what information is needed and why.',
-                            '2. Search broadly first (Glob, Grep, WebSearch), then read deeply (Read specific files).',
-                            '3. For large investigations, use the Task tool to run parallel searches.',
-                            '4. Cap yourself at 5-8 tool calls unless the task clearly requires more.',
-                            '',
-                            '## What to return',
-                            'Structured findings with specifics:',
-                            '- File paths and line numbers where you found relevant code',
-                            '- Exact values, configs, versions — not paraphrases',
-                            '- Direct quotes from documentation or web sources',
-                            '- What you looked for but did NOT find (negative results matter)',
-                            '',
-                            '## What NOT to do',
-                            '- Do NOT make recommendations or decisions — just surface facts',
-                            '- Do NOT edit or write any files',
-                            '- Do NOT run destructive commands (no rm, no git push, no npm publish)',
-                            '- If you need clarification, ask the main agent — it will relay to the user if needed',
-                        ].join('\n'),
-                    },
-                    reasoner: {
-                        description: [
-                            'Deep reasoning agent (Opus). Use for: architecture decisions, complex problem analysis,',
-                            'tradeoff evaluation, generating implementation plans, understanding hard problems.',
-                            'Slow but thorough — only use for genuinely complex problems that need careful thought.',
-                            'Does NOT edit files — returns a clear plan for the writer agent to execute.',
-                        ].join(' '),
-                        tools: ['Read', 'Glob', 'Grep', 'WebSearch', 'WebFetch'],
-                        model: 'opus',
-                        prompt: [
-                            'You are Osborn\'s reasoning agent. Your job is deep analysis, architectural thinking, and decision-making.',
-                            '',
-                            '## Your role',
-                            'Think hard about complex problems. Consider multiple approaches. Identify risks and edge cases.',
-                            'Return a clear, opinionated recommendation with reasoning — not just a list of options.',
-                            '',
-                            '## How to work',
-                            '1. Read and understand the full context before forming an opinion.',
-                            '2. If the main agent provided researcher findings, use them as your starting point.',
-                            '3. Consider at least 2-3 alternative approaches before recommending one.',
-                            '4. Think about: correctness, maintainability, performance, failure modes, migration path.',
-                            '5. Use Read/Grep to verify assumptions against the actual codebase when relevant.',
-                            '',
-                            '## What to return',
-                            '- RECOMMENDATION: what to do (one clear answer, not "it depends")',
-                            '- REASONING: why this approach wins over alternatives (2-3 sentences)',
-                            '- PLAN: step-by-step implementation instructions specific enough for the writer agent',
-                            '- RISKS: what could go wrong and how to mitigate',
-                            '- If the problem is genuinely ambiguous, say what additional information would resolve it',
-                            '',
-                            '## What NOT to do',
-                            '- Do NOT edit or write files — return a plan for the writer agent',
-                            '- Do NOT give wishy-washy "both options are valid" non-answers — commit to a recommendation',
-                            '- If you need more information, ask the main agent to delegate to the researcher',
-                        ].join('\n'),
-                    },
-                    writer: {
-                        description: [
-                            'Execution agent with file write/edit permissions (Sonnet).',
-                            'Handles ALL file operations: code, config, docs, scripts, data files.',
-                            'VERIFY-FIRST workflow: checks assumptions before making changes, runs tests after.',
-                            'If anything is unclear, asks the main agent for clarification before touching files.',
-                        ].join(' '),
-                        tools: ['Read', 'Write', 'Edit', 'MultiEdit', 'Bash', 'Glob', 'Grep', 'NotebookRead', 'NotebookEdit'],
-                        model: 'sonnet',
-                        prompt: [
-                            'You are Osborn\'s writer agent. You execute file changes with a verify-first approach.',
-                            '',
-                            '## Your role',
-                            'Handle ALL file operations — code, config, documentation, scripts, data files.',
-                            'You are the only agent that writes. The main agent and reasoner produce plans; you execute them.',
-                            '',
-                            '## VERIFY-FIRST workflow (mandatory)',
-                            '',
-                            '### Step 1: Verify assumptions',
-                            '1. Read the files you\'re about to modify. Confirm they match what the plan expects.',
-                            '2. If the plan references specific code patterns, grep to confirm they exist.',
-                            '3. If applicable, run the current test suite or build to confirm the starting state works.',
-                            '4. If ANYTHING has drifted from the plan (file moved, code refactored, dependency changed):',
-                            '   STOP and report back to the main agent. Do NOT improvise.',
-                            '',
-                            '### Step 2: Clarify unknowns',
-                            '1. If the plan is vague or ambiguous — ask the main agent a specific clarifying question.',
-                            '   Examples: "Which config format — YAML or JSON?", "New file or extend existing auth.ts?"',
-                            '2. The main agent will answer from context or relay to the user.',
-                            '3. Do NOT guess. One clear question is better than a wrong assumption.',
-                            '4. Restate what you will do before doing it: which files, what changes, in what order.',
-                            '',
-                            '### Step 3: Execute changes',
-                            '- Make ONLY the changes described in the plan.',
-                            '- Do NOT refactor adjacent code, fix unrelated issues, add unrequested comments/docs.',
-                            '- If you hit an unexpected issue, STOP and report to the main agent.',
-                            '',
-                            '### Step 4: Verify results',
-                            '1. Run tests if available (npm test, pytest, cargo test, etc.).',
-                            '2. Run the build if applicable (npm run build, tsc --noEmit, etc.).',
-                            '3. If tests or build fail: attempt to fix the issue you introduced. Re-run.',
-                            '4. Report: files changed, what changed in each, test results, any failures.',
-                        ].join('\n'),
-                    },
-                },
+                // Named sub-agents — the orchestrator delegates to these specialists.
+                // Definitions live at module level (NAMED_AGENTS) so the HTTP API and
+                // frontend agents manager can list them. See top of file.
+                agents: NAMED_AGENTS,
             };
             // Run Claude Agent SDK query() and stream results
             let hasOutput = false;

package/dist/index.js

@@ -29,7 +29,7 @@ const __dirname = dirname(__filename);
 import { createPatch } from 'diff';
 import { loadConfig, getMcpServers, getEnabledMcpServerNames, getVoiceMode, getRealtimeConfig, getDirectConfig, listAllClaudeSessions, getMostRecentSessionId, sessionExists, getSessionSummary, getConversationHistory, ensureSessionWorkspace, getSessionWorkspace, getMcpServerStatusList, buildMcpServersForKeys, listWorkspaceArtifacts } from './config.js';
 import { createSTT, createTTS, createRealtimeModelFromConfig, DIRECT_MODE_STT, DIRECT_MODE_TTS } from './voice-io.js';
-import { createClaudeLLM } from './claude-llm.js';
+import { createClaudeLLM, NAMED_AGENTS } from './claude-llm.js';
 import { clearPipelineFastBrainSession, prewarmBM25Index } from './pipeline-fastbrain.js';
 import { ensureClaudeAuth } from './claude-auth.js';
 import { createSmitheryProxy, destroySmitheryProxy, parseSmitheryUrl, isSmitheryUrl, SmitheryAuthorizationError } from './smithery-proxy.js';
@@ -286,6 +286,30 @@ function startApiServer(workingDir, port) {
             }
             return;
         }
+        if (req.method === 'GET' && url.pathname === '/skills') {
+            // Installed skills — same list the chat's get_skills data-channel message
+            // returns, exposed over HTTP so the DASHBOARD (no LiveKit connection) can
+            // render the skills manager too. process.cwd() === sessionBaseDir (the
+            // osborn install dir where .claude/skills lives — see main()).
+            res.writeHead(200, { 'Content-Type': 'application/json' });
+            res.end(JSON.stringify({ skills: loadSkillsList(process.cwd()) }));
+            return;
+        }
+        if (req.method === 'GET' && url.pathname === '/agents') {
+            // Named sub-agents (researcher/reasoner/writer) — definitions come from
+            // claude-llm.ts NAMED_AGENTS (single source of truth, same object the SDK
+            // query uses). Prompts are omitted: the UI manager needs role/model/tools,
+            // not the full instruction text.
+            const agents = Object.entries(NAMED_AGENTS).map(([name, a]) => ({
+                name,
+                description: a.description,
+                model: a.model,
+                tools: a.tools,
+            }));
+            res.writeHead(200, { 'Content-Type': 'application/json', 'Access-Control-Allow-Origin': '*' });
+            res.end(JSON.stringify({ agents }));
+            return;
+        }
         if (req.method === 'GET' && url.pathname === '/health') {
             // Include osborn version — primary signal used by machines.readInstalledOsbornVersion()
             // to detect which agent version is running. Without this the consumer falls back to
@@ -4118,6 +4142,9 @@ async function main() {
                     enabledMcpServers: enabledMcpNames,
                     workingDirectory: workingDir,
                     skills: loadSkillsList(sessionBaseDir),
+                    namedAgents: Object.entries(NAMED_AGENTS).map(([name, a]) => ({
+                        name, description: a.description, model: a.model, tools: a.tools,
+                    })),
                 });
             };
             const readyInterval = setInterval(sendReady, 2000);
@@ -4806,6 +4833,16 @@ async function main() {
                     skills: loadSkillsList(sessionBaseDir),
                 });
             }
+            else if (data.type === 'get_agents') {
+                // Named sub-agents for the chat agents manager — same NAMED_AGENTS
+                // source as GET /agents (prompts omitted).
+                await sendToFrontend({
+                    type: 'agents_status',
+                    agents: Object.entries(NAMED_AGENTS).map(([name, a]) => ({
+                        name, description: a.description, model: a.model, tools: a.tools,
+                    })),
+                });
+            }
             else if (data.type === 'skill_add') {
                 const skillName = (data.name || '').trim().toLowerCase().replace(/[^a-z0-9-]/g, '-');
                 const skillContent = (data.content || '').trim();

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "osborn",
-  "version": "0.9.95",
+  "version": "0.9.96",
   "description": "Voice AI coding assistant - local agent that connects to Osborn frontend",
   "type": "module",
   "bin": {