context

# /nemp:context

Find and display memories relevant to a search query using smart keyword expansion.

## Usage
```bash
/nemp:context auth           # Find memories related to authentication
/nemp:context database       # Find database-related memories
/nemp:context api            # Find API-related memories
/nemp:context style          # Find styling/CSS memories
/nemp:context test           # Find testing-related memories
```

## Instructions

### 1. Get the Search Query
Extract the search term from the user's command argument.

If no argument provided, show help:
```
Nemp Context Search

Usage: /nemp:context <search-term>

Examples:
  /nemp:context auth      - Find authentication memories
  /nemp:context database  - Find database memories
  /nemp:context api       - Find API memories
  /nemp:context style     - Find styling/CSS memories
  /nemp:context test      - Find testing memories

Smart search expands your query to related terms!
```

### 2. Expand Keywords Using Smart Mappings

Based on the search term, expand to related keywords:

```
KEYWORD MAPPINGS:

auth, login, authentication:
  → auth, authentication, login, session, jwt, oauth, nextauth, clerk,
    supabase-auth, passport, token, credentials, signin, signup, logout

database, db:
  → database, db, postgres, postgresql, mysql, sqlite, mongo, mongodb,
    prisma, drizzle, mongoose, sequelize, knex, typeorm, schema, migration

api, endpoint:
  → api, endpoint, route, rest, graphql, trpc, fetch, axios, request,
    response, http, webhook, cors, middleware

style, css, styling:
  → style, css, tailwind, emotion, styled-components, chakra, mantine,
    theme, design, scss, sass, less, classname, styling

test, testing:
  → test, testing, jest, vitest, playwright, cypress, unit, integration,
    e2e, mock, fixture, assertion, coverage, spec

state, store:
  → state, store, redux, zustand, jotai, recoil, context, provider,
    reducer, action, selector, persist

deploy, hosting:
  → deploy, deployment, hosting, vercel, netlify, aws, docker, kubernetes,
    ci, cd, pipeline, github-actions, build

config, env, environment:
  → config, configuration, env, environment, dotenv, settings, options,
    variables, secrets, keys

error, debug:
  → error, debug, debugging, exception, catch, try, logging, sentry,
    bugsnag, stack, trace, console

types, typescript:
  → types, typescript, interface, type, generic, zod, yup, schema,
    validation, typing
```

### 3. Search Both Project and Global Memories

**Read memory files:**

```
Project memories: .nemp/memories.json
Global memories:  ~/.nemp/memories.json

Memory format:
{
  "key-name": "memory value content",
  "another-key": "another value"
}
```

Use the Read tool to load both files. Handle missing files gracefully.

### 4. Find Matching Memories

For each memory entry, perform case-insensitive matching:

```
For each (key, value) in memories:
  - Check if KEY contains any expanded keyword
  - Check if VALUE contains any expanded keyword
  - If match found, add to results with match type
```

**Match Priority:**
1. **Key exact match** - Key equals search term
2. **Key contains** - Key contains search term or expanded keyword
3. **Value contains** - Value contains search term or expanded keyword

### 4b. Update Vitality for All Returned Memories

For each memory that matches and will be displayed to the user, update its vitality counters:

1. If the memory lacks cortex fields, initialize with defaults first:
   - `type`: `"fact"`
   - `confidence`: `{"score": 0.65, "source": "agent-inferred", "reason": "Pre-cortex memory"}`
   - `vitality`: all counters set to 0, `score`: 50, `state`: "active", `trend`: "stable", `last_read`: null, `decay_rate`: 0.01
   - `links`: `{"goals": [], "conflicts": [], "supersedes": null, "superseded_by": null, "causal": []}`
2. For each matched memory, update:
   ```
   vitality.reads += 1
   vitality.reads_7d += 1
   vitality.reads_30d += 1
   vitality.last_read = <current ISO-8601 timestamp>
   ```
3. Recalculate `vitality.score` using the formula:
   ```
   vitality = (
     (reads_7d × 15) +
     (reads_30d × 3) +
     (foresight_load_ratio × 20) +
     (agent_reference_ratio × 25) +
     (update_frequency × 10) +
     (goal_link_active × 15) -
     (correction_events × 10) -
     (days_since_last_read × decay_rate)
   )
   clamped to 0-100
   ```
   Where:
   - `foresight_load_ratio` = foresight_loads / (foresight_loads + foresight_skips), default 0 if both are 0
   - `agent_reference_ratio` = agent_references / reads, default 0 if reads is 0
   - `update_frequency` = update_count / max(1, days_since_created)
   - `goal_link_active` = 1 if links.goals has any active goal, else 0
4. Set `vitality.state` based on score:
   - 80-100: `"thriving"`
   - 50-79: `"active"`
   - 20-49: `"fading"`
   - 1-19: `"dormant"`
   - 0: `"extinct"`
5. Write ALL updated memories back to memories.json in **one write operation** (do not write per-memory).

**Log the operation:**
```bash
echo "[$(date -u +%Y-%m-%dT%H:%M:%SZ)] CONTEXT_READ agent=${CLAUDE_AGENT_NAME:-main} query=<query> matched=<n>" >> .nemp/access.log
```

### 5. Display Results

**When matches found:**

```
Context Search: "auth"

Expanded to: auth, authentication, login, session, jwt, oauth, nextauth...

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

PROJECT MEMORIES

  auth-config [KEY MATCH]
  ────────────────────────
  JWT authentication with refresh tokens. Access token expires
  in 15 minutes, refresh token in 7 days...

  api-routes [VALUE MATCH]
  ────────────────────────
  POST /api/login - User authentication
  POST /api/register - New user signup...

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

GLOBAL MEMORIES

  security-best-practices [VALUE MATCH]
  ────────────────────────────────────
  Always use bcrypt for password hashing. Implement rate
  limiting on auth endpoints...

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Found 3 memories (2 project, 1 global)

Quick ac