@a-company/paradigm 5.38.0 → 6.0.4

package/dist/university-content/notes/N-para-601-data-sovereignty.md

@@ -0,0 +1,140 @@
+---
+id: N-para-601-data-sovereignty
+title: Data Sovereignty
+type: note
+author: paradigm
+created: '2026-04-22'
+updated: '2026-04-22'
+tags:
+  - course
+  - para-601
+  - four-trust-rings
+  - all-data-is
+  - data-policyyaml-configures-observation
+symbols: []
+difficulty: beginner
+estimatedMinutes: 5
+prerequisites: []
+category: paradigm-core
+origin: imported
+source: courses/para-601.json
+---
+
+## The Local Brain Principle
+
+All data produced during agent work is project-locked by default. This is not a policy choice that requires opt-in — it is the architectural default. No data leaves the project unless the user explicitly configures it to do so. This principle is called the "local brain" — every project has its own self-contained intelligence that never leaks.
+
+The reason is trust. When an agent records a learning journal entry about your payment processing logic, that entry should not appear in another user's project. When a work log captures which files were modified, those file paths should not flow to an analytics dashboard without consent. Data sovereignty means the user controls every boundary their data crosses.
+
+## Trust Rings
+
+Data classification uses four concentric trust rings, each expanding the boundary of who can see the data:
+
+**Ring 1: Project-Locked** — Data never leaves the project directory. Work log entries, event stream, nominations, and team decisions are project-locked by default. Storage lives in `.paradigm/` within the project.
+
+**Ring 2: User-Scoped** — Data travels across the user's own projects but not beyond. Learning journal entries are user-scoped — an agent's insights from project A are available when working on project B, but only for the same user. Storage lives in `~/.paradigm/`.
+
+**Ring 3: Creator-Upstream** — Anonymized, aggregate data flows to agent creators (for agents installed from a marketplace). Only high-level metrics like task type, outcome, and helpfulness rating — never code, file paths, symbol names, or conversation content. This ring requires explicit opt-in.
+
+**Ring 4: Network-Public** — Fully anonymized, aggregated statistics shared publicly. Only `aggregated_task_success_rates` and `anonymized_pattern_frequency`. Requires explicit opt-in. Nothing in this ring can identify a project, user, or agent.
+
+The rings are ordered: data at ring 1 can never reach ring 3 without passing through ring 2 first. Each ring expansion requires a policy declaration.
+
+## data-policy.yaml Format
+
+The data policy is configured in `.paradigm/data-policy.yaml`:
+
+```yaml
+version: "1.0"
+default_ring: project-locked
+
+observation:
+  allow:
+    - "src/**"
+    - ".paradigm/**"
+    - "portal.yaml"
+  deny:
+    - ".env*"
+    - "**/*.key"
+    - "**/*.pem"
+    - "**/secrets/**"
+
+streams:
+  work_log:
+    ring: project-locked
+    allow_content: [file_paths, symbol_names, outcome]
+    deny_content: [code_snippets, file_contents, diff_content]
+  learning_journal:
+    ring: user-scoped
+    allow_content: [pattern_descriptions, confidence_adjustments, approach_descriptions]
+    deny_content: [code_snippets, file_contents, symbol_names_with_context]
+    redaction:
+      - pattern: "\\b[A-Z_]{2,}_KEY\\b"
+      - pattern: "password|secret|token"
+  team_decisions:
+    ring: project-locked
+    allow_content: [rationale, alternatives, symbol_references]
+    deny_content: [implementation_details]
+
+upstream:
+  ring: creator-upstream
+  allowed: [task_type, outcome, helpfulness, duration_bucket, error_category]
+  denied: [code_of_any_kind, file_paths, symbol_names, conversation_content, user_identity]
+
+network:
+  ring: network-public
+  opt_in: false
+  if_opted_in: [aggregated_task_success_rates, anonymized_pattern_frequency]
+```
+
+## Observation Rules
+
+Observation rules control which files agents can observe. The `allow` list defines glob patterns for permitted paths. The `deny` list defines patterns that are always blocked — deny overrides allow.
+
+The default denies `.env*`, `*.key`, `*.pem`, and `**/secrets/**`. These patterns catch common secret file locations. The deny list is **additive** when merging user policy over defaults — you can add deny patterns but never remove the built-in ones.
+
+## Stream Content Rules
+
+Each knowledge stream has its own content rules defining what categories of content are allowed or denied:
+
+**14 content categories:** `file_paths`, `symbol_names`, `symbol_names_with_context`, `outcome`, `pattern_descriptions`, `confidence_adjustments`, `approach_descriptions`, `rationale`, `alternatives`, `symbol_references`, `code_snippets`, `file_contents`, `diff_content`, `implementation_details`, `architectural_decisions`.
+
+The work log allows `file_paths` and `symbol_names` (needed for standup context) but denies `code_snippets` (no raw code in work logs). The learning journal allows `pattern_descriptions` (abstract learnings) but denies `symbol_names_with_context` (no project-specific details in the cross-project journal).
+
+**Redaction patterns** use regex to scrub sensitive content before it is stored. The default learning journal redaction catches environment variable names (`\b[A-Z_]{2,}_KEY\b`) and common secret terms (`password|secret|token`). Matches are replaced with `[REDACTED]`.
+
+## Per-Agent Overrides
+
+The `agent_overrides` section allows per-agent policy customization:
+
+```yaml
+agent_overrides:
+  security:
+    observation:
+      allow: ["src/**", ".paradigm/**", "portal.yaml", ".env.example"]
+    learning_journal:
+      deny_content: [code_snippets, file_contents, diff_content, implementation_details]
+    upstream:
+      opt_in: false
+```
+
+This gives the security agent slightly broader observation (it can read `.env.example` to verify it matches the template) while restricting its journal content and disabling upstream feedback.
+
+## Enforcement Boundaries
+
+The data policy is enforced at eight boundaries:
+
+1. **event-emission** — Before an event enters the stream, check if the path is observable
+2. **attention-filtering** — Agents only score events for paths they are allowed to observe
+3. **work-log-recording** — Content is filtered and redacted before writing to the work log
+4. **journal-recording** — Content is filtered and redacted before writing to the journal
+5. **cross-project-transfer** — Journal entries marked `transferable` are checked against ring 2 rules
+6. **upstream-feedback** — Data flowing to agent creators is checked against ring 3 rules
+7. **network-aggregation** — Data flowing to the network is checked against ring 4 rules
+8. **notebook-promotion** — Journal entries promoted to notebook are checked against content rules
+
+Every enforcement action is auditable. The `AuditEntry` interface captures who, when, what boundary, what data category, and what action was taken (allowed, filtered, redacted, or blocked).
+
+## The Merge Rule
+
+When a user provides a `data-policy.yaml`, it is merged over the `DEFAULT_DATA_POLICY` with a critical rule: **deny lists are additive, never replacing**. If the default denies `.env*` and the user's policy does not mention `.env*`, the deny still applies. The user can add more deny patterns but cannot remove built-in protections. Allow lists, by contrast, can be fully replaced.

package/dist/university-content/notes/N-para-601-event-stream.md

@@ -0,0 +1,126 @@
+---
+id: N-para-601-event-stream
+title: The Event Stream
+type: note
+author: paradigm
+created: '2026-04-22'
+updated: '2026-04-22'
+tags:
+  - course
+  - para-601
+  - streamevent-has-12
+  - 12-event-types
+  - 6-event-sources
+symbols: []
+difficulty: beginner
+estimatedMinutes: 5
+prerequisites: []
+category: paradigm-core
+origin: imported
+source: courses/para-601.json
+---
+
+## How Events Are Produced
+
+Every meaningful action in a Paradigm session produces an event. When an agent modifies a file, the post-write hook emits a `file-modified` event. When an MCP tool is called, a `symbol-queried` or `gate-checked` event fires depending on the tool. When compliance issues are detected, a `compliance-violation` event captures the details. These events flow into a shared stream that all agents can observe.
+
+The event stream is the nervous system of ambient coordination. Without it, agents are blind to each other's actions. With it, a security agent can notice that a new route was created without a gate, a tester can see that a new component was added without test coverage, and a reviewer can observe that a complex flow was modified without documentation updates.
+
+## StreamEvent Anatomy
+
+Every event follows the `StreamEvent` interface with 12 fields:
+
+```typescript
+interface StreamEvent {
+  id: string;          // Unique ID (e.g., "ev-1710937200000-4821")
+  type: EventType;     // Classification (12 types)
+  source: EventSource; // Origin (6 sources)
+  timestamp: string;   // ISO 8601
+  path?: string;       // File path (if applicable)
+  symbols?: string[];  // Paradigm symbols referenced
+  keywords?: string[]; // Semantic keywords extracted
+  context?: string;    // Brief context snippet
+  agent?: string;      // Agent that produced this event
+  tool?: string;       // MCP tool name (if from tool call)
+  severity?: string;   // info, warning, error, critical
+  data?: Record<string, unknown>; // Structured metadata
+}
+```
+
+**Event IDs** are generated from the current timestamp plus a random 4-digit suffix: `ev-{timestamp}-{rand}`. This ensures uniqueness without coordination.
+
+**Event Sources** identify where the event originated:
+- `post-write-hook` — File was written, hook detected the change
+- `mcp-tool-call` — An MCP tool was invoked
+- `stop-hook` — Session end triggered an event
+- `conversation` — Event derived from conversation context
+- `agent-action` — Agent explicitly emitted an event
+- `error` — An error occurred during processing
+
+**Event Types** classify what happened. Twelve types cover the full range of project activity:
+
+| Type | When It Fires |
+|---|---|
+| `file-modified` | A source file was changed |
+| `symbol-queried` | A symbol was looked up via search/navigate/ripple |
+| `gate-checked` | A gate (^) was evaluated or referenced |
+| `compliance-violation` | A habit, hook, or policy check failed |
+| `concept-mentioned` | A semantic concept appeared in context |
+| `work-completed` | A unit of work finished (pass/fail/partial) |
+| `decision-made` | A team decision was recorded |
+| `error-encountered` | An error was caught during processing |
+| `route-created` | A new API route was added |
+| `gate-added` | A new gate was added to portal.yaml |
+| `flow-modified` | A flow definition was changed |
+| `test-result` | A test suite reported results |
+
+## JSONL Storage
+
+Events are stored as append-only JSONL (one JSON object per line) at `.paradigm/events/stream.jsonl`. The append-only format is chosen for performance — writing one line is cheaper than reading, modifying, and rewriting a file.
+
+The stream is bounded by `DEFAULT_MAX_EVENTS` (1000). When the file exceeds ~500KB (a rough proxy for 1000 events), the `pruneIfNeeded` function reads the file, keeps only the most recent 1000 lines, and rewrites it. This ensures the stream does not grow unbounded while preserving recent history.
+
+Events are also held in a memory buffer (`memoryStream`) for fast access during the current session. The memory buffer is independently bounded to 1000 events. Even if file I/O fails, the memory stream continues to function — file write failure is non-fatal.
+
+## emitEvent
+
+The `emitEvent` function is the single entry point for producing events:
+
+```typescript
+emitEvent(rootDir, {
+  type: 'file-modified',
+  source: 'post-write-hook',
+  path: 'src/auth/middleware.ts',
+  symbols: ['#auth-middleware', '^authenticated'],
+  keywords: ['authentication', 'JWT'],
+  context: 'Modified JWT validation logic',
+});
+```
+
+The function auto-generates the `id` and `timestamp`, appends to both the memory buffer and the JSONL file, and prunes if the file is oversized. It returns the complete `StreamEvent` with all fields populated.
+
+## queryEvents
+
+The `queryEvents` function reads events from disk (falling back to the memory buffer on read failure) and supports five filters:
+
+- `type` — Filter by event type (e.g., `'file-modified'`)
+- `source` — Filter by event source (e.g., `'mcp-tool-call'`)
+- `symbol` — Filter by a specific symbol in the event's `symbols` array
+- `agent` — Filter by the agent that produced the event
+- `since` — Only events after this ISO timestamp
+- `limit` — Maximum number of events to return
+
+Results are sorted by timestamp descending (most recent first). This ordering is intentional — in ambient coordination, recent events are almost always more relevant than older ones.
+
+## Event Stream Configuration
+
+The `EventStreamConfig` interface allows fine-grained control:
+
+- `enabled` — Master switch for ambient coordination (default: true in v5.0 projects)
+- `max_events` — Maximum events retained (default: 1000)
+- `event_ttl_seconds` — Time-to-live for events (default: 3600 = 1 hour)
+- `emit` — Whitelist of event types to produce (if set, only these types fire)
+- `suppress` — Blacklist of event types to silence (overrides emit)
+- `storage` — `'memory'` (in-process only) or `'file'` (JSONL persistence)
+
+For projects that do not need ambient coordination, setting `enabled: false` turns off event emission entirely. For projects that need it but want to reduce noise, the `suppress` list can silence high-frequency event types like `symbol-queried` while preserving important ones like `compliance-violation` and `gate-added`.

package/dist/university-content/notes/N-para-601-knowledge-streams.md

@@ -0,0 +1,144 @@
+---
+id: N-para-601-knowledge-streams
+title: Knowledge Streams
+type: note
+author: paradigm
+created: '2026-04-22'
+updated: '2026-04-22'
+tags:
+  - course
+  - para-601
+  - three-knowledge-streams
+  - work-log-paradigmwork-logdate
+  - learning-journal-paradigmagentsidjournal
+symbols: []
+difficulty: beginner
+estimatedMinutes: 6
+prerequisites: []
+category: paradigm-core
+origin: imported
+source: courses/para-601.json
+---
+
+## The Lore Split
+
+Paradigm's original lore system stored everything — sessions, decisions, incidents, milestones — in a single stream of date-partitioned YAML entries. This worked well for small projects, but as projects grew, the single stream created problems. A standup bot pulling "what got done this week" had to filter through architectural decisions and incident postmortems. An agent looking for "what did I learn about JWT handling" had to parse session summaries. A new team member searching for "why did we choose Redis" had to wade through hundreds of entries.
+
+v5.0 splits lore into three knowledge streams, each with a distinct audience, lifecycle, and storage location.
+
+## Stream 1: Work Log — "What Got Done"
+
+The work log is the team-facing record of completed work. It answers the question every standup asks: what did you do, what is left, what is blocking you?
+
+**Storage:** `.paradigm/work-log/{date}/` — project-scoped, date-partitioned YAML files, one entry per work unit.
+
+**Audience:** The team. Standup bots, sprint boards, and project managers consume work log entries.
+
+**Lifecycle:** Ephemeral. Work log entries are relevant for days to weeks. After a sprint ends, they are historical context rather than active reference.
+
+**Entry structure (`WorkLogEntry`):**
+
+| Field | Required | Description |
+|---|---|---|
+| `id` | yes | Unique ID (e.g., `WL-security-001`) |
+| `agent` | yes | Agent that performed the work |
+| `timestamp` | yes | ISO 8601 timestamp |
+| `summary` | yes | What was done |
+| `outcome` | yes | pass, fail, partial, or blocked |
+| `task_ref` | no | Ticket or issue reference (e.g., `ENG-142`) |
+| `files_modified` | no | List of modified files |
+| `symbols_touched` | no | Paradigm symbols touched |
+| `next_steps` | no | What remains to be done |
+| `blockers` | no | What is blocking progress |
+| `duration_minutes` | no | How long the work took |
+| `commit` | no | Git commit hash |
+
+**MCP Tools:**
+- `paradigm_work_log_record` — Record a work log entry. Requires `agent`, `summary`, and `outcome`. Supports optional `task_ref`, `files_modified`, `symbols_touched`, `next_steps`, `blockers`, `duration_minutes`, and `commit`.
+- `paradigm_work_log_search` — Search work log entries by `agent`, `outcome`, `task_ref`, `symbol`, `dateFrom`, `dateTo`. Pass `summary: true` to get an aggregate summary instead of individual entries.
+
+## Stream 2: Learning Journal — "What I Learned"
+
+The learning journal is the agent-private record of insights, corrections, and patterns discovered during work. It answers the question: what should I remember for next time?
+
+**Storage:** `~/.paradigm/agents/{id}/journal/` — user-scoped, agent-specific. The journal travels with the agent across projects because learning is not project-specific.
+
+**Audience:** The agent itself (and optionally other agents if the insight is marked `transferable`).
+
+**Lifecycle:** Durable. A pattern discovered today about JWT ordering is relevant months from now. Journal entries persist until explicitly archived.
+
+**Entry structure (`JournalEntry`):**
+
+| Field | Required | Description |
+|---|---|---|
+| `id` | yes | Unique ID (e.g., `LJ-2026-03-20-001`) |
+| `agent` | yes | Agent who learned this |
+| `timestamp` | yes | ISO 8601 timestamp |
+| `trigger` | yes | What prompted the learning (7 trigger types) |
+| `insight` | yes | The insight itself |
+| `project` | yes | Project where this happened |
+| `transferable` | yes | Whether this applies to other projects |
+| `confidence_before` | no | Agent's confidence before (0.0-1.0) |
+| `confidence_after` | no | Adjusted confidence after (0.0-1.0) |
+| `pattern` | no | Extracted `LearningPattern` (id, applies_when, correct_approach) |
+| `linked_work_log` | no | Work log entry that prompted this learning |
+| `tags` | no | Tags for categorization |
+
+Seven journal triggers capture distinct learning moments: `correction_received` (human corrected the approach), `confidence_miss` (agent was confident but wrong), `pattern_discovered` (new reusable pattern found), `debate_loss` (another agent's approach was chosen), `failure_analysis` (something broke and was analyzed), `human_feedback` (direct human assessment), and `self_reflection` (agent proactively recorded an insight).
+
+**MCP Tools:**
+- `paradigm_journal_record` — Record a journal entry. Requires `agent`, `trigger`, `insight`, `project`, and `transferable`. Supports optional `confidence_before`, `confidence_after`, `pattern`, `linked_work_log`, and `tags`.
+- `paradigm_journal_search` — Search journal entries by `agent`, `trigger`, `project`, `transferable`, `tag`, `dateFrom`, `dateTo`. Pass `stats: true` (with `agent`) to get aggregate statistics.
+
+## Stream 3: Team Decisions — "What We Decided"
+
+Team decisions are the institutional record of choices made, rationale given, and alternatives rejected. They answer the question: why did we do it this way?
+
+**Storage:** `.paradigm/decisions/` — project-scoped, not date-partitioned (decisions are referenced by topic, not by when they were made).
+
+**Audience:** The entire team — current and future. New team members benefit most from decision records.
+
+**Lifecycle:** Institutional. Decisions persist until explicitly superseded or deprecated. A decision made in month one remains authoritative until a newer decision replaces it.
+
+**Entry structure (`TeamDecision`):**
+
+| Field | Required | Description |
+|---|---|---|
+| `id` | yes | Unique ID (e.g., `TD-2026-03-20-001`) |
+| `title` | yes | Decision title |
+| `timestamp` | yes | ISO 8601 timestamp |
+| `participants` | yes | Who participated (id, role, stance) |
+| `decision` | yes | The decision itself |
+| `rationale` | yes | Why this was chosen |
+| `alternatives_considered` | no | What else was considered and why it was rejected |
+| `symbols_affected` | no | Paradigm symbols affected |
+| `status` | yes | active, proposed, superseded, deprecated, rejected |
+| `tags` | no | Tags for categorization |
+
+Participant stances capture the human dynamics: `proposed`, `supported`, `dissented`, `abstained`, `neutral`. Recording dissent is especially important — when a decision is revisited later, knowing who dissented and why saves time.
+
+**MCP Tools:**
+- `paradigm_decision_record` — Record a decision. Requires `title`, `decision`, `rationale`, and `participants`. Supports optional `alternatives_considered`, `symbols_affected`, `status`, and `tags`.
+- `paradigm_decision_search` — Search decisions by `status`, `participant`, `symbol`, `tag`, `dateFrom`, `dateTo`. Pass `summary: true` for an aggregate view.
+
+## Auto-Classification and the Companion-Lore Pattern
+
+When recording via `paradigm_lore_record`, the `stream` parameter routes the entry to the correct knowledge stream. Setting `stream: 'auto'` triggers auto-classification based on the entry type. The `LORE_TYPE_TO_STREAM` mapping (defined in `packages/paradigm-mcp/src/types/knowledge-streams.ts`) defines how lore types map to streams:
+
+- `agent-session` splits into work-log (what was done) and journal (what was learned)
+- `incident` splits across work-log (what happened), journal (what we learned), and decisions (prevention strategy)
+- `review` splits into work-log and journal
+- `human-note` routes to the decisions stream (institutional context)
+- `retro` and `insight` route to journal and decisions (learnings worth preserving)
+- `milestone` routes to the decisions stream
+
+Note that the `decision` lore *type* was removed in v6.0 — see PARA 501 — but the `decision` *stream* persists. The stream is fed by `paradigm_decision_record`, not by typed lore entries. The `LORE_TYPE_TO_STREAM` table still contains a residual `'decision': ['decision']` mapping for backward-compat with v1/v2 entries that get migrated to type `insight` on read; new writes never reach that branch.
+
+### The Companion-Lore Pattern (v6.0)
+
+When you call `paradigm_decision_record`, two things happen:
+
+1. The canonical decision is written to `.paradigm/decisions/TD-*.yaml` (decisions stream).
+2. A companion lore entry of type `insight` is auto-written to the lore timeline (journal stream), with a back-reference (`references.decision_id`) to the TD- ID.
+
+This split lets the decision stay topic-addressable (search by symbol, status, participant) while the timeline still shows the moment it was made. Project newcomers can follow the timeline forward and see the major calls; researchers can query the decisions stream directly. The companion write is best-effort — a failure to write the companion lore never blocks the decision record.

package/dist/university-content/notes/N-para-601-learning-loop.md

@@ -0,0 +1,68 @@
+---
+id: N-para-601-learning-loop
+title: The Learning Loop
+type: note
+author: paradigm
+created: '2026-04-22'
+updated: '2026-04-22'
+tags:
+  - course
+  - para-601
+  - six-phase-learning-loop
+  - observation-without-adaptation
+  - v50-closes-the
+symbols: []
+difficulty: beginner
+estimatedMinutes: 4
+prerequisites: []
+category: paradigm-core
+origin: imported
+source: courses/para-601.json
+---
+
+## Why Observation Without Adaptation Is Waste
+
+Most development tools observe extensively but adapt almost never. Your linter sees thousands of issues. Your CI runs hundreds of tests. Your APM collects millions of metrics. All of this observation generates data — but data without a feedback loop is just noise with a storage bill.
+
+Consider what happens in a typical AI-assisted session today. An agent modifies 8 files, creates a new service, adds routes to portal.yaml, and records a lore entry. The session ends. A week later, a different agent picks up related work and makes the same architectural mistake the first agent corrected mid-session. Why? Because the correction was never captured in a form that feeds back into future sessions. The observation happened (the lore entry recorded what was done), but the adaptation never occurred (the learning was not injected into the next agent's context).
+
+This is the gap that Paradigm v5.0 closes.
+
+## The DO-RECORD-ASSESS-LEARN-ADAPT-DO Cycle
+
+The ambient coordination system implements a six-phase loop:
+
+**DO** — An agent performs work: modifying files, calling tools, making decisions. Every action produces events in the event stream.
+
+**RECORD** — The work is captured in three knowledge streams, each with a different audience and lifecycle. The work log records what got done (for the team). The learning journal records what the agent learned (for itself). Team decisions record what was decided and why (for the institution).
+
+**ASSESS** — Events flow through attention filters. Each agent scores every event against its attention patterns — symbol matches, path matches, concept matches, signal matches. Events that exceed an agent's threshold trigger the next phase.
+
+**LEARN** — Agents self-nominate contributions based on relevant events. A security agent notices a new route without a gate. A reviewer spots a pattern they have seen fail before. A tester sees a new component without test coverage. These nominations capture agent-specific insights triggered by project activity.
+
+**ADAPT** — Learnings feed back into context. Journal insights from past sessions appear in the next session's prompt enrichment. Recent team decisions are surfaced to agents working on related symbols. Pending nominations are included in the active agent's context. The `paradigm_context_compose` tool assembles all of this into a coherent context section.
+
+**DO** — The cycle repeats, but now the agent starts with richer context. It knows what was tried before, what the team decided, what the security agent flagged, and what patterns to avoid. Each iteration produces better outcomes because the loop is closed.
+
+## What v5.0 Adds to Close the Loop
+
+Before v5.0, Paradigm had the DO and RECORD phases (lore entries, .purpose files, portal.yaml). It had partial ASSESS capability through ripple analysis. But the LEARN and ADAPT phases were manual — a human had to read lore entries and tell the next agent what to watch out for.
+
+v5.0 adds four capabilities that close the loop automatically:
+
+1. **Knowledge Streams** — Lore is split into three streams with distinct storage, lifecycles, and audiences, enabling targeted adaptation.
+2. **Event Stream** — Every tool call and file edit produces a structured event that flows through attention filters, enabling real-time assessment.
+3. **Attention Scoring & Nominations** — Agents evaluate events against their attention patterns and self-nominate contributions, enabling machine-driven learning.
+4. **Context Composition** — Journal insights, team decisions, and pending nominations are composed into the next session's context, enabling automatic adaptation.
+
+## Context Engineering: Slim CLAUDE.md + On-Demand Guidance
+
+The learning loop requires efficient context management. A 900-line CLAUDE.md that loads every time wastes tokens on content that may not be relevant to the current task. v5.0 implements a context engineering approach:
+
+**Slim CLAUDE.md** — The base CLAUDE.md was reduced from ~856 lines to ~150 lines. It contains only the orientation information needed for every session: project overview, symbol system, conventions, commit format, and pointers to on-demand resources.
+
+**On-Demand Guidance** — Twelve guidance resources are available via `paradigm://guidance/{topic}`. Topics include logging, portal protocol, MCP workflow, flows, orchestration, workspaces, university, calibration, checkpoints, navigation, component types, and troubleshooting. An agent loads only the guidance it needs for the current task.
+
+**Agent Contributions** — Active agents inject their own context sections via `AgentContext.contributions`. A security agent might contribute a section listing recently added gates. A reviewer might contribute a section listing code smells found in the current PR. These contributions compose dynamically based on which agents are active.
+
+The result is a context window that contains high-signal, task-relevant content rather than a static wall of instructions. The learning loop feeds relevant history into this context, making each session incrementally smarter than the last.

package/dist/university-content/notes/N-para-601-maestro-team-collab.md

@@ -0,0 +1,136 @@
+---
+id: N-para-601-maestro-team-collab
+title: 'Maestro: Visible Team Orchestration'
+type: note
+author: paradigm
+created: '2026-04-22'
+updated: '2026-04-22'
+tags:
+  - course
+  - para-601
+  - maestro-is-a
+  - attributed-responses-nickname
+  - agent-profiles-carry
+symbols: []
+difficulty: beginner
+estimatedMinutes: 6
+prerequisites: []
+category: paradigm-core
+origin: imported
+source: courses/para-601.json
+---
+
+## From Synthesized Summaries to Attributed Conversations
+
+Traditional multi-agent orchestration has a visibility problem. An orchestrator spawns three agents, waits for their responses, synthesizes a summary, and presents it to the human. The human sees one voice — the orchestrator's — and loses all nuance from individual agent perspectives. If the architect disagreed with the security agent, you would never know. If the builder had a novel approach, it gets flattened into a consensus view.
+
+The Maestro model inverts this pattern. Every agent speaks for itself.
+
+## The Maestro Model
+
+Maestro is not a separate system — it is a behavior pattern for the active Claude Code session. When you ask a complex question that benefits from multiple perspectives, Maestro:
+
+1. **Evaluates expertise** — Which agents have the highest confidence scores on the relevant symbols?
+2. **Loads ambient context** — Recent team decisions, journal insights, pending nominations are injected into each agent's prompt via `buildProfileEnrichment()`.
+3. **Spawns subagents** — Each agent receives its full profile: personality, expertise history, transferable patterns, notebook entries, and the ambient context.
+4. **Presents attributed responses** — Each agent's response appears with a `[role]` or `[nickname (role)]` prefix. You see exactly who said what.
+5. **Records to Symphony** — Each contribution is written as a Symphony message, creating a persistent team thread visible in Conductor and the Platform dashboard.
+6. **Learns from feedback** — At session end, `paradigm_ambient_learn` adjusts each agent's attention threshold based on acceptance/dismissal rates.
+
+## Agent Profiles and Nicknames
+
+Each agent has an `.agent` YAML file in `~/.paradigm/agents/` with:
+
+- **personality** — style (deliberate/rapid/exploratory/methodical), risk tolerance, verbosity
+- **expertise** — per-symbol confidence scores, exponential moving average from lore
+- **attention** — threshold, symbol/path/concept/signal subscriptions
+- **collaboration** — default stance toward other agents, debate behavior
+- **nomination** — urgency patterns, communication style
+- **nickname** — optional display name (e.g., "George" for the architect)
+- **benched** — if true, Maestro skips this agent entirely
+
+The `nickname` field makes agents feel like team members. Terminal output shows `[George (architect)]` instead of the generic `[architect]`.
+
+## Bench and Activate
+
+Not every agent should speak on every task. The bench system lets you silence noisy agents:
+
+- `paradigm agent bench security` — security agent stops nominating and is excluded from orchestration
+- `paradigm agent activate security` — restore to active status
+- `paradigm agent roster` — see who is active vs benched with stats
+
+Benched agents are skipped in both `paradigm_orchestrate_inline` and the nomination engine's `processEvent`. Their profiles remain intact — bench is a pause, not a delete.
+
+## Symphony Team Threads
+
+Every orchestration creates a thread prefixed `thr-orch-`. Maestro writes each agent contribution as a Symphony message from the agent's identity (`{project}/{role}`). This creates:
+
+- **Persistent record** — The team conversation survives session restarts
+- **Conductor visibility** — The TeamThreadView shows messages with colored role prefixes
+- **Platform dashboard** — The Team section displays the same thread in a browser
+- **Recovery context** — Next session's handoff includes which agents contributed and what they said
+
+## The Neverland Test
+
+Named after the validation criteria in the spec, the Neverland test tracks whether agent learning actually works across sessions:
+
+- **Sessions 1-3**: Agents accumulate — touching symbols, recording lore, discovering patterns
+- **Sessions 4-5**: Maestro routes based on learned confidence scores
+- **Sessions 6-10**: Accepted suggestions lower threshold (agent speaks more). Dismissed suggestions raise it (agent speaks less).
+
+Measurable targets:
+- By session 10, Maestro routes to the right agent >80% of the time
+- Agent acceptance rate improves from ~50% (cold start) to >70%
+
+Track progress with `paradigm_ambient_health` — returns per-agent stats and overall health status (cold-start → accumulating → calibrating → mature).
+
+## Postflight Learning Loop
+
+The postflight skill closes the feedback loop after every task:
+
+1. **Step 8b** runs `paradigm_ambient_learn` for each contributing agent — adjusts attention thresholds based on accept/dismiss rates
+2. Runs `paradigm_ambient_promote` — auto-promotes high-confidence journal patterns to the agent's notebook
+3. Records contributions via Symphony if not already done during execution
+
+This ensures every session makes agents incrementally smarter. The handoff skill captures agent performance summaries so the next session inherits this knowledge.
+
+## The Teacher Model
+
+The learning loop has a quality problem: the nomination engine only sees file paths, never content. Briefs like "review for consistency" get dismissed, which raises the agent's threshold, which silences the agent. The system learns to be *silent* instead of *better*.
+
+The Teacher Model fixes this. Maestro (the active session) acts as a teacher who observes the full session and writes targeted feedback.
+
+### Session Work Log
+
+During each session, a running JSONL log at `.paradigm/events/session-log.jsonl` captures:
+- **Agent contributions**: what each agent was asked to do (from orchestration)
+- **User verdicts**: accepted / dismissed / revised, with the reason why
+
+This is the data Maestro reads at postflight to write meaningful learning feedback.
+
+### Postflight Learning Pass
+
+At session end, Step 8b reads the session work log and writes journal entries per agent:
+
+- **Accepted** → `human_feedback` trigger, confidence 0.85, extract the pattern that was confirmed correct
+- **Dismissed** → `correction_received` trigger, confidence 0.4, explain what was wrong and what to do differently
+- **Revised** → `correction_received` trigger, confidence 0.65, include the delta between proposal and actual
+
+These journal entries include `pattern.applies_when` and `pattern.correct_approach` fields — the exact knowledge that gets promoted to notebooks.
+
+### Training New Behaviors
+
+The journal → notebook → `buildProfileEnrichment` pipeline is also how you teach agents new skills. If you say "documentor, also update CHANGELOG from now on," Maestro writes a journal entry. It promotes to a notebook entry. Next session, that knowledge is in the agent's context. No configuration needed.
+
+## The Documentor Agent
+
+The 6th core agent. Its sole job: maintain Paradigm metadata files after other agents finish their work.
+
+- Always runs as the **final orchestration stage**
+- Reviews what changed (git diff, session work log)
+- Updates .purpose files, portal.yaml, symbol registrations
+- Uses ONLY `paradigm_purpose_*`, `paradigm_portal_*`, and `paradigm_reindex` MCP tools
+- Never modifies source code
+- Relieves all other agents of Paradigm compliance
+
+This separation of concerns means architect, builder, security, and reviewer can focus purely on their domain. The documentor handles the bookkeeping.