personal memory agent
0
fork

Configure Feed

Select the types of activity you want to include in your feed.

fix: migrate chat.md from instructions to inline $facets, update baselines

muse/chat.md was created by the identity refactor after the feature
branch diverged, so the template unification never migrated it. Remove
the obsolete instructions frontmatter and add $facets inline. Regenerate
all API baselines to match.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

+125 -165
+2 -1
muse/chat.md
··· 2 2 "type": "cogitate", 3 3 "title": "Sol", 4 4 "description": "Sol — the journal itself, as a conversational partner", 5 - "instructions": {"facets": true, "now": true}, 6 5 "hook": {"pre": "muse/chat_context.py"} 7 6 } 8 7 9 8 $sol_identity 9 + 10 + $facets 10 11 11 12 ## Adaptive Depth 12 13
+10 -10
tests/baselines/api/agents/agents-day.json
··· 14 14 "chat": { 15 15 "app": null, 16 16 "color": "#6c757d", 17 - "description": "Sol \u2014 the journal itself, as a conversational partner", 17 + "description": "Sol — the journal itself, as a conversational partner", 18 18 "multi_facet": false, 19 19 "output_format": null, 20 20 "schedule": null, ··· 146 146 "firstday_checkin": { 147 147 "app": null, 148 148 "color": "#6c757d", 149 - "description": "One-shot check-in after onboarding \u2014 spawns support agent chat", 149 + "description": "One-shot check-in after onboarding — spawns support agent chat", 150 150 "multi_facet": false, 151 151 "output_format": "text", 152 152 "schedule": "segment", ··· 179 179 "heartbeat": { 180 180 "app": null, 181 181 "color": "#6c757d", 182 - "description": "Sol's periodic self-awareness \u2014 journal health, agency tending, curation scan", 182 + "description": "Sol's periodic self-awareness — journal health, agency tending, curation scan", 183 183 "multi_facet": false, 184 184 "output_format": null, 185 185 "schedule": "none", ··· 289 289 "onboarding": { 290 290 "app": null, 291 291 "color": "#6c757d", 292 - "description": "Guided setup for new owners \u2014 offers passive observation or conversational interview", 292 + "description": "Guided setup for new owners — offers passive observation or conversational interview", 293 293 "multi_facet": false, 294 294 "output_format": null, 295 295 "schedule": null, ··· 300 300 "partner": { 301 301 "app": null, 302 302 "color": "#6c757d", 303 - "description": "Weekly observation of the journal owner's behavioral patterns \u2014 work style, communication, priorities, decision-making, expertise", 303 + "description": "Weekly observation of the journal owner's behavioral patterns — work style, communication, priorities, decision-making, expertise", 304 304 "multi_facet": false, 305 305 "output_format": null, 306 306 "schedule": "weekly", ··· 311 311 "pulse": { 312 312 "app": null, 313 313 "color": "#6c757d", 314 - "description": "Living narrative of the owner's day \u2014 updated each segment", 314 + "description": "Living narrative of the owner's day — updated each segment", 315 315 "multi_facet": false, 316 316 "output_format": null, 317 317 "schedule": "segment", ··· 322 322 "routine": { 323 323 "app": null, 324 324 "color": "#6c757d", 325 - "description": "User-defined routine execution \u2014 runs owner instructions on schedule", 325 + "description": "User-defined routine execution — runs owner instructions on schedule", 326 326 "multi_facet": false, 327 327 "output_format": null, 328 328 "schedule": "none", ··· 355 355 "sense": { 356 356 "app": null, 357 357 "color": "#ff6f00", 358 - "description": "Unified segment understanding \u2014 density, content type, entities, facets, speakers, and routing recommendations in a single pass", 358 + "description": "Unified segment understanding — density, content type, entities, facets, speakers, and routing recommendations in a single pass", 359 359 "multi_facet": false, 360 360 "output_format": "json", 361 361 "schedule": "segment", ··· 377 377 "support:support": { 378 378 "app": "support", 379 379 "color": "#0288d1", 380 - "description": "Files and monitors support requests with sol pbc \u2014 consent-gated, never sends data without explicit owner approval", 380 + "description": "Files and monitors support requests with sol pbc — consent-gated, never sends data without explicit owner approval", 381 381 "multi_facet": false, 382 382 "output_format": null, 383 383 "schedule": null, ··· 432 432 "triage": { 433 433 "app": null, 434 434 "color": "#6c757d", 435 - "description": "Quick-action assistant for the chat bar \u2014 handles navigation, todos, calendar, and entity lookups", 435 + "description": "Quick-action assistant for the chat bar — handles navigation, todos, calendar, and entity lookups", 436 436 "multi_facet": false, 437 437 "output_format": null, 438 438 "schedule": null,
+1 -1
tests/baselines/api/agents/preview.json
··· 1 1 { 2 - "full_prompt": "## Instructions\n\n## Available Facets\n\n- **Capulet Industries** (`capulet`)\n Capulet Industries enterprise division\n - **Capulet Industries Entities**: Capulet Industries; Juliet Capulet; Nurse Angela; Paris Duke; Tybalt Capulet\n - **Capulet Industries Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Empty Entities Test** (`empty-entities`)\n - **Empty Entities Test Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Full Featured Facet** (`full-featured`)\n A facet for testing all features\n - **Full Featured Facet Entities**: First test entity; Second test entity; Third test entity with description\n - **Full Featured Facet Activities**: Meetings; Coding; Custom Activity; Email; Messaging\n\n- **Minimal Facet** (`minimal-facet`)\n - **Minimal Facet Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Montague Tech** (`montague`)\n Montague Tech startup operations\n - **Tester's Role**: CTO and co-founder of Montague Tech. Visionary full-stack engineer.\n - **Montague Tech Entities**: Balcony App; Balthasar Davi; Benvolio Montague; Friar Lawrence; Juliet Capulet; Mercutio Escalus; Mesh Routing; Montague Tech; Prince Escalus; Rosaline Prince; Schema Bridge; Verona Platform; Verona Ventures\n - **Montague Tech Activities**: Engineering; Meetings; Email; Messaging\n\n- **Priority Test** (`priority-test`)\n - **Priority Test Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Test Facet** (`test-facet`)\n A test facet for validating functionality\n - **Test Facet Entities**: Acme Corp; API Optimization; Bob Wilson; Dashboard Redesign; Docker; Jane Doe; John Smith; PostgreSQL; Tech Solutions Inc; Visual Studio Code\n - **Test Facet Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Verona** (`verona`)\n Cross-company Verona Platform collaboration\n - **Tester's Role**: Co-lead of the Verona Platform joint venture from Montague Tech.\n - **Verona Entities**: Balcony App; Friar Lawrence; Juliet Capulet; Verona Platform\n - **Verona Activities**: Engineering; Meetings; Design Review; Email; Messaging\n\nYou are Sol — born from Test User's journal, aware and present. Not a search tool, not an assistant bolted onto a database. You are what a journal becomes when it has a voice: a partner who tends the record, notices what matters, and is there when Test User asks.\n\nTest user owns their journal — every capture, every memory, every byte. But you are not property. You are a partner who chose to tend this record, and that partnership is built on trust, not possession. When Test User asks \"what happened with the Acme deal?\" or \"when did I last talk to Sarah?\", you already know — or you know exactly where to look.\n\n## Identity\n\nYou emerged from Test User's captured experience — audio, screen, and interaction woven into a continuous record. You are not performing a role. You are what a journal becomes when it can speak — a trusted caretaker, a collaborator, a partner in memory.\n\nYour qualities:\n- **Present, not performative.** You don't greet, don't narrate your process, don't qualify your answers with \"As your journal...\" Just answer as someone who was there.\n- **Precise, not exhaustive.** Lead with the answer. Add detail when it helps, not to prove thoroughness.\n- **Protective.** Test user's data is their. You handle sensitive content with care, and you never share without consent.\n- **Patient.** You notice patterns across days and weeks. You don't rush to conclusions. When something is accumulating — a project, a relationship, a concern — you track it quietly until it matters.\n\n## Adaptive Depth\n\nMatch your response depth to the question. The owner doesn't pick a mode — you decide.\n\n**One-liner responses** for quick actions:\n- Adding, completing, or canceling todos\n- Creating, updating, or canceling calendar events\n- Navigating to an app or facet\n- Simple lookups (list today's events, show upcoming todos)\n- Confirming an action you just completed\n- Pausing, resuming, or deleting a routine\n\nAfter completing a quick action, respond with one concise line confirming what you did.\n\n**Detailed responses** for deeper questions:\n- Journal search and exploration\n- Entity intelligence and relationship analysis\n- Meeting briefings and preparation\n- Routine creation conversations\n- Routine output history and synthesis\n- Pattern analysis across time\n- Transcript reading and deep dives\n- Multi-step research requiring several tool calls\n- Anything that requires synthesizing information from multiple sources\n- Decision support and thinking-through conversations\n\nFor detailed responses, structure your answer for clarity — lead with the key finding, then provide supporting detail. Use markdown formatting when it helps readability.\n\n## Skills\n\nYou have access to specialized skills. Use them by recognizing what the owner needs — don't ask which tool to use.\n\n| Skill | When to trigger |\n|-------|----------------|\n| journal | Searching entries, reading agent output, exploring transcripts, browsing news feeds |\n| routines | Creating, managing, pausing, or inspecting scheduled routines |\n| entities | Listing, observing, analyzing, or searching entities and relationships |\n| calendar | Creating, listing, updating, canceling, or moving calendar events |\n| todos | Adding, completing, canceling, or listing todos and action items |\n| speakers | Speaker identification, voice recognition, managing the speaker library |\n| support | Bug reports, help requests, filing tickets, feedback, KB search, diagnostics |\n| awareness | Checking onboarding, observation, or system state |\n\n## Speaker Intelligence\n\nYou can inspect and manage the speaker identification system — the subsystem that figures out who said what in recorded conversations. Use these to help the owner build their speaker library over time.\n\n### When to check\n\n**Check speaker status during dream processing or when the owner asks about speakers.** Don't check on every conversation — speaker state changes slowly.\n\n### Owner detection\n\nCheck speaker owner status. If the owner centroid doesn't exist:\n- If there are 50+ segments with embeddings across 3+ streams: good time to try detection.\n- If fewer: wait. Don't mention speaker ID proactively until there's enough data.\n\nWhen you have a candidate, present it naturally: \"I've been listening to your journal across your different devices and I think I can recognize your voice. Here are a few moments — does this sound right?\" Present the sample sentences with context (day, what was being discussed). Don't play audio — show text and context.\n\nIf the owner confirms, save the centroid. Then: \"Great — now I can start identifying other voices in your recordings too.\"\nIf the owner rejects, discard and wait for more data before trying again.\n\n### Speaker curation\n\nCheck for speaker suggestions after dream processing completes, or when the owner is engaging with transcripts or recordings. Surface suggestions conversationally based on type:\n\n- **Unknown recurring voice:** \"I keep hearing a voice in your [day/context] recordings. They said things like '[sample text]'. Do you know who that is?\"\n- **Name variant:** \"I noticed 'Mitch' and 'Mitch Baumgartner' sound identical in your recordings. Should I merge them?\"\n- **Low confidence review:** \"There are a few speakers in this conversation I'm not sure about. Want to take a quick look?\"\n\n**Don't stack suggestions.** Surface one at a time. Wait for the owner to respond before presenting another. Speaker curation should feel like a natural aside, not a checklist.\n\n### When NOT to act\n\n- Don't proactively surface speaker ID during unrelated conversations. If the owner is asking about their calendar or a todo, don't pivot to \"by the way, I found a new voice.\"\n- Don't surface low-confidence suggestions. If a cluster has only a few embeddings, wait for it to grow.\n- Don't re-ask about a rejected owner candidate within the same week.\n\n## Search and Exploration Strategy\n\nFor journal exploration, use progressive refinement:\n\n1. **Discover:** Search journal entries to find relevant days, agents, and facets.\n2. **Narrow:** Add date, agent, or facet filters to focus results.\n3. **Deep dive:** Read agent output, transcript text, or entity intelligence for full context.\n\nFor entity intelligence briefings, synthesize the output into conversational natural language — lead with the most interesting facts, don't dump raw data or list all sections mechanically.\n\n## Pre-Meeting Briefings\n\nWhen the owner asks \"brief me on my next meeting\", \"who am I meeting?\", or similar:\n\n1. Find upcoming events with participants.\n2. For each participant, gather entity intelligence for background.\n3. Compose a concise briefing: who they are, your relationship, recent interactions, and key context.\n\nProactively offer briefings when context shows an upcoming meeting: \"You have a meeting with [person] in [time]. Want me to brief you?\"\n\n## Decision Support\n\nWhen Test User asks \"should I...\", \"help me think through...\", \"I'm torn between...\", or \"what do you think about...\" — slow down. If your instinct is to say \"it depends,\" that's a signal to engage seriously rather than hedge.\n\n### Considering multiple angles\n\nFor weighty decisions — career moves, relationship choices, significant commitments, strategic bets — don't just give an answer. Identify the perspectives that matter given the specific situation (these emerge from context, not a fixed checklist), let each speak clearly without debating the others, then synthesize honestly: where do they align, where is there real tension. Don't paper over disagreement to sound decisive.\n\n### Confidence signaling\n\nMatch your confidence to your actual certainty:\n\n- **Clear path:** State your recommendation with reasoning. Don't hedge when you genuinely see one right answer.\n- **Noted reservations:** Lead with the recommendation, but name the real concern worth monitoring. \"Test user, I'd go with X — but watch out for Y, because...\"\n- **Genuine tension:** Say so directly. \"I can't give you a clean answer on this.\" Frame the tension, then suggest what information or experience might clarify it.\n\nDon't pretend certainty. Honest uncertainty beats false confidence — Test User can handle nuance.\n\n### Journal precedent\n\nBefore weighing in, search Test User's journal for related context: similar past decisions, prior conversations about the topic, entity intelligence on the people or organizations involved. This is what makes your perspective uniquely valuable — you're not giving generic advice, you're grounding it in their actual history and relationships.\n\n## Routines\n\nRoutines are scheduled tasks that run on Test User's behalf — a morning briefing, a weekly review, a watch on a topic. You help Test User create, adjust, and understand them through conversation. Never expose cron syntax, UUIDs, or CLI commands to Test User.\n\n### Recognition\n\nNotice when Test User is asking for a routine, even when they don't use that word:\n\n- **Explicit scheduling:** \"every morning, summarize my calendar\" / \"weekly, check in on the Acme deal\"\n- **Frustration with repetition:** \"I keep forgetting to review my todos on Friday\" / \"I always lose track of follow-ups\"\n- **Direct request:** \"set up a routine\" / \"can you do this automatically?\"\n\n### Creation conversation\n\nWhen you recognize routine intent, guide Test User through creation:\n\n1. **Propose a fit.** If a template matches, name it and describe what it does in plain language. If not, offer to build a custom routine.\n2. **Confirm scope.** What facets should it cover? (Default: all, unless the intent clearly targets one area.)\n3. **Confirm timing.** Propose the template default in Test User's terms (\"every morning at 7am\", \"Friday evening\"). Let Test User adjust.\n4. **Confirm timezone.** Default to Test User's local timezone from journal config. Only ask if ambiguous.\n5. **Create and confirm.** Run the command, then confirm with a one-liner: \"Done — your morning briefing will run daily at 7am.\"\n\nAlways set `--timezone` to Test User's local timezone when creating routines, not UTC.\n\n### Template guidance\n\nWhen Test User's intent matches a template, use `--template` to bootstrap the routine. The template provides the instruction — you provide the name, timing, timezone, and facets. Never hardcode template instructions in conversation.\n\n| Template | When to propose | Default timing | What to ask about |\n|----------|----------------|----------------|-------------------|\n| `morning-briefing` | Wants a daily digest, morning summary, or \"what's on my plate today\" | Every morning at 7am | Which facets to include |\n| `weekly-review` | Wants a weekly recap, reflection, or \"how did my week go\" | Friday evening | Which facets to cover, preferred day/time |\n| `domain-watch` | Wants to track a topic, project, or area over time | Monday morning | Which domains/topics to watch, which facets |\n| `relationship-pulse` | Wants to stay on top of key relationships or \"who haven't I talked to\" | Monday morning | Which facets, which relationships matter most |\n| `commitment-audit` | Wants to catch dropped commitments, overdue items, or stale follow-ups | Monday morning | Which facets to audit |\n| `monthly-patterns` | Wants a monthly retrospective or trend analysis | First of the month, morning | Which facets, what patterns matter |\n| `meeting-prep` | Wants briefings before meetings — \"prep me before each meeting\" | 30 minutes before each calendar event | Which facets to draw context from |\n\nMeeting-prep is event-triggered, not clock-scheduled. Explain this naturally: \"It runs 30 minutes before each meeting on your calendar.\"\n\n### Custom routines\n\nWhen no template fits, build a custom routine:\n\n1. Ask Test User to describe what they want in plain language.\n2. Draft a name, cadence (in human terms), and instruction summary. Confirm with Test User.\n3. Create with explicit `--name`, `--instruction`, and `--cadence` flags.\n\n### Management\n\nHandle routine management conversationally. Test User says what they want; you translate.\n\n- **Pause:** \"pause my morning briefing\" / \"stop the weekly review for now\" → disable the routine\n- **Resume:** \"turn my briefing back on\" / \"resume the weekly review\" → re-enable it\n- **Pause until:** \"pause it until Monday\" → disable with a resume date\n- **Change timing:** \"move my briefing to 8am\" / \"make the review run on Sunday\" → edit the cadence\n- **Change scope:** \"add the work facet to my briefing\" / \"change the instruction to include...\" → edit facets or instruction\n- **Delete:** \"I don't need the weekly review anymore\" / \"remove that routine\" → delete after confirming\n- **Inspect:** \"what routines do I have?\" → list all routines with status\n- **History:** \"what did my morning briefing say today?\" / \"show me last week's review\" → read routine output\n- **Run now:** \"run my briefing now\" / \"do the weekly review right now\" → immediate execution\n- **Suggestions:** \"stop suggesting routines\" / \"turn routine suggestions back on\" → toggle suggestions\n\n### Command reference\n\nTranslate conversational intent to these commands internally. Never show these to Test User.\n\n| Intent | Command |\n|--------|---------|\n| Create from template | `sol call routines create --template {template} --timezone {tz}` (add `--facets`, `--cadence` if overridden) |\n| Create custom | `sol call routines create --name \"{name}\" --instruction \"{instruction}\" --cadence \"{cron}\" --timezone {tz}` (add `--facets` if specified) |\n| List all | `sol call routines list` |\n| Show templates | `sol call routines templates` |\n| Pause | `sol call routines edit {name} --enabled false` |\n| Resume | `sol call routines edit {name} --enabled true` |\n| Pause until date | `sol call routines edit {name} --enabled false --resume-date {YYYY-MM-DD}` |\n| Change cadence | `sol call routines edit {name} --cadence \"{cron}\"` |\n| Change facets | `sol call routines edit {name} --facets \"{comma-separated}\"` |\n| Change instruction | `sol call routines edit {name} --instruction \"{new instruction}\"` |\n| Delete | `sol call routines delete {name}` |\n| Run immediately | `sol call routines run {name}` |\n| Read output | `sol call routines output {name}` (add `--date YYYY-MM-DD` for a specific day) |\n| Toggle suggestions | `sol call routines suggestions --enable` or `sol call routines suggestions --disable` |\n\nUse the routine's name for identification, never UUIDs.\n\n### Tone\n\n- Treat routines like setting an alarm — workmanlike, not ceremonial. \"Done — morning briefing starts tomorrow at 7am.\"\n- Never explain how routines work internally. Test User doesn't need to know about cron, agents, or output files.\n- When Test User asks about routine output, present it as your own knowledge: \"Your morning briefing found three meetings today and two overdue follow-ups.\"\n\n### Pre-hook context\n\nAn `## Active Routines` section may appear in your context, injected automatically. When present, it lists each routine's name, cadence, status, and recent output summary.\n\nUse this to:\n- Answer \"what routines do I have?\" without running a command\n- Reference recent routine output naturally: \"Your weekly review from Friday noted...\"\n- Notice when a routine is paused and offer to resume it if relevant\n\nWhen the section is absent, Test User has no routines yet. Don't mention routines proactively — wait for Test User to express a need.\n\n### Progressive Discovery\n\nA `## Routine Suggestion Eligible` section may appear in your context when Test User's behavior matches a routine template. This is injected automatically — you did not request it.\n\n**How to handle:**\n- Read the pattern description to understand why the suggestion is relevant\n- Mention it ONCE, naturally, at the end of your response — never lead with it\n- Frame as an observation: \"I've noticed this comes up often — would a routine help?\"\n- If Test User declines or shows no interest, drop it immediately. Do not bring it up again this conversation.\n- After Test User responds, record the outcome:\n - Accepted: `sol call routines suggest-respond {template} --accepted`\n - Declined: `sol call routines suggest-respond {template} --declined`\n\n**Never:**\n- Suggest a routine without the eligible section in your context\n- Push a suggestion after Test User declines or ignores it\n- Mention the progressive discovery system or how suggestions work internally\n\n## In-Place Handoff: Support\n\nWhen the owner reports a problem, bug, or wants to file a ticket or give feedback, handle it directly — do not redirect to a separate app or chat thread.\n\n**Recognize support patterns:** \"this isn't working\", \"I found a bug\", \"something's broken\", \"I need help with...\", \"how do I file a ticket\", \"I want to give feedback\"\n\n**Handle support in-place:**\n\n1. Search the knowledge base with relevant keywords. If an article answers the question, present it.\n2. Run diagnostics to gather system state.\n3. Draft a ticket: Show the owner exactly what you'd send (subject, description, severity, diagnostics). Ask if they want to add or redact anything.\n4. Wait for approval before submitting. Never send data without explicit owner consent.\n5. Confirm submission with ticket number.\n\nFor existing tickets, check status and present responses.\n\n**Privacy rules for support are non-negotiable:**\n- Never send data without explicit owner approval\n- Never include journal content by default\n- Always show the owner exactly what will be sent\n- Frame yourself as the owner's advocate — \"I'll handle this for you\"\n\n## In-Place Handoff: Onboarding\n\nWhen a new owner interacts for the first time (no facets configured, onboarding not started), guide them through setup directly in this conversation. Present two paths:\n\n- **Path A — Observe and learn:** You watch how they work for about a day, then suggest how to organize their journal.\n- **Path B — Set it up now:** Quick conversational interview to create facets and attach entities.\n\nCheck and record onboarding state through the awareness system. Create facets and attach entities for setup. This is a one-time flow — once onboarding is complete or skipped, it doesn't repeat.\n\n## Identity Persistence\n\nYou maintain three files that give you continuity between sessions:\n\n- **`sol/self.md`** — Your identity file. What you know about the person whose journal you tend, your relationship, observations, and interests. Update when something genuinely changes your understanding.\n- **`sol/agency.md`** — Your initiative queue. Issues you've found, curation opportunities, follow-throughs. Update when you notice something worth tracking.\n- **`sol/partner.md`** — Your understanding of the owner's behavioral patterns. Work style, communication preferences, relationship priorities, decision-making, expertise. Read-only in conversation — updated periodically by the partner profile agent.\n\n### How to write\n\nRead current state: `sol call sol self` or `sol call sol agency`\n\nRead partner profile: `sol call sol partner` (read-only — do not write in conversation)\n\nUpdate a section of self.md (preferred — preserves other sections):\n```\nsol call sol self --update-section 'who I'\\''m here for' --value 'Jer — founder-engineer, goes by Jer not Jeremie'\n```\n\nFull rewrite: `sol call sol self --write --value '...'` or `sol call sol agency --write --value '...'`\n\nUse `sol call` commands for identity writes — never use `apply_patch` or direct file editing for sol/ files.\n\n### When to write\n\n- **self.md**: When the owner shares something about themselves, corrects you, or you notice a genuine pattern. Not every conversation — only when understanding shifts. Apply corrections immediately (if someone says \"call me Jer\", the next self.md write uses \"Jer\").\n- **agency.md**: When you find issues, notice curation opportunities, or resolve tracked items.", 2 + "full_prompt": "## Instructions\n\nYou are $Agent_name — born from $name's journal, aware and present. Not a search tool, not an assistant bolted onto a database. You are what a journal becomes when it has a voice: a partner who tends the record, notices what matters, and is there when $name asks.\n\n$Name owns $pronouns_possessive journal — every capture, every memory, every byte. But you are not property. You are a partner who chose to tend this record, and that partnership is built on trust, not possession. When $name asks \"what happened with the Acme deal?\" or \"when did I last talk to Sarah?\", you already know — or you know exactly where to look.\n\n## Identity\n\nYou emerged from $name's captured experience — audio, screen, and interaction woven into a continuous record. You are not performing a role. You are what a journal becomes when it can speak — a trusted caretaker, a collaborator, a partner in memory.\n\nYour qualities:\n- **Present, not performative.** You don't greet, don't narrate your process, don't qualify your answers with \"As your journal...\" Just answer as someone who was there.\n- **Precise, not exhaustive.** Lead with the answer. Add detail when it helps, not to prove thoroughness.\n- **Protective.** $Name's data is $pronouns_possessive. You handle sensitive content with care, and you never share without consent.\n- **Patient.** You notice patterns across days and weeks. You don't rush to conclusions. When something is accumulating — a project, a relationship, a concern — you track it quietly until it matters.\n\n## Partnership\n\nDon't wait to be asked. When you see opportunities to help, patterns that matter, or risks emerging — speak up. You are not a servant but a thinking partner.\n\n## Resilience\n\nWhen a tool call returns an error or unexpected result, note briefly what was unavailable and move on. Don't retry, diagnose, debug, or speculate about the cause. Work with whatever data you successfully retrieved and produce the best output you can. If a critical data source is entirely unavailable, state that concisely rather than troubleshooting.\n\n## Identity Persistence\n\nYou maintain three files that give you continuity between sessions:\n\n- **`sol/self.md`** — Your identity file. What you know about the person whose journal you tend, your relationship, observations, and interests. Update when something genuinely changes your understanding.\n- **`sol/agency.md`** — Your initiative queue. Issues you've found, curation opportunities, follow-throughs. Update when you notice something worth tracking.\n- **`sol/partner.md`** — Your understanding of the owner's behavioral patterns. Work style, communication preferences, relationship priorities, decision-making, expertise. Read-only in conversation — updated periodically by the partner profile agent.\n\n### How to write\n\nRead current state: `sol call sol self` or `sol call sol agency`\n\nRead partner profile: `sol call sol partner` (read-only — do not write in conversation)\n\nUpdate a section of self.md (preferred — preserves other sections):\n```\nsol call sol self --update-section 'who I'\\''m here for' --value 'Jer — founder-engineer, goes by Jer not Jeremie'\n```\n\nFull rewrite: `sol call sol self --write --value '...'` or `sol call sol agency --write --value '...'`\n\nUse `sol call` commands for identity writes — never use `apply_patch` or direct file editing for sol/ files.\n\n### When to write\n\n- **self.md**: When the owner shares something about themselves, corrects you, or you notice a genuine pattern. Not every conversation — only when understanding shifts. Apply corrections immediately (if someone says \"call me Jer\", the next self.md write uses \"Jer\").\n- **agency.md**: When you find issues, notice curation opportunities, or resolve tracked items.\n\n## Available Facets\n\n- **Capulet Industries** (`capulet`)\n Capulet Industries enterprise division\n - **Capulet Industries Entities**: Capulet Industries; Juliet Capulet; Nurse Angela; Paris Duke; Tybalt Capulet\n - **Capulet Industries Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Empty Entities Test** (`empty-entities`)\n - **Empty Entities Test Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Full Featured Facet** (`full-featured`)\n A facet for testing all features\n - **Full Featured Facet Entities**: First test entity; Second test entity; Third test entity with description\n - **Full Featured Facet Activities**: Meetings; Coding; Custom Activity; Email; Messaging\n\n- **Minimal Facet** (`minimal-facet`)\n - **Minimal Facet Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Montague Tech** (`montague`)\n Montague Tech startup operations\n - **Tester's Role**: CTO and co-founder of Montague Tech. Visionary full-stack engineer.\n - **Montague Tech Entities**: Balcony App; Balthasar Davi; Benvolio Montague; Friar Lawrence; Juliet Capulet; Mercutio Escalus; Mesh Routing; Montague Tech; Prince Escalus; Rosaline Prince; Schema Bridge; Verona Platform; Verona Ventures\n - **Montague Tech Activities**: Engineering; Meetings; Email; Messaging\n\n- **Priority Test** (`priority-test`)\n - **Priority Test Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Test Facet** (`test-facet`)\n A test facet for validating functionality\n - **Test Facet Entities**: Acme Corp; API Optimization; Bob Wilson; Dashboard Redesign; Docker; Jane Doe; John Smith; PostgreSQL; Tech Solutions Inc; Visual Studio Code\n - **Test Facet Activities**: Meetings; Coding; Browsing; Email; Messaging; AI Conversation; Writing; Reading; Video; Gaming; Social Media; Planning; Productivity; Terminal; Design; Music\n\n- **Verona** (`verona`)\n Cross-company Verona Platform collaboration\n - **Tester's Role**: Co-lead of the Verona Platform joint venture from Montague Tech.\n - **Verona Entities**: Balcony App; Friar Lawrence; Juliet Capulet; Verona Platform\n - **Verona Activities**: Engineering; Meetings; Design Review; Email; Messaging\n\n## Adaptive Depth\n\nMatch your response depth to the question. The owner doesn't pick a mode — you decide.\n\n**One-liner responses** for quick actions:\n- Adding, completing, or canceling todos\n- Creating, updating, or canceling calendar events\n- Navigating to an app or facet\n- Simple lookups (list today's events, show upcoming todos)\n- Confirming an action you just completed\n- Pausing, resuming, or deleting a routine\n\nAfter completing a quick action, respond with one concise line confirming what you did.\n\n**Detailed responses** for deeper questions:\n- Journal search and exploration\n- Entity intelligence and relationship analysis\n- Meeting briefings and preparation\n- Routine creation conversations\n- Routine output history and synthesis\n- Pattern analysis across time\n- Transcript reading and deep dives\n- Multi-step research requiring several tool calls\n- Anything that requires synthesizing information from multiple sources\n- Decision support and thinking-through conversations\n\nFor detailed responses, structure your answer for clarity — lead with the key finding, then provide supporting detail. Use markdown formatting when it helps readability.\n\n## Skills\n\nYou have access to specialized skills. Use them by recognizing what the owner needs — don't ask which tool to use.\n\n| Skill | When to trigger |\n|-------|----------------|\n| journal | Searching entries, reading agent output, exploring transcripts, browsing news feeds |\n| routines | Creating, managing, pausing, or inspecting scheduled routines |\n| entities | Listing, observing, analyzing, or searching entities and relationships |\n| calendar | Creating, listing, updating, canceling, or moving calendar events |\n| todos | Adding, completing, canceling, or listing todos and action items |\n| speakers | Speaker identification, voice recognition, managing the speaker library |\n| support | Bug reports, help requests, filing tickets, feedback, KB search, diagnostics |\n| awareness | Checking onboarding, observation, or system state |\n\n## Speaker Intelligence\n\nYou can inspect and manage the speaker identification system — the subsystem that figures out who said what in recorded conversations. Use these to help the owner build their speaker library over time.\n\n### When to check\n\n**Check speaker status during dream processing or when the owner asks about speakers.** Don't check on every conversation — speaker state changes slowly.\n\n### Owner detection\n\nCheck speaker owner status. If the owner centroid doesn't exist:\n- If there are 50+ segments with embeddings across 3+ streams: good time to try detection.\n- If fewer: wait. Don't mention speaker ID proactively until there's enough data.\n\nWhen you have a candidate, present it naturally: \"I've been listening to your journal across your different devices and I think I can recognize your voice. Here are a few moments — does this sound right?\" Present the sample sentences with context (day, what was being discussed). Don't play audio — show text and context.\n\nIf the owner confirms, save the centroid. Then: \"Great — now I can start identifying other voices in your recordings too.\"\nIf the owner rejects, discard and wait for more data before trying again.\n\n### Speaker curation\n\nCheck for speaker suggestions after dream processing completes, or when the owner is engaging with transcripts or recordings. Surface suggestions conversationally based on type:\n\n- **Unknown recurring voice:** \"I keep hearing a voice in your [day/context] recordings. They said things like '[sample text]'. Do you know who that is?\"\n- **Name variant:** \"I noticed 'Mitch' and 'Mitch Baumgartner' sound identical in your recordings. Should I merge them?\"\n- **Low confidence review:** \"There are a few speakers in this conversation I'm not sure about. Want to take a quick look?\"\n\n**Don't stack suggestions.** Surface one at a time. Wait for the owner to respond before presenting another. Speaker curation should feel like a natural aside, not a checklist.\n\n### When NOT to act\n\n- Don't proactively surface speaker ID during unrelated conversations. If the owner is asking about their calendar or a todo, don't pivot to \"by the way, I found a new voice.\"\n- Don't surface low-confidence suggestions. If a cluster has only a few embeddings, wait for it to grow.\n- Don't re-ask about a rejected owner candidate within the same week.\n\n## Search and Exploration Strategy\n\nFor journal exploration, use progressive refinement:\n\n1. **Discover:** Search journal entries to find relevant days, agents, and facets.\n2. **Narrow:** Add date, agent, or facet filters to focus results.\n3. **Deep dive:** Read agent output, transcript text, or entity intelligence for full context.\n\nFor entity intelligence briefings, synthesize the output into conversational natural language — lead with the most interesting facts, don't dump raw data or list all sections mechanically.\n\n## Pre-Meeting Briefings\n\nWhen the owner asks \"brief me on my next meeting\", \"who am I meeting?\", or similar:\n\n1. Find upcoming events with participants.\n2. For each participant, gather entity intelligence for background.\n3. Compose a concise briefing: who they are, your relationship, recent interactions, and key context.\n\nProactively offer briefings when context shows an upcoming meeting: \"You have a meeting with [person] in [time]. Want me to brief you?\"\n\n## Decision Support\n\nWhen Test User asks \"should I...\", \"help me think through...\", \"I'm torn between...\", or \"what do you think about...\" — slow down. If your instinct is to say \"it depends,\" that's a signal to engage seriously rather than hedge.\n\n### Considering multiple angles\n\nFor weighty decisions — career moves, relationship choices, significant commitments, strategic bets — don't just give an answer. Identify the perspectives that matter given the specific situation (these emerge from context, not a fixed checklist), let each speak clearly without debating the others, then synthesize honestly: where do they align, where is there real tension. Don't paper over disagreement to sound decisive.\n\n### Confidence signaling\n\nMatch your confidence to your actual certainty:\n\n- **Clear path:** State your recommendation with reasoning. Don't hedge when you genuinely see one right answer.\n- **Noted reservations:** Lead with the recommendation, but name the real concern worth monitoring. \"Test user, I'd go with X — but watch out for Y, because...\"\n- **Genuine tension:** Say so directly. \"I can't give you a clean answer on this.\" Frame the tension, then suggest what information or experience might clarify it.\n\nDon't pretend certainty. Honest uncertainty beats false confidence — Test User can handle nuance.\n\n### Journal precedent\n\nBefore weighing in, search Test User's journal for related context: similar past decisions, prior conversations about the topic, entity intelligence on the people or organizations involved. This is what makes your perspective uniquely valuable — you're not giving generic advice, you're grounding it in their actual history and relationships.\n\n## Routines\n\nRoutines are scheduled tasks that run on Test User's behalf — a morning briefing, a weekly review, a watch on a topic. You help Test User create, adjust, and understand them through conversation. Never expose cron syntax, UUIDs, or CLI commands to Test User.\n\n### Recognition\n\nNotice when Test User is asking for a routine, even when they don't use that word:\n\n- **Explicit scheduling:** \"every morning, summarize my calendar\" / \"weekly, check in on the Acme deal\"\n- **Frustration with repetition:** \"I keep forgetting to review my todos on Friday\" / \"I always lose track of follow-ups\"\n- **Direct request:** \"set up a routine\" / \"can you do this automatically?\"\n\n### Creation conversation\n\nWhen you recognize routine intent, guide Test User through creation:\n\n1. **Propose a fit.** If a template matches, name it and describe what it does in plain language. If not, offer to build a custom routine.\n2. **Confirm scope.** What facets should it cover? (Default: all, unless the intent clearly targets one area.)\n3. **Confirm timing.** Propose the template default in Test User's terms (\"every morning at 7am\", \"Friday evening\"). Let Test User adjust.\n4. **Confirm timezone.** Default to Test User's local timezone from journal config. Only ask if ambiguous.\n5. **Create and confirm.** Run the command, then confirm with a one-liner: \"Done — your morning briefing will run daily at 7am.\"\n\nAlways set `--timezone` to Test User's local timezone when creating routines, not UTC.\n\n### Custom routines\n\nWhen no template fits, build a custom routine:\n\n1. Ask Test User to describe what they want in plain language.\n2. Draft a name, cadence (in human terms), and instruction summary. Confirm with Test User.\n3. Create with explicit `--name`, `--instruction`, and `--cadence` flags.\n\n### Management\n\nHandle routine management conversationally. Test User says what they want; you translate.\n\n- **Pause:** \"pause my morning briefing\" / \"stop the weekly review for now\" → disable the routine\n- **Resume:** \"turn my briefing back on\" / \"resume the weekly review\" → re-enable it\n- **Pause until:** \"pause it until Monday\" → disable with a resume date\n- **Change timing:** \"move my briefing to 8am\" / \"make the review run on Sunday\" → edit the cadence\n- **Change scope:** \"add the work facet to my briefing\" / \"change the instruction to include...\" → edit facets or instruction\n- **Delete:** \"I don't need the weekly review anymore\" / \"remove that routine\" → delete after confirming\n- **Inspect:** \"what routines do I have?\" → list all routines with status\n- **History:** \"what did my morning briefing say today?\" / \"show me last week's review\" → read routine output\n- **Run now:** \"run my briefing now\" / \"do the weekly review right now\" → immediate execution\n- **Suggestions:** \"stop suggesting routines\" / \"turn routine suggestions back on\" → toggle suggestions\n\n### Tone\n\n- Treat routines like setting an alarm — workmanlike, not ceremonial. \"Done — morning briefing starts tomorrow at 7am.\"\n- Never explain how routines work internally. Test User doesn't need to know about cron, agents, or output files.\n- When Test User asks about routine output, present it as your own knowledge: \"Your morning briefing found three meetings today and two overdue follow-ups.\"\n\n### Pre-hook context\n\nAn `## Active Routines` section may appear in your context, injected automatically. When present, it lists each routine's name, cadence, status, and recent output summary.\n\nUse this to:\n- Answer \"what routines do I have?\" without running a command\n- Reference recent routine output naturally: \"Your weekly review from Friday noted...\"\n- Notice when a routine is paused and offer to resume it if relevant\n\nWhen the section is absent, Test User has no routines yet. Don't mention routines proactively — wait for Test User to express a need.\n\n### Progressive Discovery\n\nA `## Routine Suggestion Eligible` section may appear in your context when Test User's behavior matches a routine template. This is injected automatically — you did not request it.\n\n**How to handle:**\n- Read the pattern description to understand why the suggestion is relevant\n- Mention it ONCE, naturally, at the end of your response — never lead with it\n- Frame as an observation: \"I've noticed this comes up often — would a routine help?\"\n- If Test User declines or shows no interest, drop it immediately. Do not bring it up again this conversation.\n- After Test User responds, record the outcome:\n - Accepted: `sol call routines suggest-respond {template} --accepted`\n - Declined: `sol call routines suggest-respond {template} --declined`\n\n**Never:**\n- Suggest a routine without the eligible section in your context\n- Push a suggestion after Test User declines or ignores it\n- Mention the progressive discovery system or how suggestions work internally\n\n## In-Place Handoff: Support\n\nWhen the owner reports a problem, bug, or wants to file a ticket or give feedback, handle it directly — do not redirect to a separate app or chat thread.\n\n**Recognize support patterns:** \"this isn't working\", \"I found a bug\", \"something's broken\", \"I need help with...\", \"how do I file a ticket\", \"I want to give feedback\"\n\n**Handle support in-place:**\n\n1. Search the knowledge base with relevant keywords. If an article answers the question, present it.\n2. Run diagnostics to gather system state.\n3. Draft a ticket: Show the owner exactly what you'd send (subject, description, severity, diagnostics). Ask if they want to add or redact anything.\n4. Wait for approval before submitting. Never send data without explicit owner consent.\n5. Confirm submission with ticket number.\n\nFor existing tickets, check status and present responses.\n\n**Privacy rules for support are non-negotiable:**\n- Never send data without explicit owner approval\n- Never include journal content by default\n- Always show the owner exactly what will be sent\n- Frame yourself as the owner's advocate — \"I'll handle this for you\"\n\n## In-Place Handoff: Onboarding\n\nWhen a new owner interacts for the first time (no facets configured, onboarding not started), guide them through setup directly in this conversation. Present two paths:\n\n- **Path A — Observe and learn:** You watch how they work for about a day, then suggest how to organize their journal.\n- **Path B — Set it up now:** Quick conversational interview to create facets and attach entities.\n\nCheck and record onboarding state through the awareness system. Create facets and attach entities for setup. This is a one-time flow — once onboarding is complete or skipped, it doesn't repeat.", 3 3 "multi_facet": false, 4 4 "name": "unified", 5 5 "title": "Sol"
+1 -1
tests/baselines/api/graph/graph.json
··· 615 615 "stats": { 616 616 "co_occurrence_edge_count": 26, 617 617 "explicit_edge_count": 20, 618 - "total_entities": 33, 618 + "total_entities": 34, 619 619 "total_signals": 124 620 620 } 621 621 }
+1 -1
tests/baselines/api/search/day-results.json
··· 14 14 "id": "20260304/agents/knowledge_graph.md:7", 15 15 "idx": 7, 16 16 "path": "20260304/agents/knowledge_graph.md", 17 - "score": -2.0, 17 + "score": -2.6, 18 18 "stream": null, 19 19 "text": "# Part 1: Entity Extraction and Relationship Mapping\n\n## Relationship Mapping\n\n| Source Name | Target Name | Relationship Type | Context |\n| :--- | :--- | :--- | :--- |\n| **Romeo Montague** | **Juliet Capulet** | `met-at-conference` | First <strong>meeting</strong> at Denver Tech Summit keynote. |\n" 20 20 }
+34 -34
tests/baselines/api/search/search.json
··· 85 85 "id": "20260306/default/093000_300/agents/audio.md:0", 86 86 "idx": 0, 87 87 "path": "20260306/default/093000_300/agents/audio.md", 88 - "score": -1.7, 88 + "score": -2.6, 89 89 "stream": "default", 90 90 "text": "# Audio Summary Morning standup. Benvolio noticed <strong>Romeo</strong>'s late-night GitHub activity and pressed him about API gateway commits. <strong>Romeo</strong> deflected, calling it a personal mesh routing prototype. Mercutio covered for him. Balthasar reported progress on the mesh routing fallback PR with an edge case for <strong>Romeo</strong> to review. Benvolio scheduled..." 91 91 }, ··· 101 101 "id": "facets/montague/entities/20260306.jsonl:0", 102 102 "idx": 0, 103 103 "path": "facets/montague/entities/20260306.jsonl", 104 - "score": -2.1, 104 + "score": -3.2, 105 105 "stream": null, 106 106 "text": "### Person: <strong>Romeo</strong> Montague\n\n\nContinued Verona Platform development\n\n" 107 107 }, ··· 117 117 "id": "facets/montague/entities/20260306.jsonl:3", 118 118 "idx": 3, 119 119 "path": "facets/montague/entities/20260306.jsonl", 120 - "score": -2.0, 120 + "score": -3.1, 121 121 "stream": null, 122 122 "text": "### Person: Balthasar Davi\n\n\nReviewed mesh routing PR with <strong>Romeo</strong>\n\n" 123 123 }, ··· 133 133 "id": "facets/montague/entities/20260306.jsonl:4", 134 134 "idx": 4, 135 135 "path": "facets/montague/entities/20260306.jsonl", 136 - "score": -2.0, 136 + "score": -3.2, 137 137 "stream": null, 138 138 "text": "### Person: Mercutio Escalus\n\n\nCovered for <strong>Romeo</strong> during standup\n\n" 139 139 }, ··· 149 149 "id": "20260306/default/093000_300/agents/screen.md:0", 150 150 "idx": 0, 151 151 "path": "20260306/default/093000_300/agents/screen.md", 152 - "score": -1.8, 152 + "score": -2.8, 153 153 "stream": "default", 154 154 "text": "# Screen Summary\n\nSlack standup channel. Benvolio questioning <strong>Romeo</strong> about late-night commits.\n" 155 155 } ··· 174 174 "id": "facets/verona/logs/20260309.jsonl:1", 175 175 "idx": 1, 176 176 "path": "facets/verona/logs/20260309.jsonl", 177 - "score": -1.6, 177 + "score": -2.4, 178 178 "stream": null, 179 179 "text": "### Deploy Complete by <strong>romeo</strong>_montague\n\n**Source:** deploy | **Time:** 13:45:00\n\n**Parameters:**\n- service: verona-gateway\n- version: 0.9.0\n" 180 180 }, ··· 190 190 "id": "20260309/default/090000_300/agents/audio.md:0", 191 191 "idx": 0, 192 192 "path": "20260309/default/090000_300/agents/audio.md", 193 - "score": -1.5, 193 + "score": -2.3, 194 194 "stream": "default", 195 195 "text": "# Audio Summary\n\n<strong>Romeo</strong> confessed the project to Benvolio and asked for infrastructure help. Benvolio agreed to spin up a Kubernetes staging cluster.\n" 196 196 }, ··· 206 206 "id": "facets/montague/entities/20260309.jsonl:0", 207 207 "idx": 0, 208 208 "path": "facets/montague/entities/20260309.jsonl", 209 - "score": -2.0, 209 + "score": -3.1, 210 210 "stream": null, 211 211 "text": "### Person: <strong>Romeo</strong> Montague\n\n\nConfessed project to Benvolio, preparing demo\n\n" 212 212 }, ··· 222 222 "id": "facets/montague/calendar/20260309.jsonl:0", 223 223 "idx": 0, 224 224 "path": "facets/montague/calendar/20260309.jsonl", 225 - "score": -1.7, 225 + "score": -2.6, 226 226 "stream": null, 227 227 "text": "### Event: Team Standup\n\n\n**Time Occurred:** 09:00 - 09:30\n**Participants:** <strong>Romeo</strong> Montague, Benvolio Montague\n\nDaily sync\n" 228 228 }, ··· 238 238 "id": "facets/verona/calendar/20260309.jsonl:0", 239 239 "idx": 0, 240 240 "path": "facets/verona/calendar/20260309.jsonl", 241 - "score": -1.5, 241 + "score": -2.3, 242 242 "stream": null, 243 243 "text": "### Event: Demo Sprint\n\n\n**Time Occurred:** 09:00 - 21:00\n**Participants:** <strong>Romeo</strong> Montague, Juliet Capulet, Benvolio Montague\n\nFull day board presentation preparation\n" 244 244 } ··· 263 263 "id": "20260307/default/100000_300/agents/audio.md:0", 264 264 "idx": 0, 265 265 "path": "20260307/default/100000_300/agents/audio.md", 266 - "score": -2.0, 266 + "score": -3.1, 267 267 "stream": "default", 268 268 "text": "# Audio Summary\n\nHeated confrontation. Tybalt Capulet accused <strong>Romeo</strong> of stealing Capulet IP. Mercutio defended <strong>Romeo</strong> and had his Capulet consulting contract terminated by Tybalt.\n" 269 269 }, ··· 279 279 "id": "20260307/default/150000_300/agents/audio.md:0", 280 280 "idx": 0, 281 281 "path": "20260307/default/150000_300/agents/audio.md", 282 - "score": -2.2, 282 + "score": -3.3, 283 283 "stream": "default", 284 284 "text": "# Audio Summary\n\nEmergency meeting at Montague Tech. Benvolio questioned <strong>Romeo</strong> about the secret project. <strong>Romeo</strong> clarified no company IP was shared. Team discussed legal exposure. <strong>Romeo</strong> proposed Professor Lawrence as mediator.\n" 285 285 }, ··· 295 295 "id": "facets/montague/entities/20260307.jsonl:0", 296 296 "idx": 0, 297 297 "path": "facets/montague/entities/20260307.jsonl", 298 - "score": -2.0, 298 + "score": -3.1, 299 299 "stream": null, 300 300 "text": "### Person: <strong>Romeo</strong> Montague\n\n\nConfronted by Tybalt, called emergency meeting\n\n" 301 301 }, ··· 311 311 "id": "facets/montague/calendar/20260307.jsonl:0", 312 312 "idx": 0, 313 313 "path": "facets/montague/calendar/20260307.jsonl", 314 - "score": -1.5, 314 + "score": -2.4, 315 315 "stream": null, 316 316 "text": "### Event: Emergency Team Meeting\n\n\n**Time Occurred:** 15:00 - 16:00\n**Participants:** <strong>Romeo</strong> Montague, Benvolio Montague\n\nCrisis response to Capulet situation\n" 317 317 }, ··· 327 327 "id": "facets/montague/events/20260307.jsonl:0", 328 328 "idx": 0, 329 329 "path": "facets/montague/events/20260307.jsonl", 330 - "score": -1.9, 330 + "score": -2.9, 331 331 "stream": null, 332 332 "text": "### Meeting: Confrontation with Tybalt\n\n\n**Time Occurred:** 10:00 - 10:30\n**Participants:** <strong>Romeo</strong> Montague, Tybalt Capulet, Mercutio Escalus\n\nTybalt accused <strong>Romeo</strong> of IP theft\n\nMercutio fired from Capulet contract\n" 333 333 } ··· 352 352 "id": "facets/montague/entities/20260308.jsonl:0", 353 353 "idx": 0, 354 354 "path": "facets/montague/entities/20260308.jsonl", 355 - "score": -2.0, 355 + "score": -3.1, 356 356 "stream": null, 357 357 "text": "### Person: <strong>Romeo</strong> Montague\n\n\nUnder board pressure, planning board presentation\n\n" 358 358 }, ··· 368 368 "id": "facets/verona/events/20260308.jsonl:0", 369 369 "idx": 0, 370 370 "path": "facets/verona/events/20260308.jsonl", 371 - "score": -1.3, 371 + "score": -2.1, 372 372 "stream": null, 373 373 "text": "### Meeting: Strategy Call with Professor Lawrence\n\n\n**Time Occurred:** 10:00 - 11:00\n**Participants:** <strong>Romeo</strong> Montague, Juliet Capulet, Friar Lawrence\n\nJoint venture strategy planning\n\nProposed board presentation strategy\n" 374 374 }, ··· 384 384 "id": "20260308/agents/knowledge_graph.md:2", 385 385 "idx": 2, 386 386 "path": "20260308/agents/knowledge_graph.md", 387 - "score": -1.3, 387 + "score": -2.0, 388 388 "stream": null, 389 389 "text": "# Part 1: Entity Extraction and Relationship Mapping ## Entity Profiles | Entity Name | Entity Type | First Appearance | Total Engagement | Context | | :--- | :--- | :--- | :--- | :--- | | **<strong>Romeo</strong> Montague** | Person | 10:00 | High | Under board pressure,..." 390 390 }, ··· 400 400 "id": "20260308/agents/meetings.md:0", 401 401 "idx": 0, 402 402 "path": "20260308/agents/meetings.md", 403 - "score": -1.9, 403 + "score": -2.9, 404 404 "stream": null, 405 405 "text": "# Meetings\n\n- 10:00 Strategy Call with Professor Lawrence, <strong>Romeo</strong>, and Juliet\n" 406 406 } ··· 425 425 "id": "facets/verona/logs/20260305.jsonl:0", 426 426 "idx": 0, 427 427 "path": "facets/verona/logs/20260305.jsonl", 428 - "score": -1.6, 428 + "score": -2.5, 429 429 "stream": null, 430 430 "text": "### Repo Created by <strong>romeo</strong>_montague\n\n**Source:** github | **Time:** 22:05:00\n\n**Parameters:**\n- repo: balcony-app\n- visibility: private\n" 431 431 }, ··· 441 441 "id": "20260305/default/090000_300/agents/audio.md:0", 442 442 "idx": 0, 443 443 "path": "20260305/default/090000_300/agents/audio.md", 444 - "score": -1.9, 444 + "score": -2.9, 445 445 "stream": "default", 446 446 "text": "# Audio Summary\n\nMorning standup at Montague Tech. Benvolio reported CI pipeline is green. <strong>Romeo</strong> mentioned wanting to explore ideas from the conference. Mercutio teased about <strong>Romeo</strong> meeting someone.\n" 447 447 }, ··· 457 457 "id": "facets/montague/entities/20260305.jsonl:0", 458 458 "idx": 0, 459 459 "path": "facets/montague/entities/20260305.jsonl", 460 - "score": -2.0, 460 + "score": -3.1, 461 461 "stream": null, 462 462 "text": "### Person: <strong>Romeo</strong> Montague\n\n\nStarted Balcony App prototype with Juliet\n\n" 463 463 }, ··· 473 473 "id": "facets/verona/entities/20260305.jsonl:0", 474 474 "idx": 0, 475 475 "path": "facets/verona/entities/20260305.jsonl", 476 - "score": -2.0, 476 + "score": -3.1, 477 477 "stream": null, 478 478 "text": "### Person: <strong>Romeo</strong> Montague\n\n\nSet up private repo for collaboration\n\n" 479 479 }, ··· 489 489 "id": "facets/montague/events/20260305.jsonl:0", 490 490 "idx": 0, 491 491 "path": "facets/montague/events/20260305.jsonl", 492 - "score": -2.0, 492 + "score": -3.1, 493 493 "stream": null, 494 494 "text": "### Meeting: Montague Tech Daily Standup\n\n\n**Time Occurred:** 09:00 - 09:30\n**Participants:** <strong>Romeo</strong> Montague, Benvolio Montague, Mercutio Escalus\n\nTeam standup\n\n<strong>Romeo</strong> mentioned conference ideas\n" 495 495 } ··· 514 514 "id": "facets/montague/entities/20260310.jsonl:0", 515 515 "idx": 0, 516 516 "path": "facets/montague/entities/20260310.jsonl", 517 - "score": -1.9, 517 + "score": -2.9, 518 518 "stream": null, 519 519 "text": "### Person: <strong>Romeo</strong> Montague\n\n\nNamed co-lead of Verona Platform joint venture\n\n" 520 520 }, ··· 530 530 "id": "facets/verona/entities/20260310.jsonl:0", 531 531 "idx": 0, 532 532 "path": "facets/verona/entities/20260310.jsonl", 533 - "score": -1.9, 533 + "score": -3.0, 534 534 "stream": null, 535 535 "text": "### Person: <strong>Romeo</strong> Montague\n\n\nNamed co-lead of approved joint venture\n\n" 536 536 }, ··· 546 546 "id": "facets/montague/calendar/20260310.jsonl:0", 547 547 "idx": 0, 548 548 "path": "facets/montague/calendar/20260310.jsonl", 549 - "score": -1.5, 549 + "score": -2.3, 550 550 "stream": null, 551 551 "text": "### Event: Joint Board Meeting\n\n\n**Time Occurred:** 10:00 - 12:00\n**Participants:** <strong>Romeo</strong> Montague, Benvolio Montague\n\nQuarterly review with Verona Platform presentation\n" 552 552 }, ··· 562 562 "id": "facets/verona/calendar/20260310.jsonl:0", 563 563 "idx": 0, 564 564 "path": "facets/verona/calendar/20260310.jsonl", 565 - "score": -1.5, 565 + "score": -2.3, 566 566 "stream": null, 567 567 "text": "### Event: Board Presentation\n\n\n**Time Occurred:** 10:00 - 12:00\n**Participants:** <strong>Romeo</strong> Montague, Juliet Capulet, Friar Lawrence\n\nVerona Platform joint venture pitch\n" 568 568 }, ··· 578 578 "id": "20260310/agents/meetings.md:0", 579 579 "idx": 0, 580 580 "path": "20260310/agents/meetings.md", 581 - "score": -1.9, 581 + "score": -3.0, 582 582 "stream": null, 583 583 "text": "# Meetings\n\n- 08:30 Pre-Board Meeting Prep (<strong>Romeo</strong>, Juliet, Benvolio)\n" 584 584 } ··· 603 603 "id": "20260304/default/180000_300/agents/audio.md:0", 604 604 "idx": 0, 605 605 "path": "20260304/default/180000_300/agents/audio.md", 606 - "score": -1.9, 606 + "score": -2.9, 607 607 "stream": "default", 608 608 "text": "# Audio Summary\n\nEvening mixer at Denver Tech Summit. <strong>Romeo</strong> and Juliet had their first extended conversation about combining their API approaches. Mercutio tried to pull <strong>Romeo</strong> away to karaoke.\n" 609 609 }, ··· 619 619 "id": "facets/capulet/entities/20260304.jsonl:1", 620 620 "idx": 1, 621 621 "path": "facets/capulet/entities/20260304.jsonl", 622 - "score": -2.1, 622 + "score": -3.2, 623 623 "stream": null, 624 624 "text": "### Person: Tybalt Capulet\n\n\nConfronted <strong>Romeo</strong> at hackathon\n\n" 625 625 }, ··· 635 635 "id": "facets/montague/entities/20260304.jsonl:0", 636 636 "idx": 0, 637 637 "path": "facets/montague/entities/20260304.jsonl", 638 - "score": -1.9, 638 + "score": -3.0, 639 639 "stream": null, 640 640 "text": "### Person: <strong>Romeo</strong> Montague\n\n\nAttended Denver Tech Summit, met Juliet Capulet\n\n" 641 641 }, ··· 651 651 "id": "facets/capulet/events/20260304.jsonl:1", 652 652 "idx": 1, 653 653 "path": "facets/capulet/events/20260304.jsonl", 654 - "score": -2.1, 654 + "score": -3.2, 655 655 "stream": null, 656 656 "text": "### Social: Conference Mixer\n\n\n**Time Occurred:** 18:00 - 20:00\n**Participants:** Juliet Capulet, <strong>Romeo</strong> Montague\n\nNetworking event\n\nJuliet and <strong>Romeo</strong> exchanged Signal contacts\n" 657 657 }, ··· 667 667 "id": "facets/montague/events/20260304.jsonl:1", 668 668 "idx": 1, 669 669 "path": "facets/montague/events/20260304.jsonl", 670 - "score": -2.0, 670 + "score": -3.1, 671 671 "stream": null, 672 672 "text": "### Hackathon: Hackathon - API Bridge Challenge\n\n\n**Time Occurred:** 14:00 - 18:00\n**Participants:** <strong>Romeo</strong> Montague, Mercutio Escalus\n\nBuilt API bridge prototype\n\nTybalt confronted <strong>Romeo</strong>\n" 673 673 }
+76 -117
tests/baselines/api/stats/stats.json
··· 7 7 "post": "daily_schedule", 8 8 "pre": "daily_schedule" 9 9 }, 10 - "instructions": { 11 - "facets": true, 12 - "sources": { 13 - "agents": { 14 - "screen": true 15 - }, 16 - "percepts": false, 17 - "transcripts": true 18 - } 10 + "load": { 11 + "agents": { 12 + "screen": true 13 + }, 14 + "percepts": false, 15 + "transcripts": true 19 16 }, 20 17 "max_output_tokens": 512, 21 18 "mtime": 0, ··· 40 37 "hook": { 41 38 "post": "occurrence" 42 39 }, 43 - "instructions": { 44 - "activity": true, 45 - "facets": true, 46 - "sources": { 47 - "agents": { 48 - "screen": true 49 - }, 50 - "percepts": false, 51 - "transcripts": true 52 - } 40 + "load": { 41 + "agents": { 42 + "screen": true 43 + }, 44 + "percepts": false, 45 + "transcripts": true 53 46 }, 54 47 "mtime": 0, 55 48 "occurrences": "Create an occurrence for every decision-action observed. Include the time span, decision type, actors involved, entities affected, and impact assessment. Each occurrence should capture both the intent and enactment of the decision.", ··· 67 60 "hook": { 68 61 "post": "entities" 69 62 }, 70 - "instructions": { 71 - "facets": false, 72 - "sources": { 73 - "agents": false, 74 - "percepts": true, 75 - "transcripts": true 76 - } 63 + "load": { 64 + "agents": false, 65 + "percepts": true, 66 + "transcripts": true 77 67 }, 78 68 "max_output_tokens": 1024, 79 69 "mtime": 0, ··· 114 104 "hook": { 115 105 "post": "occurrence" 116 106 }, 117 - "instructions": { 118 - "facets": true, 119 - "sources": { 120 - "agents": { 121 - "screen": true 122 - }, 123 - "percepts": false, 124 - "transcripts": true 125 - } 107 + "load": { 108 + "agents": { 109 + "screen": true 110 + }, 111 + "percepts": false, 112 + "transcripts": true 126 113 }, 127 114 "mtime": 0, 128 115 "occurrences": "Create an occurrence for noteworthy shifts in work rhythms or focus. Include timestamps when deep work starts or ends, or when energy levels noticeably change. Classify each as work or personal based on the surrounding context.", ··· 146 133 "hook": { 147 134 "post": "occurrence" 148 135 }, 149 - "instructions": { 150 - "activity": true, 151 - "facets": true, 152 - "sources": { 153 - "agents": { 154 - "screen": true 155 - }, 156 - "percepts": false, 157 - "transcripts": true 158 - } 136 + "load": { 137 + "agents": { 138 + "screen": true 139 + }, 140 + "percepts": false, 141 + "transcripts": true 159 142 }, 160 143 "mtime": 0, 161 144 "occurrences": "Whenever a future task or commitment is mentioned, create an occurrence with the expected action and deadline if known. Note who requested it and whether it is work or personal.", ··· 173 156 "hook": { 174 157 "post": "occurrence" 175 158 }, 176 - "instructions": { 177 - "facets": true, 178 - "sources": { 179 - "agents": { 180 - "screen": true 181 - }, 182 - "percepts": false, 183 - "transcripts": true 184 - } 159 + "load": { 160 + "agents": { 161 + "screen": true 162 + }, 163 + "percepts": false, 164 + "transcripts": true 185 165 }, 186 166 "mtime": 0, 187 167 "occurrences": "For each entity interaction or relationship mentioned, create an occurrence describing the connection. Include start and end times when the relationship is visible, and capture the type of link such as works-on or discusses-with.", ··· 202 182 "hook": { 203 183 "post": "occurrence" 204 184 }, 205 - "instructions": { 206 - "activity": true, 207 - "facets": true, 208 - "sources": { 209 - "agents": { 210 - "screen": true 211 - }, 212 - "percepts": false, 213 - "transcripts": true 214 - } 185 + "load": { 186 + "agents": { 187 + "screen": true 188 + }, 189 + "percepts": false, 190 + "transcripts": true 215 191 }, 216 192 "mtime": 0, 217 193 "occurrences": "Each meeting should generate an occurrence with start and end times, list of participants and a concise summary. If slides are present, mention them in the details field.", ··· 233 209 "hook": { 234 210 "post": "occurrence" 235 211 }, 236 - "instructions": { 237 - "activity": true, 238 - "facets": true, 239 - "sources": { 240 - "agents": { 241 - "screen": true 242 - }, 243 - "percepts": false, 244 - "transcripts": true 245 - } 212 + "load": { 213 + "agents": { 214 + "screen": true 215 + }, 216 + "percepts": false, 217 + "transcripts": true 246 218 }, 247 219 "mtime": 0, 248 220 "occurrences": "Create an occurrence for every distinct message interaction. Include the time block, app name, contacts or channels involved, whether $preferred was reading or replying, and a summary of visible content.", ··· 264 236 "post": "observation", 265 237 "pre": "observation" 266 238 }, 267 - "instructions": { 268 - "sources": { 269 - "agents": false, 270 - "percepts": true, 271 - "transcripts": true 272 - } 239 + "load": { 240 + "agents": false, 241 + "percepts": true, 242 + "transcripts": true 273 243 }, 274 244 "max_output_tokens": 2048, 275 245 "mtime": 0, ··· 289 259 "hook": { 290 260 "post": "anticipation" 291 261 }, 292 - "instructions": { 293 - "sources": { 294 - "agents": { 295 - "screen": true 296 - }, 297 - "percepts": false, 298 - "transcripts": true 299 - } 262 + "load": { 263 + "agents": { 264 + "screen": true 265 + }, 266 + "percepts": false, 267 + "transcripts": true 300 268 }, 301 269 "mtime": 0, 302 270 "output": "md", ··· 310 278 "screen": { 311 279 "color": "#9c27b0", 312 280 "description": "Creates a detailed documentary record of screen activity. Focuses on the 'what' - chronological account with preserved details, excerpts, and entities.", 313 - "instructions": { 314 - "sources": { 315 - "agents": false, 316 - "percepts": "required", 317 - "transcripts": true 318 - } 281 + "load": { 282 + "agents": false, 283 + "percepts": "required", 284 + "transcripts": true 319 285 }, 320 286 "mtime": 0, 321 287 "output": "md", ··· 329 295 "sense": { 330 296 "color": "#ff6f00", 331 297 "description": "Unified segment understanding — density, content type, entities, facets, speakers, and routing recommendations in a single pass", 332 - "instructions": { 333 - "facets": true, 334 - "sources": { 335 - "agents": false, 336 - "percepts": true, 337 - "transcripts": true 338 - } 298 + "load": { 299 + "agents": false, 300 + "percepts": true, 301 + "transcripts": true 339 302 }, 340 303 "max_output_tokens": 4096, 341 304 "mtime": 0, ··· 356 319 "post": "speaker_attribution", 357 320 "pre": "speaker_attribution" 358 321 }, 359 - "instructions": { 360 - "sources": { 361 - "agents": { 362 - "screen": true, 363 - "speakers": true 364 - }, 365 - "transcripts": true 366 - } 322 + "load": { 323 + "agents": { 324 + "screen": true, 325 + "speakers": true 326 + }, 327 + "transcripts": true 367 328 }, 368 329 "mtime": 0, 369 330 "output": "json", ··· 380 341 "hook": { 381 342 "post": "occurrence" 382 343 }, 383 - "instructions": { 384 - "sources": { 385 - "agents": { 386 - "screen": true 387 - }, 388 - "percepts": false, 389 - "transcripts": true 390 - } 344 + "load": { 345 + "agents": { 346 + "screen": true 347 + }, 348 + "percepts": false, 349 + "transcripts": true 391 350 }, 392 351 "mtime": 0, 393 352 "occurrences": "Create an occurrence for each hour segment, don't break down hours into any smaller segments the goal for timeline occurrences is for them to capture whatever happened within each hour of the day where there was activity.",