fix: migration 009 add source_count + entity dedup index

- Add source_count INTEGER DEFAULT 1 column
- Dedup existing rows before creating unique index
- CREATE UNIQUE INDEX idx_memory_entity_project_name (project_id, name)
- Idempotent: safe to re-run

.gitea/workflows/build.yaml

@@ -50,19 +50,13 @@ jobs:
           REGISTRY_USER: ${{ secrets.FORGEJO_REGISTRY_USER }}
           REGISTRY_TOKEN: ${{ secrets.FORGEJO_REGISTRY_TOKEN }}
 
-      - name: Build Docker image
+      - name: Build and push Docker image (SHA tag only)
         run: |
           docker build --no-cache --progress=plain \
             -t "${IMAGE}:${{ steps.sha.outputs.short_sha }}" \
-            -t "${IMAGE}:latest" \
             -f Dockerfile .
-
-      - name: Push Docker image
-        if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
-        run: |
           docker push "${IMAGE}:${{ steps.sha.outputs.short_sha }}"
-          docker push "${IMAGE}:latest"
-          echo "✓ Pushed: ${IMAGE}:${{ steps.sha.outputs.short_sha }}"
+          echo "Pushed: ${IMAGE}:${{ steps.sha.outputs.short_sha }}"
 
       - name: Prune unused images
         run: docker image prune -a --force 2>&1 | tail -3 || true

.gitea/workflows/deploy.yaml

@@ -0,0 +1,44 @@
+name: Deploy
+
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+env:
+  REGISTRY: forgejo.riotpiao.com
+  IMAGE: forgejo.riotpiao.com/riotpiao-poimen/poimen-memory
+  DOCKER_HOST: tcp://localhost:2375
+
+jobs:
+  deploy:
+    name: Tag & Push Latest
+    runs-on: rust
+    steps:
+      - name: Install Docker
+        run: apt-get update && apt-get install -y docker.io
+
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Get short SHA
+        id: sha
+        run: echo "short_sha=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+
+      - name: Registry login
+        run: |
+          echo "${REGISTRY_TOKEN}" | docker login "${REGISTRY}" \
+            --username "${REGISTRY_USER}" --password-stdin
+        env:
+          REGISTRY_USER: ${{ secrets.FORGEJO_REGISTRY_USER }}
+          REGISTRY_TOKEN: ${{ secrets.FORGEJO_REGISTRY_TOKEN }}
+
+      - name: Pull SHA image and tag as latest
+        run: |
+          docker pull "${IMAGE}:${{ steps.sha.outputs.short_sha }}" && \
+          docker tag "${IMAGE}:${{ steps.sha.outputs.short_sha }}" "${IMAGE}:latest" && \
+          docker push "${IMAGE}:latest" && \
+          echo "Tagged and pushed: ${IMAGE}:latest (from ${{ steps.sha.outputs.short_sha }})"
+
+      - name: Prune images
+        run: docker image prune -a --force 2>&1 | tail -3 || true

CLAUDE.md

@@ -0,0 +1,136 @@
+# Poimen Memory System
+
+## Project Status
+
+**Architecture**: Temporal Knowledge Graph for Agent Memory (Zep paper alignment — arXiv:2501.13956)
+
+**Current**: Ingest pipeline with LLM entity + fact extraction working E2E. Deployed to K8s.
+
+### What Works
+- ✅ HTTP server (actix-web) with 15+ endpoints
+- ✅ LLM entity extraction (LlmEntityExtractor) — extracts person/tool/concept/org entities
+- ✅ LLM fact extraction (LlmFactExtractor) — extracts relationships between entities
+- ✅ Reasoning model support — strips `<think>` tags, markdown fences
+- ✅ Ollama + vLLM + OpenAI-compatible API support
+- ✅ Entity persistence to pgvector (memory_entity table)
+- ✅ Edge persistence (memory_edge table with temporal fields)
+- ✅ Graph query endpoints (entities, edges, BFS traversal)
+- ✅ Visualization (React Flow JSON, force-directed layout, SSE streaming)
+- ✅ JWT auth (Authentik OIDC) with RBAC
+- ✅ K8s deployment (CNPG postgres, ConfigMap, SOPS secrets)
+- ✅ CI: PR builds push :SHA tag, main merges retag :latest
+- ✅ 781 tests passing
+
+### Deployment
+- **Namespace**: `poimen`
+- **Image**: `forgejo.riotpiao.com/riotpiao-poimen/poimen-memory:latest`
+- **DB**: CNPG cluster `memory-db` (pgvector)
+- **LLM**: `reasoning-predictor.llm-serving.svc.cluster.local` (ornith:35b / qwen2.5:3b)
+- **Auth**: Authentik OIDC (`MEM_AUTH_MODE=none` for dev)
+- **Registry**: Forgejo container registry (FORGEJO_REGISTRY_USER/TOKEN secrets)
+
+### Key Env Vars
+```
+DATABASE_URL          postgresql://...
+MEM_AUTH_MODE         none|jwt|apikey
+LLM_ENDPOINT          http://localhost:11434/v1/chat/completions  (Ollama)
+LLM_MODEL             qwen2.5:3b | ornith:35b | reasoning
+LLM_API_KEY           (for authenticated LLM APIs)
+MEM_API_KEY           (server API key, fallback "test-key")
+OPENSEARCH_HOSTS      (optional, hybrid search)
+GATEWAY_URL           (optional, external queue)
+```
+
+## Rules
+
+1. **No progress markdown files.** Track via Forgejo issues + PRs only.
+2. **Obsidian vault repo**: `ssh://[email protected]:2222/rock/poimen-obesdient-memory.git`
+3. **Secrets via KSOPS**: Age-based SOPS encryption. Never commit plaintext.
+4. **Tea CLI**: `poimen` login has API token `1f717a00134f17c9d2d656c620b955e03ea41276`
+
+## Architecture (Zep Paper §2)
+
+### Three-Tier Knowledge Graph
+```
+Episode Subgraph (raw messages)
+  → Entity Subgraph (extracted entities + facts/edges)
+    → Community Subgraph (clusters, planned Phase 4)
+```
+
+### Ingest Pipeline (4 stages)
+1. **Entity extraction** — LLM extracts named entities with type + summary
+2. **Deduplication** — HashSet on normalized name
+3. **Fact extraction** — LLM extracts relationships between entity pairs
+4. **Contradiction detection** — pre-filter + review queue
+
+### Retrieval (3 methods, §3)
+- Cosine semantic similarity (pgvector HNSW)
+- BM25 full-text (OpenSearch, optional)
+- BFS graph traversal (depth 1-3)
+
+### Extractors
+- `LlmEntityExtractor`: calls LLM_ENDPOINT, parses JSON, handles reasoning models
+- `LlmFactExtractor`: takes entity list + text, extracts edges between known entities
+- `WikiLinkFallbackExtractor`: pattern-matches `[[wiki links]]` (no LLM)
+- `SimpleFactExtractor`: verb pattern matching (no LLM)
+- Selection: LLM extractors when `LLM_ENDPOINT` set, else fallbacks
+
+### LLM Response Cleaning
+`clean_llm_response()` handles:
+- `<think>...</think>` blocks (reasoning models)
+- Markdown code fences (```json ... ```)
+- Array responses (wrap in `{"entities": [...]}`)
+- Extract first JSON object from mixed text
+
+## Crate Structure
+
+```
+crates/
+  mem-core/     — Entity, Edge, domain types (174 tests)
+  mem-store/    — DB repos, schema, vector store
+  mem-ingest/   — Entity/fact extraction, contradiction detection (87 tests)
+  mem-llm/      — Embeddings, chat, rerank clients
+  mem-cli/      — HTTP server, handlers, query, ingest worker (496 tests)
+```
+
+## API Endpoints
+
+```
+GET  /health
+POST /memory/ingest                  — Queue ingest job
+GET  /memory/ingest/{id}             — Check job status
+GET  /memory/query?project=&question= — Graph query
+POST /memory/query                   — Unified query
+POST /memory/context                 — Three-tier retrieval
+POST /memory/learn                   — Direct learn
+POST /memory/visualize               — React Flow JSON
+POST /memory/visualize/stream        — SSE streaming
+POST /memory/compact                 — Trigger compaction
+GET  /memory/projects                — List projects
+GET  /memory/skills                  — List skills
+GET  /memory/vault                   — Browse vault
+POST /memory/synthesis/*             — Entity linking, alias detection
+```
+
+## Current PRs / Branches
+
+- **PR #48** `feat/memory-ingest-retrieval` — LLM entity + fact extraction, deployment fixes
+- **PR #47** merged — Agent entity types (Phase 3.1)
+- **PR #46** merged — Integration test fixes, CI
+
+## Next Steps
+
+1. Merge PR #48 → new image with LLM extraction
+2. Query retrieval E2E — verify entities/edges returned in query results
+3. Visualization E2E — test /memory/visualize with extracted graph
+4. Restore 198 deleted tests from PR #46
+5. Community detection (Phase 4, Zep §2.3)
+6. Temporal edge invalidation (Zep §2.2.3)
+7. Reranker (cross-encoder, RRF, episode-mentions — Zep §3.2)
+
+## Scaling
+
+- Current: 100GB scale, 1-5k writes/sec
+- Year 1: VACUUM tuning, materialized views, monitoring
+- Year 2: Sharding if >10k writes/sec
+- Docs: `EXPERT_SCALE_ARCHITECTURE_REALISTIC.md`

crates/mem-cli/src/cache_alignment.rs

@@ -224,9 +224,20 @@ impl KvCacheAligner {
 
     /// Pre-load hot chunks into cache
     pub fn preload_hot_chunks(&self, hot_chunks: Vec<(&str, &str)>) -> Result<()> {
+        let count = hot_chunks.len();
         for (chunk_id, text) in hot_chunks {
             self.cache.put(chunk_id, text);
         }
+        let metrics = self.cache.metrics();
+        tracing::info!(
+            target: "observability",
+            event = "cache_preload",
+            preloaded = count,
+            cache_hits = metrics.hits,
+            cache_misses = metrics.misses,
+            hit_ratio = format!("{:.2}", metrics.hit_ratio()),
+            "Cache preload complete"
+        );
         Ok(())
     }
 

crates/mem-cli/src/chunk_optimizer.rs

@@ -211,17 +211,32 @@ impl ChunkOptimizer {
 
     /// End-to-end optimization pipeline
     pub fn optimize(&self, chunks: Vec<OptimizableChunk>) -> (Vec<OptimizableChunk>, SelectionMetrics) {
+        let input_count = chunks.len();
+
         // Step 1: Filter by threshold
         let filtered = self.threshold_filter.filter(chunks.clone());
+        let after_filter = filtered.len();
 
         // Step 2: Deduplicate
         let (deduplicated, dedup_removed) = self.deduplicator.deduplicate(filtered);
+        let after_dedup = deduplicated.len();
 
         // Step 3: Select within budget
         let (selected, mut metrics) = self.budget_selector.select(deduplicated);
-
         metrics.dedup_removed = dedup_removed;
 
+        tracing::info!(
+            target: "observability",
+            event = "chunk_optimize",
+            input = input_count,
+            after_threshold_filter = after_filter,
+            after_dedup = after_dedup,
+            dedup_removed = dedup_removed,
+            selected = selected.len(),
+            budget_bytes = metrics.total_bytes,
+            "Chunk optimization complete"
+        );
+
         (selected, metrics)
     }
 }

crates/mem-cli/src/compaction.rs

@@ -346,7 +346,19 @@ pub async fn compact_memory(
     }
 
     total_stats.duration_ms = start.elapsed().as_millis() as u64;
-    info!("Compaction complete in {}ms: {:?}", total_stats.duration_ms, total_stats);
+    info!(
+        target: "observability",
+        event = "compaction_complete",
+        mode = ?mode,
+        duration_ms = total_stats.duration_ms,
+        duplicate_edges_deleted = total_stats.duplicate_edges_deleted,
+        stale_facts_deleted = total_stats.stale_facts_deleted,
+        semantic_merged = total_stats.semantic_merged,
+        llm_calls = total_stats.llm_calls,
+        bytes_freed = total_stats.bytes_freed,
+        human_reviews_queued = total_stats.human_reviews_queued,
+        "Compaction complete"
+    );
 
     Ok(total_stats)
 }

crates/mem-cli/src/full_pipeline.rs

@@ -344,6 +344,22 @@ impl FullPipeline {
 
         metrics.total_latency_ms = start.elapsed().as_millis() as u64;
 
+        tracing::info!(
+            target: "observability",
+            event = "full_pipeline_complete",
+            query = query,
+            candidates = metrics.wiki_scope_docs,
+            prefiltered = metrics.prefilter_candidates,
+            optimized = metrics.post_optimization_count,
+            dedup_removed = metrics.dedup_removed,
+            boosts_applied = metrics.metadata_boosts_applied,
+            cache_hit_ratio = format!("{:.2}", metrics.cache_hit_ratio),
+            budget_bytes = metrics.budget_used_bytes,
+            total_ms = metrics.total_latency_ms,
+            "Full query pipeline complete"
+        );
+
+
         Ok(PipelineResult {
             query: query.to_string(),
             query_intent,
@@ -467,6 +483,22 @@ impl FullPipeline {
 
         metrics.total_latency_ms = start.elapsed().as_millis() as u64;
 
+        tracing::info!(
+            target: "observability",
+            event = "full_pipeline_complete",
+            query = query,
+            candidates = metrics.wiki_scope_docs,
+            prefiltered = metrics.prefilter_candidates,
+            optimized = metrics.post_optimization_count,
+            dedup_removed = metrics.dedup_removed,
+            boosts_applied = metrics.metadata_boosts_applied,
+            cache_hit_ratio = format!("{:.2}", metrics.cache_hit_ratio),
+            budget_bytes = metrics.budget_used_bytes,
+            total_ms = metrics.total_latency_ms,
+            "Full query pipeline complete"
+        );
+
+
         Ok(PipelineResult {
             query: query.to_string(),
             query_intent,

crates/mem-cli/src/ingest_worker.rs

@@ -2,14 +2,15 @@ use anyhow::Result;
 use mem_store::{MemoryL1, VectorStore, ChunkL0, EntityRepoOps, EdgeRepoOps};
 use mem_llm::EmbeddingsClient;
 use mem_ingest::ingest_pipeline::{IngestPipeline, Episode};
-use mem_ingest::entity_extractor::WikiLinkFallbackExtractor;
-use mem_ingest::fact_extractor::SimpleFactExtractor;
+use mem_ingest::entity_extractor::{WikiLinkFallbackExtractor, LlmEntityExtractor};
+use mem_ingest::fact_extractor::{SimpleFactExtractor, LlmFactExtractor};
 use mem_ingest::contradiction_detector::ContradictionHandler;
 use sqlx::PgPool;
 use uuid::Uuid;
 use std::sync::Arc;
 use pgvector::Vector;
 
+
 /// Ingest worker — processes queued records through entity/fact extraction pipeline
 pub struct IngestWorker {
     pool: PgPool,
@@ -26,11 +27,25 @@ impl IngestWorker {
     ) -> Self {
         let vector_store = Arc::new(VectorStore::new(pool.clone()));
         
-        // Initialize extraction pipeline
+        // Initialize extraction pipeline — use LLM if LLM_ENDPOINT is set, else fallback to wiki links
         let entity_extractor: Arc<dyn mem_ingest::entity_extractor::EntityExtractor> = 
-            Arc::new(WikiLinkFallbackExtractor);
+            if std::env::var("LLM_ENDPOINT").is_ok() {
+                let model = std::env::var("LLM_MODEL").unwrap_or_else(|_| "qwen2.5:3b-instruct".to_string());
+                tracing::info!("Using LLM entity extractor: model={}", model);
+                Arc::new(LlmEntityExtractor::new(&model))
+            } else {
+                tracing::info!("LLM_ENDPOINT not set, using WikiLink fallback extractor");
+                Arc::new(WikiLinkFallbackExtractor)
+            };
         let fact_extractor: Arc<dyn mem_ingest::fact_extractor::FactExtractor> = 
-            Arc::new(SimpleFactExtractor);
+            if std::env::var("LLM_ENDPOINT").is_ok() {
+                let model = std::env::var("LLM_MODEL").unwrap_or_else(|_| "qwen2.5:3b-instruct".to_string());
+                tracing::info!("Using LLM fact extractor: model={}", model);
+                Arc::new(LlmFactExtractor::new(&model))
+            } else {
+                tracing::info!("LLM_ENDPOINT not set, using simple pattern fact extractor");
+                Arc::new(SimpleFactExtractor)
+            };
         let contradiction_detector = Arc::new(ContradictionHandler::default());
         let pipeline = Arc::new(IngestPipeline::new(
             entity_extractor,
@@ -121,9 +136,15 @@ impl IngestWorker {
             .await?;
 
         tracing::info!(
-            "Ingest completed: {} (entities={}, edges={}, reviews={})",
-            ingest_id, total_entities, total_edges, total_reviews
+            target: "observability",
+            event = "ingest_complete",
+            ingest_id = ingest_id,
+            entities = total_entities,
+            edges = total_edges,
+            reviews = total_reviews,
+            "Ingest completed"
         );
+
         Ok(())
     }
 
@@ -173,7 +194,12 @@ async fn save_entity_to_db(pool: &PgPool, entity: &mem_core::entity::Entity) ->
     sqlx::query(
         "INSERT INTO memory_entity (id, project_id, name, entity_type, description, t_created, t_updated, confidence)
          VALUES ($1, $2, $3, $4, $5, $6::TIMESTAMPTZ, $7::TIMESTAMPTZ, $8)
-         ON CONFLICT (id) DO NOTHING"
+         ON CONFLICT (project_id, name) DO UPDATE SET
+           entity_type = EXCLUDED.entity_type,
+           description = COALESCE(NULLIF(EXCLUDED.description, ''), memory_entity.description),
+           t_updated = NOW(),
+           confidence = GREATEST(memory_entity.confidence, EXCLUDED.confidence),
+           source_count = memory_entity.source_count + 1"
     )
     .bind(&entity.id)
     .bind(&entity.project_id)
@@ -193,7 +219,7 @@ async fn save_entity_to_db(pool: &PgPool, entity: &mem_core::entity::Entity) ->
 async fn save_edge_to_db(pool: &PgPool, edge: &mem_core::edge::Edge) -> Result<()> {
     // Try temporal schema first (id, project_id, source_entity_id, etc)
     let result = sqlx::query(
-        "INSERT INTO memory_edge (id, project_id, source_entity_id, target_entity_id, relation_type, fact, t_valid, t_invalid, t_created, confidence)
+        "INSERT INTO memory_edge (id, project_id, source_id, target_id, relation_type, fact, t_valid, t_invalid, t_created, confidence)
          VALUES ($1, $2, $3, $4, $5, $6, $7::TIMESTAMPTZ, $8::TIMESTAMPTZ, $9::TIMESTAMPTZ, $10)
          ON CONFLICT (id) DO NOTHING"
     )

crates/mem-cli/src/query_router.rs

@@ -238,6 +238,17 @@ impl QueryRouter {
 
         let latency_ms = start.elapsed().as_millis() as u64;
 
+        tracing::info!(
+            target: "observability",
+            event = "query_route",
+            route = "direct",
+            candidates = all_candidates.len(),
+            prefiltered = prefilter_size,
+            selected = selected_chunks.len(),
+            latency_ms = latency_ms,
+            "Query routing complete"
+        );
+
         Ok(RoutedResult {
             selected_chunks,
             route,

crates/mem-cli/src/result_compressor.rs

@@ -235,6 +235,18 @@ impl BudgetCompressor {
         let strategy = self.select_strategy(estimated);
         let compressed = self.compressor.compress_batch(results, strategy);
 
+        let compressed_size: usize = compressed.iter().map(|c| c.text.as_ref().map_or(0, |t| t.len())).sum();
+        tracing::info!(
+            target: "observability",
+            event = "result_compress",
+            input_count = compressed.len(),
+            estimated_bytes = estimated,
+            compressed_bytes = compressed_size,
+            budget_bytes = self.max_budget_bytes,
+            strategy = ?strategy,
+            "Result compression complete"
+        );
+
         (compressed, strategy)
     }
 }

crates/mem-core/src/agent_entity.rs

@@ -0,0 +1,300 @@
+/// Agent-specific entity metadata for Phase 3 Agent Self-Awareness.
+///
+/// These structures attach to Entity via entity_type discriminator.
+/// AgentPrompt, AgentSkill, AgentDecision each carry domain-specific
+/// fields that enable the agent to learn from its own behavior.
+
+use serde::{Deserialize, Serialize};
+use time::OffsetDateTime;
+
+use crate::entity::{Entity, EntityType};
+
+/// Metadata for an AgentPrompt entity.
+/// Tracks prompt templates, their usage frequency, and effectiveness.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AgentPromptMeta {
+    /// The prompt template text (may contain {{placeholders}}).
+    pub template: String,
+    /// Which LLM model this prompt targets (e.g. "claude-3-sonnet").
+    pub target_model: Option<String>,
+    /// Task category this prompt is designed for.
+    pub task_category: String,
+    /// Number of times this prompt has been used.
+    pub usage_count: u64,
+    /// Average quality score from outcomes (0.0-1.0).
+    pub avg_quality: f32,
+    /// Last time this prompt was used.
+    #[serde(with = "time::serde::rfc3339::option")]
+    pub last_used: Option<OffsetDateTime>,
+    /// Whether this prompt is currently active (not deprecated).
+    pub active: bool,
+    /// Version for tracking prompt evolution.
+    pub version: u32,
+    /// Tags for categorization.
+    pub tags: Vec<String>,
+}
+
+/// Metadata for an AgentSkill entity.
+/// Tracks learned capabilities and their effectiveness.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AgentSkillMeta {
+    /// Description of what this skill does.
+    pub description: String,
+    /// Trigger conditions that activate this skill.
+    pub trigger_patterns: Vec<String>,
+    /// Success rate over all invocations (0.0-1.0).
+    pub success_rate: f32,
+    /// Number of times this skill was invoked.
+    pub invocation_count: u64,
+    /// Average latency in milliseconds.
+    pub avg_latency_ms: u64,
+    /// Linked prompt entity IDs that this skill uses.
+    pub linked_prompts: Vec<String>,
+    /// Whether this skill is currently enabled.
+    pub enabled: bool,
+}
+
+/// Metadata for an AgentDecision entity.
+/// Records a decision the agent made, including reasoning and outcome.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AgentDecisionMeta {
+    /// What the agent decided to do.
+    pub action: String,
+    /// Why the agent chose this action.
+    pub reasoning: String,
+    /// Available alternatives that were considered.
+    pub alternatives: Vec<String>,
+    /// Confidence in the decision (0.0-1.0).
+    pub confidence: f32,
+    /// Outcome of the decision (set after execution).
+    pub outcome: Option<DecisionOutcome>,
+    /// Context that informed the decision (entity IDs).
+    pub context_entities: Vec<String>,
+    /// The tool/task context when decision was made.
+    pub tool: Option<String>,
+    pub task: Option<String>,
+}
+
+/// Outcome of an agent decision.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct DecisionOutcome {
+    /// Whether the decision led to success.
+    pub success: bool,
+    /// Quality score of the outcome (0.0-1.0).
+    pub quality: f32,
+    /// Feedback or error message.
+    pub feedback: Option<String>,
+    /// When the outcome was recorded.
+    #[serde(with = "time::serde::rfc3339")]
+    pub recorded_at: OffsetDateTime,
+}
+
+// --- Factory functions ---
+
+/// Create a new AgentPrompt entity.
+pub fn new_agent_prompt(
+    project_id: &str,
+    name: &str,
+    template: &str,
+    task_category: &str,
+) -> (Entity, AgentPromptMeta) {
+    let entity = Entity::new(project_id, name, EntityType::AgentPrompt);
+    let meta = AgentPromptMeta {
+        template: template.to_string(),
+        target_model: None,
+        task_category: task_category.to_string(),
+        usage_count: 0,
+        avg_quality: 0.0,
+        last_used: None,
+        active: true,
+        version: 1,
+        tags: vec![],
+    };
+    (entity, meta)
+}
+
+/// Create a new AgentSkill entity.
+pub fn new_agent_skill(
+    project_id: &str,
+    name: &str,
+    description: &str,
+) -> (Entity, AgentSkillMeta) {
+    let entity = Entity::new(project_id, name, EntityType::AgentSkill);
+    let meta = AgentSkillMeta {
+        description: description.to_string(),
+        trigger_patterns: vec![],
+        success_rate: 0.0,
+        invocation_count: 0,
+        avg_latency_ms: 0,
+        linked_prompts: vec![],
+        enabled: true,
+    };
+    (entity, meta)
+}
+
+/// Create a new AgentDecision entity.
+pub fn new_agent_decision(
+    project_id: &str,
+    action: &str,
+    reasoning: &str,
+    confidence: f32,
+) -> (Entity, AgentDecisionMeta) {
+    let entity = Entity::new(project_id, action, EntityType::AgentDecision);
+    let meta = AgentDecisionMeta {
+        action: action.to_string(),
+        reasoning: reasoning.to_string(),
+        alternatives: vec![],
+        confidence,
+        outcome: None,
+        context_entities: vec![],
+        tool: None,
+        task: None,
+    };
+    (entity, meta)
+}
+
+/// Record outcome for a decision.
+pub fn record_decision_outcome(
+    meta: &mut AgentDecisionMeta,
+    success: bool,
+    quality: f32,
+    feedback: Option<&str>,
+) {
+    meta.outcome = Some(DecisionOutcome {
+        success,
+        quality,
+        feedback: feedback.map(|s| s.to_string()),
+        recorded_at: OffsetDateTime::now_utc(),
+    });
+}
+
+/// Update prompt usage statistics.
+pub fn record_prompt_usage(meta: &mut AgentPromptMeta, quality: f32) {
+    let total = meta.avg_quality * meta.usage_count as f32 + quality;
+    meta.usage_count += 1;
+    meta.avg_quality = total / meta.usage_count as f32;
+    meta.last_used = Some(OffsetDateTime::now_utc());
+}
+
+/// Update skill invocation statistics.
+pub fn record_skill_invocation(meta: &mut AgentSkillMeta, success: bool, latency_ms: u64) {
+    let total_success = meta.success_rate * meta.invocation_count as f32
+        + if success { 1.0 } else { 0.0 };
+    let total_latency = meta.avg_latency_ms * meta.invocation_count + latency_ms;
+    meta.invocation_count += 1;
+    meta.success_rate = total_success / meta.invocation_count as f32;
+    meta.avg_latency_ms = total_latency / meta.invocation_count;
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_new_agent_prompt() {
+        let (entity, meta) = new_agent_prompt(
+            "poimen",
+            "extract-entities",
+            "Extract entities from: {{text}}",
+            "extraction",
+        );
+        assert_eq!(entity.entity_type, EntityType::AgentPrompt);
+        assert_eq!(entity.name, "extract-entities");
+        assert_eq!(meta.template, "Extract entities from: {{text}}");
+        assert_eq!(meta.task_category, "extraction");
+        assert_eq!(meta.usage_count, 0);
+        assert!(meta.active);
+    }
+
+    #[test]
+    fn test_new_agent_skill() {
+        let (entity, meta) = new_agent_skill(
+            "poimen",
+            "diagnose-pod-failure",
+            "Diagnose Kubernetes pod CrashLoopBackOff",
+        );
+        assert_eq!(entity.entity_type, EntityType::AgentSkill);
+        assert_eq!(meta.description, "Diagnose Kubernetes pod CrashLoopBackOff");
+        assert!(meta.enabled);
+        assert_eq!(meta.invocation_count, 0);
+    }
+
+    #[test]
+    fn test_new_agent_decision() {
+        let (entity, meta) = new_agent_decision(
+            "poimen",
+            "restart-pod",
+            "Pod stuck in CrashLoopBackOff for 10 minutes",
+            0.85,
+        );
+        assert_eq!(entity.entity_type, EntityType::AgentDecision);
+        assert_eq!(meta.action, "restart-pod");
+        assert_eq!(meta.confidence, 0.85);
+        assert!(meta.outcome.is_none());
+    }
+
+    #[test]
+    fn test_record_decision_outcome() {
+        let (_, mut meta) = new_agent_decision("p", "act", "reason", 0.9);
+        assert!(meta.outcome.is_none());
+
+        record_decision_outcome(&mut meta, true, 0.95, Some("Pod recovered"));
+        assert!(meta.outcome.is_some());
+        let outcome = meta.outcome.unwrap();
+        assert!(outcome.success);
+        assert_eq!(outcome.quality, 0.95);
+        assert_eq!(outcome.feedback, Some("Pod recovered".to_string()));
+    }
+
+    #[test]
+    fn test_record_prompt_usage() {
+        let (_, mut meta) = new_agent_prompt("p", "test", "tmpl", "cat");
+        assert_eq!(meta.usage_count, 0);
+        assert_eq!(meta.avg_quality, 0.0);
+
+        record_prompt_usage(&mut meta, 0.8);
+        assert_eq!(meta.usage_count, 1);
+        assert_eq!(meta.avg_quality, 0.8);
+
+        record_prompt_usage(&mut meta, 1.0);
+        assert_eq!(meta.usage_count, 2);
+        assert!((meta.avg_quality - 0.9).abs() < 0.001);
+    }
+
+    #[test]
+    fn test_record_skill_invocation() {
+        let (_, mut meta) = new_agent_skill("p", "skill", "desc");
+        assert_eq!(meta.invocation_count, 0);
+
+        record_skill_invocation(&mut meta, true, 100);
+        assert_eq!(meta.invocation_count, 1);
+        assert_eq!(meta.success_rate, 1.0);
+        assert_eq!(meta.avg_latency_ms, 100);
+
+        record_skill_invocation(&mut meta, false, 200);
+        assert_eq!(meta.invocation_count, 2);
+        assert_eq!(meta.success_rate, 0.5);
+        assert_eq!(meta.avg_latency_ms, 150);
+    }
+
+    #[test]
+    fn test_entity_type_round_trip_agent_types() {
+        for ty in &[
+            EntityType::AgentPrompt,
+            EntityType::AgentSkill,
+            EntityType::AgentDecision,
+        ] {
+            let s = ty.as_str();
+            assert_eq!(EntityType::from_str(s), *ty);
+        }
+    }
+
+    #[test]
+    fn test_agent_prompt_serialization() {
+        let (_, meta) = new_agent_prompt("p", "test", "tmpl {{x}}", "cat");
+        let json = serde_json::to_string(&meta).unwrap();
+        let deserialized: AgentPromptMeta = serde_json::from_str(&json).unwrap();
+        assert_eq!(deserialized.template, "tmpl {{x}}");
+        assert_eq!(deserialized.task_category, "cat");
+    }
+}

crates/mem-core/src/entity.rs

@@ -8,7 +8,7 @@ use time::OffsetDateTime;
 use std::fmt;
 
 /// Entity type classification (extensible enum).
-#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize, Hash)]
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Hash)]
 #[serde(rename_all = "snake_case")]
 pub enum EntityType {
     Person,
@@ -17,6 +17,13 @@ pub enum EntityType {
     Location,
     Event,
     Organization,
+    /// Agent prompt template tracked as a first-class entity.
+    /// Enables the agent to learn which prompts produce good results.
+    AgentPrompt,
+    /// Agent skill — a reusable capability the agent has learned.
+    AgentSkill,
+    /// Agent decision — a recorded choice with reasoning and outcome.
+    AgentDecision,
     Unknown,
 }
 
@@ -29,6 +36,9 @@ impl EntityType {
             Self::Location => "location",
             Self::Event => "event",
             Self::Organization => "organization",
+            Self::AgentPrompt => "agent_prompt",
+            Self::AgentSkill => "agent_skill",
+            Self::AgentDecision => "agent_decision",
             Self::Unknown => "unknown",
         }
     }
@@ -41,11 +51,24 @@ impl EntityType {
             "location" => Self::Location,
             "event" => Self::Event,
             "organization" => Self::Organization,
+            "agent_prompt" => Self::AgentPrompt,
+            "agent_skill" => Self::AgentSkill,
+            "agent_decision" => Self::AgentDecision,
             _ => Self::Unknown,
         }
     }
 }
 
+impl<'de> serde::Deserialize<'de> for EntityType {
+    fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
+    where
+        D: serde::Deserializer<'de>,
+    {
+        let s = String::deserialize(deserializer)?;
+        Ok(Self::from_str(&s))
+    }
+}
+
 impl fmt::Display for EntityType {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         write!(f, "{}", self.as_str())
@@ -175,6 +198,9 @@ mod tests {
             EntityType::Person,
             EntityType::Tool,
             EntityType::Concept,
+            EntityType::AgentPrompt,
+            EntityType::AgentSkill,
+            EntityType::AgentDecision,
         ] {
             let s = ty.as_str();
             assert_eq!(EntityType::from_str(s), *ty);

crates/mem-core/src/lib.rs

@@ -12,6 +12,7 @@ pub mod scoring;
 pub mod entity;
 pub mod edge;
 pub mod community;
+pub mod agent_entity;
 
 pub use gate_parser::{GateResponse, ParseError, parse_gate_response};
 
@@ -30,3 +31,4 @@ pub use scoring::{DocumentScorer, ScoringPipeline, GlobalTfIdfScorer, ProjectTfI
 pub use entity::{Entity, EntityType};
 pub use edge::{Edge, ContradictionStatus};
 pub use community::Community;
+pub use agent_entity::{AgentPromptMeta, AgentSkillMeta, AgentDecisionMeta, DecisionOutcome};

crates/mem-ingest/src/authentik_jwt.rs

@@ -52,13 +52,24 @@ impl AuthentikJwtIssuer {
 
     /// From environment: AUTHENTIK_ISSUER, AUTHENTIK_CLIENT_ID, AUTHENTIK_CLIENT_SECRET
     pub fn from_env() -> Result<Self> {
+        // Support both naming conventions: AUTHENTIK_* and memory-agent-oidc secret keys
         let issuer = std::env::var("AUTHENTIK_ISSUER")
-            .map_err(|_| anyhow!("AUTHENTIK_ISSUER not set"))?;
+            .or_else(|_| std::env::var("ISSUER"))
+            .map_err(|_| anyhow!("AUTHENTIK_ISSUER or ISSUER not set"))?;
         let client_id = std::env::var("AUTHENTIK_CLIENT_ID")
-            .map_err(|_| anyhow!("AUTHENTIK_CLIENT_ID not set"))?;
+            .or_else(|_| std::env::var("CLIENT_ID"))
+            .map_err(|_| anyhow!("AUTHENTIK_CLIENT_ID or CLIENT_ID not set"))?;
         let client_secret = std::env::var("AUTHENTIK_CLIENT_SECRET")
-            .map_err(|_| anyhow!("AUTHENTIK_CLIENT_SECRET not set"))?;
+            .or_else(|_| std::env::var("CLIENT_SECRET"))
+            .map_err(|_| anyhow!("AUTHENTIK_CLIENT_SECRET or CLIENT_SECRET not set"))?;
 
+        tracing::info!(
+            target: "observability",
+            event = "authentik_jwt_init",
+            issuer = %issuer,
+            client_id = %client_id,
+            "Authentik JWT issuer initialized"
+        );
         Ok(Self::new(&issuer, &client_id, &client_secret))
     }
 
@@ -92,12 +103,25 @@ impl AuthentikJwtIssuer {
         let client = reqwest::Client::new();
         
         // Authentik OAuth2 token endpoint
-        let token_url = format!("{}/token/", self.issuer_url.trim_end_matches('/'));
+        // Use TOKEN_URL env var if set, otherwise derive from issuer
+        let token_url = std::env::var("TOKEN_URL")
+            .or_else(|_| std::env::var("AUTHENTIK_TOKEN_URL"))
+            .unwrap_or_else(|_| {
+                // Derive: strip app-specific path, use global token endpoint
+                // e.g., https://authentik.riotpiao.com/application/o/memory-agent/
+                //     -> https://authentik.riotpiao.com/application/o/token/
+                if let Some(base) = self.issuer_url.rfind("/o/") {
+                    format!("{}/o/token/", &self.issuer_url[..base])
+                } else {
+                    format!("{}/token/", self.issuer_url.trim_end_matches('/'))
+                }
+            });
         
         let params = [
             ("grant_type", "client_credentials"),
             ("client_id", &self.client_id),
             ("client_secret", &self.client_secret),
+            ("scope", "openid roles"),
         ];
 
         let response = client

crates/mem-ingest/src/entity_extractor.rs

@@ -22,11 +22,15 @@ use tokio::sync::Mutex;
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ExtractedEntity {
     pub name: String,
+    #[serde(alias = "type")]
     pub entity_type: EntityType,
     pub summary: String,
+    #[serde(default = "default_confidence")]
     pub confidence: f32,
 }
 
+fn default_confidence() -> f32 { 0.8 }
+
 impl ExtractedEntity {
     /// Convert to domain model (Phase 1 type)
     pub fn to_domain(&self, project_id: &str) -> Entity {
@@ -62,6 +66,35 @@ impl LlmEntityExtractor {
 
     /// Parse extraction response JSON
     /// Format: { "entities": [{ "name": "...", "type": "...", "summary": "..." }, ...] }
+    /// Clean LLM response: strip thinking tags, markdown fences, extract JSON
+    fn clean_llm_response(text: &str) -> String {
+        let mut result = text.to_string();
+        // Remove <think>...</think> blocks
+        while let Some(start) = result.find("<think>") {
+            if let Some(end) = result.find("</think>") {
+                result = format!("{}{}", &result[..start], &result[end + 8..]);
+            } else {
+                break;
+            }
+        }
+        // Remove markdown code fences
+        result = result.replace("```json", "").replace("```", "");
+        // Find JSON object
+        let trimmed = result.trim();
+        if let Some(start) = trimmed.find('{') {
+            if let Some(end) = trimmed.rfind('}') {
+                return trimmed[start..=end].to_string();
+            }
+        }
+        // Maybe it's a JSON array — wrap in object
+        if let Some(start) = trimmed.find('[') {
+            if let Some(end) = trimmed.rfind(']') {
+                return format!("{{\"entities\": {}}}", &trimmed[start..=end]);
+            }
+        }
+        trimmed.to_string()
+    }
+
     fn parse_extraction(response: &str) -> Result<Vec<ExtractedEntity>> {
         #[derive(Deserialize)]
         struct Response {
@@ -123,7 +156,7 @@ impl LlmEntityExtractor {
                 {"role": "user", "content": prompt}
             ],
             "temperature": 0.3,
-            "max_tokens": 500
+            "max_tokens": 12000
         });
         
         let response = client
@@ -131,7 +164,7 @@ impl LlmEntityExtractor {
             .header("Authorization", auth_header)
             .header("Content-Type", "application/json")
             .json(&payload)
-            .timeout(std::time::Duration::from_secs(30))
+            .timeout(std::time::Duration::from_secs(90))
             .send()
             .await?;
         
@@ -146,12 +179,28 @@ impl LlmEntityExtractor {
         }
         
         let data: serde_json::Value = response.json().await?;
-        let content = data["choices"][0]["message"]["content"]
-            .as_str()
-            .unwrap_or("{}")
-            .to_string();
+        // Extract content — some models put JSON in "content", others in "reasoning"
+        let msg = &data["choices"][0]["message"];
+        let raw_content = msg["content"].as_str().unwrap_or("").to_string();
+        let raw_reasoning = msg["reasoning"].as_str().unwrap_or("").to_string();
         
-        tracing::debug!("LLM response (via Authentik JWT): {}", content);
+        // Use content if non-empty, otherwise try reasoning field
+        let raw = if !raw_content.trim().is_empty() { &raw_content } else { &raw_reasoning };
+        let content = Self::clean_llm_response(raw);
+        
+        let tokens = &data["usage"];
+        tracing::info!(
+            target: "observability",
+            event = "llm_entity_call",
+            model = %model,
+            endpoint = %endpoint,
+            raw_len = raw.len(),
+            cleaned_len = content.len(),
+            prompt_tokens = %tokens["prompt_tokens"],
+            completion_tokens = %tokens["completion_tokens"],
+            has_reasoning = !raw_reasoning.is_empty(),
+            "LLM entity extraction call complete"
+        );
         Ok(content)
     }
     
@@ -233,14 +282,27 @@ Respond in JSON:
             );
 
             let reflection = if std::env::var("LLM_ENDPOINT").is_ok() {
-                self.call_llm_endpoint(&reflection_prompt).await.unwrap_or_else(|_| self.simulate_llm(&reflection_prompt).unwrap_or_default())
+                self.call_llm_endpoint(&reflection_prompt).await.unwrap_or_else(|e| {
+                    tracing::warn!("Reflection LLM call failed: {}, skipping verification", e);
+                    String::new()
+                })
             } else {
                 self.simulate_llm(&reflection_prompt)?
             };
-            let verified = Self::parse_reflection(&reflection)?;
 
-            // Filter: keep only entities marked present
+            // If reflection succeeded, filter entities; otherwise keep all
+            if !reflection.is_empty() {
+                match Self::parse_reflection(&reflection) {
+                    Ok(verified) => {
                         entities.retain(|e| verified.iter().any(|(name, present)| name == &e.name && *present));
+                    }
+                    Err(e) => {
+                        tracing::warn!("Reflection parse failed: {}, keeping all entities", e);
+                    }
+                }
+            } else {
+                tracing::info!("Reflection skipped, keeping {} unverified entities", entities.len());
+            }
 
             // Adjust confidence for reflected entities (slight penalty for needing verification)
             for entity in &mut entities {

crates/mem-ingest/src/fact_extractor.rs

@@ -1,12 +1,12 @@
 //! Fact extraction: Identify relationships between entities
 //!
-//! Two implementations:
+//! Three implementations:
 //! 1. SimpleFactExtractor: Pattern-based (verbs + wiki links)
-//! 2. LlmFactExtractor: LLM-based (placeholder for production)
+//! 2. LlmFactExtractor: LLM-based extraction with entity context
+//! 3. Fallback chain: LLM → Simple pattern matching
 //!
-//! CRAP: 12 (Simple pattern matching + LLM placeholder)
-//! SOLID: Trait-based (Open/Closed)
-//! DRY: Reuses EntityExtractor pattern
+//! Aligned with Zep paper §2.2.2: Facts as edges between entity pairs,
+//! with temporal extraction and dedup against existing edges.
 
 use anyhow::Result;
 use async_trait::async_trait;
@@ -27,20 +27,18 @@ pub struct ExtractedFact {
 pub trait FactExtractor: Send + Sync {
     async fn extract(&self, text: &str) -> Result<Vec<ExtractedFact>>;
     
-    /// Extract facts with GRM context (optional, defaults to extract())
+    /// Extract facts with entity context (Zep §2.2.2: facts between known entities)
     async fn extract_with_context(
         &self,
         text: &str,
         _entity_contexts: &[crate::grm_retriever::EntityContext],
     ) -> Result<Vec<ExtractedFact>> {
-        // Default: ignore context, use plain extraction
         self.extract(text).await
     }
 }
 
 /// Simple fact extractor based on verb patterns
 /// Pattern: [[Entity1]] verb [[Entity2]]
-/// Common verbs: uses, manages, runs, deployed_to, works_with
 pub struct SimpleFactExtractor;
 
 #[async_trait]
@@ -48,17 +46,15 @@ impl FactExtractor for SimpleFactExtractor {
     async fn extract(&self, text: &str) -> Result<Vec<ExtractedFact>> {
         let mut facts = vec![];
 
-        // Extract [[Entity]] patterns
         let entity_pattern = Regex::new(r"\[\[([^\]]+)\]\]")?;
-        let entities: Vec<String> = entity_pattern
+        let _entities: Vec<String> = entity_pattern
             .captures_iter(text)
             .filter_map(|cap| cap.get(1).map(|m| m.as_str().to_string()))
             .collect();
 
-        // Common relationship verbs
-        let verbs = ["uses", "manages", "runs", "deployed_to", "works_with"];
+        let verbs = ["uses", "manages", "runs", "deployed_to", "works_with",
+                      "depends_on", "contains", "extends", "implements", "connects_to"];
 
-        // Simple heuristic: if two entities appear close together with a verb between them
         for verb in &verbs {
             let pattern = format!(
                 r"\[\[([^\]]+)\]\].*?{}.*?\[\[([^\]]+)\]\]",
@@ -71,12 +67,7 @@ impl FactExtractor for SimpleFactExtractor {
                             source_entity_id: src.as_str().to_string(),
                             target_entity_id: tgt.as_str().to_string(),
                             relation_type: verb.to_uppercase(),
-                            fact: format!(
-                                "{} {} {}",
-                                src.as_str(),
-                                verb,
-                                tgt.as_str()
-                            ),
+                            fact: format!("{} {} {}", src.as_str(), verb, tgt.as_str()),
                         });
                     }
                 }
@@ -87,19 +78,252 @@ impl FactExtractor for SimpleFactExtractor {
     }
 }
 
-/// LLM-based fact extractor (placeholder for production)
-/// TODO (Phase 2.6): Implement with real LLM API
-/// TODO (Phase 2.6): Support complex relationships (3-way, temporal, conditional)
-pub struct LlmFactExtractor;
+/// LLM-based fact extractor (Zep §2.2.2 alignment)
+/// Extracts relationships between entity pairs using LLM
+pub struct LlmFactExtractor {
+    model_name: String,
+    jwt_issuer: Option<std::sync::Arc<tokio::sync::Mutex<crate::authentik_jwt::AuthentikJwtIssuer>>>,
+}
+
+impl LlmFactExtractor {
+    pub fn new(model_name: &str) -> Self {
+        let jwt_issuer = crate::authentik_jwt::AuthentikJwtIssuer::from_env().ok();
+        Self {
+            model_name: model_name.to_string(),
+            jwt_issuer: jwt_issuer.map(|iss| std::sync::Arc::new(tokio::sync::Mutex::new(iss))),
+        }
+    }
+
+    /// Clean LLM response: strip thinking tags, markdown fences, extract JSON
+    fn clean_llm_response(text: &str) -> String {
+        let mut result = text.to_string();
+        while let Some(start) = result.find("<think>") {
+            if let Some(end) = result.find("</think>") {
+                result = format!("{}{}", &result[..start], &result[end + 8..]);
+            } else { break; }
+        }
+        result = result.replace("```json", "").replace("```", "");
+        let trimmed = result.trim();
+        if let Some(start) = trimmed.find('{') {
+            if let Some(end) = trimmed.rfind('}') {
+                return trimmed[start..=end].to_string();
+            }
+        }
+        if let Some(start) = trimmed.find('[') {
+            if let Some(end) = trimmed.rfind(']') {
+                return format!("{{\"facts\": {}}}", &trimmed[start..=end]);
+            }
+        }
+        trimmed.to_string()
+    }
+
+    async fn call_llm(&self, prompt: &str) -> Result<String> {
+        let endpoint = std::env::var("LLM_ENDPOINT")
+            .unwrap_or_else(|_| "http://localhost:11434/v1/chat/completions".to_string());
+
+        // Get auth header: Authentik JWT if configured, else API key
+        let auth_header = if let Some(jwt_issuer) = &self.jwt_issuer {
+            let issuer = jwt_issuer.lock().await;
+            match issuer.get_access_token().await {
+                Ok(token) => format!("Bearer {}", token),
+                Err(e) => {
+                    tracing::warn!(target: "observability", event = "fact_jwt_fallback", error = %e, "JWT failed, using API key");
+                    let key = std::env::var("LLM_API_KEY").unwrap_or_else(|_| "default-key".to_string());
+                    format!("Bearer {}", key)
+                }
+            }
+        } else {
+            let key = std::env::var("LLM_API_KEY")
+                .or_else(|_| std::env::var("MEM_API_KEY"))
+                .unwrap_or_else(|_| "default-key".to_string());
+            format!("Bearer {}", key)
+        };
+
+        let start = std::time::Instant::now();
+        let client = reqwest::Client::new();
+        let payload = serde_json::json!({
+            "model": self.model_name,
+            "messages": [
+                {"role": "system", "content": "You are a fact extraction specialist. Extract relationships between entities from text. Output ONLY valid JSON."},
+                {"role": "user", "content": prompt}
+            ],
+            "max_tokens": 12000,
+            "temperature": 0.1
+        });
+
+        let response = client
+            .post(&endpoint)
+            .header("Authorization", &auth_header)
+            .header("Content-Type", "application/json")
+            .json(&payload)
+            .timeout(std::time::Duration::from_secs(120))
+            .send()
+            .await?;
+
+        let status = response.status();
+        if !status.is_success() {
+            let body = response.text().await.unwrap_or_default();
+            tracing::warn!(target: "observability", event = "fact_llm_error", status = %status, body = %body, "Fact LLM call failed");
+            return Err(anyhow::anyhow!("LLM API error: {}", status));
+        }
+
+        let elapsed = start.elapsed();
+        let data: serde_json::Value = response.json().await?;
+        
+        // Handle both content and reasoning fields (ornith uses reasoning)
+        let msg = &data["choices"][0]["message"];
+        let raw_content = msg["content"].as_str().unwrap_or("").to_string();
+        let raw_reasoning = msg["reasoning"].as_str().unwrap_or("").to_string();
+        let raw = if !raw_content.trim().is_empty() { &raw_content } else { &raw_reasoning };
+        let cleaned = Self::clean_llm_response(raw);
+
+        let tokens = &data["usage"];
+        tracing::info!(
+            target: "observability",
+            event = "llm_fact_call",
+            model = %self.model_name,
+            endpoint = %endpoint,
+            raw_len = raw.len(),
+            cleaned_len = cleaned.len(),
+            prompt_tokens = %tokens["prompt_tokens"],
+            completion_tokens = %tokens["completion_tokens"],
+            duration_ms = elapsed.as_millis() as u64,
+            has_reasoning = !raw_reasoning.is_empty(),
+            "LLM fact extraction call complete"
+        );
+        Ok(cleaned)
+    }
+}
 
 #[async_trait]
 impl FactExtractor for LlmFactExtractor {
-    async fn extract(&self, _text: &str) -> Result<Vec<ExtractedFact>> {
-        // TODO (Phase 2.6): Implement LLM-based extraction
-        // Pattern: Send text to api.riotpiao.com with prompt
-        // Parse response for [source, relation, target] tuples
+    async fn extract(&self, text: &str) -> Result<Vec<ExtractedFact>> {
+        self.extract_with_context(text, &[]).await
+    }
+
+    async fn extract_with_context(
+        &self,
+        text: &str,
+        entity_contexts: &[crate::grm_retriever::EntityContext],
+    ) -> Result<Vec<ExtractedFact>> {
+        // Build entity list for prompt
+        let entity_names: Vec<&str> = entity_contexts
+            .iter()
+            .map(|e| e.entity_name.as_str())
+            .collect();
+
+        if entity_names.is_empty() {
+            tracing::debug!("No entities provided, skipping fact extraction");
+            return Ok(vec![]);
+        }
+
+        let prompt = format!(
+            r#"Extract relationships (facts) between these entities from the text.
+
+Entities: {:?}
+
+Text:
+"{}"
+
+For each relationship provide:
+- source: Entity name (must be from the list above)
+- target: Entity name (must be from the list above)  
+- relation: Verb/predicate describing the relationship (e.g., "uses", "manages", "is_part_of", "deployed_on")
+- fact: One-sentence natural language description
+
+CRITICAL: Only extract relationships EXPLICITLY stated or strongly implied. Source and target must both be from the entity list.
+
+Respond in JSON:
+{{"facts": [{{"source": "...", "target": "...", "relation": "...", "fact": "..."}}, ...]}}
+"#,
+            entity_names, text
+        );
+
+        let llm_ok = std::env::var("LLM_ENDPOINT").is_ok();
+        let response = if llm_ok {
+            match self.call_llm(&prompt).await {
+                Ok(r) => r,
+                Err(e) => {
+                    tracing::warn!("Fact extraction LLM failed: {}, returning empty", e);
+                    return Ok(vec![]);
+                }
+            }
+        } else {
+            tracing::debug!("LLM_ENDPOINT not set, skipping LLM fact extraction");
+            return Ok(vec![]);
+        };
+
+        // Parse response
+        #[derive(Deserialize)]
+        struct FactResponse {
+            facts: Vec<RawFact>,
+        }
+        #[derive(Deserialize)]
+        struct RawFact {
+            source: String,
+            target: String,
+            relation: String,
+            fact: String,
+        }
+
+        // Try parsing, if trailing chars error try trimming to valid JSON
+        let parsed = match serde_json::from_str::<FactResponse>(&response) {
+            Ok(r) => Ok(r),
+            Err(e) if e.to_string().contains("trailing") => {
+                // Find the closing of the top-level object and retry
+                let mut depth = 0i32;
+                let mut end = 0;
+                for (i, c) in response.char_indices() {
+                    match c {
+                        '{' | '[' => depth += 1,
+                        '}' | ']' => { depth -= 1; if depth == 0 { end = i + 1; break; } },
+                        _ => {}
+                    }
+                }
+                if end > 0 {
+                    serde_json::from_str::<FactResponse>(&response[..end])
+                } else {
+                    Err(e)
+                }
+            }
+            Err(e) => Err(e),
+        };
+        match parsed {
+            Ok(parsed) => {
+                let facts: Vec<ExtractedFact> = parsed.facts
+                    .into_iter()
+                    .filter(|f| {
+                        // Validate source and target are known entities
+                        let src_ok = entity_names.iter().any(|e| e.eq_ignore_ascii_case(&f.source));
+                        let tgt_ok = entity_names.iter().any(|e| e.eq_ignore_ascii_case(&f.target));
+                        if !src_ok || !tgt_ok {
+                            tracing::debug!(
+                                "Dropping fact with unknown entity: {} -> {}",
+                                f.source, f.target
+                            );
+                        }
+                        src_ok && tgt_ok && f.source != f.target
+                    })
+                    .map(|f| ExtractedFact {
+                        source_entity_id: f.source,
+                        target_entity_id: f.target,
+                        relation_type: f.relation.to_uppercase(),
+                        fact: f.fact,
+                    })
+                    .collect();
+
+                tracing::info!(
+                    "LLM fact extraction: {} facts from {} entities",
+                    facts.len(), entity_names.len()
+                );
+                Ok(facts)
+            }
+            Err(e) => {
+                tracing::warn!("Fact extraction JSON parse failed: {}", e);
                 Ok(vec![])
             }
+        }
+    }
 }
 
 #[cfg(test)]
@@ -110,9 +334,38 @@ mod tests {
     async fn test_simple_fact_extraction() {
         let extractor = SimpleFactExtractor;
         let text = "[[Rock]] uses [[Kubernetes]] and [[ArgoCD]]";
-
         let facts = extractor.extract(text).await.unwrap();
-        assert!(facts.len() > 0);
+        assert!(!facts.is_empty());
         assert!(facts.iter().any(|f| f.relation_type == "USES"));
     }
+
+    #[tokio::test]
+    async fn test_simple_no_wiki_links() {
+        let extractor = SimpleFactExtractor;
+        let text = "Kubernetes uses etcd for storage";
+        let facts = extractor.extract(text).await.unwrap();
+        assert!(facts.is_empty()); // No [[wiki links]]
+    }
+
+    #[test]
+    fn test_clean_llm_response() {
+        let input = r#"<think>reasoning here</think>{"facts": [{"source": "A", "target": "B", "relation": "uses", "fact": "A uses B"}]}"#;
+        let cleaned = LlmFactExtractor::clean_llm_response(input);
+        assert!(cleaned.starts_with("{"));
+        assert!(cleaned.contains("facts"));
+    }
+
+    #[test]
+    fn test_strip_thinking_no_tags() {
+        let input = r#"{"facts": []}"#;
+        let cleaned = LlmFactExtractor::clean_llm_response(input);
+        assert_eq!(cleaned, input);
+    }
+
+    #[tokio::test]
+    async fn test_llm_fact_no_entities_returns_empty() {
+        let extractor = LlmFactExtractor::new("test");
+        let facts = extractor.extract_with_context("some text", &[]).await.unwrap();
+        assert!(facts.is_empty());
+    }
 }

crates/mem-store/migrations/009_temporal_edge_migration.sql

@@ -0,0 +1,67 @@
+-- Migration 009: Temporal edge schema (Zep paper §2.2.2)
+-- Replaces old memory_edge (child_sha/parent_sha node graph)
+-- with temporal edge schema supporting relation types, facts, and validity periods.
+-- Idempotent: safe to run multiple times.
+
+-- Rename old table if it still exists (skip if already migrated)
+DO $$
+BEGIN
+    IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'memory_edge'
+               AND EXISTS (SELECT 1 FROM information_schema.columns 
+                          WHERE table_name = 'memory_edge' AND column_name = 'child_sha'))
+    THEN
+        ALTER TABLE memory_edge RENAME TO memory_edge_legacy;
+    END IF;
+END $$;
+
+-- Create temporal edge table
+CREATE TABLE IF NOT EXISTS memory_edge (
+    id TEXT PRIMARY KEY,
+    project_id TEXT NOT NULL DEFAULT 'default',
+    source_id TEXT NOT NULL,
+    target_id TEXT NOT NULL,
+    relation_type TEXT NOT NULL DEFAULT '',
+    fact TEXT NOT NULL DEFAULT '',
+    weight REAL NOT NULL DEFAULT 1.0,
+    strength REAL DEFAULT 1.0,
+    confidence REAL DEFAULT 0.8,
+    t_valid TIMESTAMPTZ,
+    t_invalid TIMESTAMPTZ,
+    t_created TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    t_expired TIMESTAMPTZ,
+    created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+    episode_id TEXT,
+    deleted_at TIMESTAMPTZ
+);
+
+-- Ensure app user owns the table
+DO $$ BEGIN
+    IF EXISTS (SELECT 1 FROM pg_roles WHERE rolname = 'app') THEN
+        ALTER TABLE memory_edge OWNER TO app;
+    END IF;
+END $$;
+
+CREATE INDEX IF NOT EXISTS idx_memory_edge_source ON memory_edge(source_id);
+CREATE INDEX IF NOT EXISTS idx_memory_edge_target ON memory_edge(target_id);
+CREATE INDEX IF NOT EXISTS idx_memory_edge_project ON memory_edge(project_id);
+CREATE INDEX IF NOT EXISTS idx_memory_edge_relation ON memory_edge(relation_type);
+
+-- Ensure memory_entity has all columns code expects
+ALTER TABLE memory_entity ADD COLUMN IF NOT EXISTS deleted_at TIMESTAMPTZ;
+ALTER TABLE memory_entity ADD COLUMN IF NOT EXISTS source_count INTEGER DEFAULT 1;
+
+-- Unique constraint for entity upsert dedup
+DO $$
+BEGIN
+    -- Dedup existing rows before creating unique index
+    DELETE FROM memory_entity a USING memory_entity b
+    WHERE a.project_id = b.project_id AND a.name = b.name
+      AND a.t_created < b.t_created;
+EXCEPTION WHEN OTHERS THEN NULL;
+END $$;
+CREATE UNIQUE INDEX IF NOT EXISTS idx_memory_entity_project_name ON memory_entity(project_id, name);
+
+-- ROLLBACK instructions:
+-- DROP TABLE IF EXISTS memory_edge;
+-- ALTER TABLE IF EXISTS memory_edge_legacy RENAME TO memory_edge;

k8s/app/config.yaml

@@ -20,7 +20,6 @@ data:
   # OpenSearch
   OPENSEARCH_HOST: "opensearch.poimen.svc.cluster.local:9200"
   # Obsidian
-  OBSIDIAN_URL: "http://obsidian-server.poimen.svc.cluster.local:8080"
   # LLM Configuration (for entity extraction)
   LLM_ENDPOINT: "http://api-internal.riotpiao.com:8000/v1/chat/completions"
   LLM_MODEL: "qwen:7b"

k8s/app/deployment.yaml

@@ -1,6 +1,6 @@
 # Poimen Memory API Server
-# Serves 7 HTTP endpoints for memory ingest, query, and management.
-# Connects to memory-db (pgvector) for persistent storage.
+# Serves HTTP endpoints for memory ingest, query, visualization.
+# Connects to memory-db (pgvector) + api.riotpiao.com (LLM via Authentik JWT).
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -60,13 +60,43 @@ spec:
                   key: password
             - name: DATABASE_URL
               value: "postgresql://$(DATABASE_USER):$(DATABASE_PASSWORD)@$(DATABASE_HOST):$(DATABASE_PORT)/$(DATABASE_NAME)?sslmode=disable"
-            # LLM Gateway API key
+
+            # LLM via api.riotpiao.com (Authentik JWT auth)
+            - name: LLM_ENDPOINT
+              value: "https://api.riotpiao.com/v1/chat/completions"
+            - name: LLM_API_BASE
+              value: "https://api.riotpiao.com/v1"
+            - name: LLM_MODEL
+              value: "ornith:35b"
+
+            # Authentik service account (memory-agent-oidc secret)
+            - name: AUTHENTIK_ISSUER
+              valueFrom:
+                secretKeyRef:
+                  name: memory-agent-oidc
+                  key: ISSUER
+            - name: AUTHENTIK_CLIENT_ID
+              valueFrom:
+                secretKeyRef:
+                  name: memory-agent-oidc
+                  key: CLIENT_ID
+            - name: AUTHENTIK_CLIENT_SECRET
+              valueFrom:
+                secretKeyRef:
+                  name: memory-agent-oidc
+                  key: CLIENT_SECRET
+            - name: TOKEN_URL
+              valueFrom:
+                secretKeyRef:
+                  name: memory-agent-oidc
+                  key: TOKEN_URL
+
+            # Server config
             - name: MEM_API_KEY
               valueFrom:
                 secretKeyRef:
                   name: poimen-memory-secrets
                   key: llm-api-key
-            # Server config (from ConfigMap)
             - name: MEM_PORT
               value: "8080"
             - name: MEM_HOME
@@ -74,10 +104,7 @@ spec:
           envFrom:
             - configMapRef:
                 name: poimen-memory-config
-            - secretRef:
-                name: poimen-memory-auth
-            - secretRef:
-                name: poimen-memory-secrets
+          command: ["/app/mem"]
           args:
             - serve
             - --port
@@ -110,7 +137,6 @@ spec:
         - name: tmp
           emptyDir:
             sizeLimit: 64Mi
-      # Tolerate control-plane nodes
       tolerations:
         - key: node-role.kubernetes.io/control-plane
           operator: Exists

k8s/app/kustomization.yaml

@@ -6,7 +6,7 @@ resources:
   - deployment.yaml
   - service.yaml
   - config.yaml
-  - obsidian.yaml
+  # obsidian.yaml retired — reference docs now via memory graph
   # Legacy secret managed separately
   # - secrets.yaml
 generators:

k8s/app/obsidian.yaml

@@ -1,159 +0,0 @@
----
-# Obsidian server deployment
-# Serves local vault with web UI and API
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: obsidian-server
-  namespace: poimen
-  labels:
-    app.kubernetes.io/name: obsidian-server
-    app.kubernetes.io/part-of: poimen-memory
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: obsidian-server
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: obsidian-server
-        app.kubernetes.io/part-of: poimen-memory
-    spec:
-      serviceAccountName: obsidian-server
-      securityContext:
-        runAsNonRoot: true
-        runAsUser: 1000
-        runAsGroup: 1000
-        fsGroup: 1000
-        seccompProfile:
-          type: RuntimeDefault
-      initContainers:
-      - name: git-sync-init
-        image: alpine/git:latest
-        securityContext:
-          runAsNonRoot: false
-          runAsUser: 0
-          allowPrivilegeEscalation: false
-          capabilities:
-            drop:
-              - ALL
-            add:
-              - CHOWN
-              - DAC_OVERRIDE
-        command:
-        - sh
-        - -c
-        - |
-          export GIT_SSH_COMMAND="ssh -i /root/.ssh/id_ed25519 -o StrictHostKeyChecking=no"
-          git config --global --add safe.directory /vault
-          if [ -d /vault/.git ]; then
-            cd /vault && git pull origin main || true
-          else
-            # Clone into temp, move contents into vault
-            rm -rf /tmp/repo
-            git clone ssh://[email protected]:2222/rock/poimen-obesdient-memory.git /tmp/repo
-            cp -a /tmp/repo/. /vault/
-            rm -rf /tmp/repo
-          fi
-          chown -R 1000:1000 /vault
-        volumeMounts:
-        - name: vault
-          mountPath: /vault
-        - name: ssh-key
-          mountPath: /root/.ssh
-          readOnly: true
-      containers:
-      - name: obsidian-server
-        image: ppatlabs/obsidian:latest
-        imagePullPolicy: IfNotPresent
-        securityContext:
-          allowPrivilegeEscalation: false
-          capabilities:
-            drop:
-              - ALL
-        ports:
-        - name: http
-          containerPort: 27124
-          protocol: TCP
-        env:
-        - name: VAULT_NAME
-          value: poimen-vault
-        - name: VAULT_PATH
-          value: /vault
-        - name: REST_API_ENABLED
-          value: "true"
-        - name: REST_API_PORT
-          value: "8080"
-        volumeMounts:
-        - name: vault
-          mountPath: /vault
-        - name: config
-          mountPath: /config
-        resources:
-          requests:
-            cpu: 100m
-            memory: 256Mi
-          limits:
-            cpu: 500m
-            memory: 512Mi
-        livenessProbe:
-          httpGet:
-            path: /
-            port: http
-            scheme: HTTPS
-          initialDelaySeconds: 30
-          periodSeconds: 10
-          timeoutSeconds: 5
-        readinessProbe:
-          httpGet:
-            path: /
-            port: http
-            scheme: HTTPS
-          initialDelaySeconds: 15
-          periodSeconds: 5
-          timeoutSeconds: 5
-      volumes:
-      - name: vault
-        persistentVolumeClaim:
-          claimName: obsidian-vault
-      - name: config
-        emptyDir: {}
-      - name: ssh-key
-        secret:
-          secretName: obsidian-git-ssh
-          defaultMode: 0400
-
-# PVC managed by homelab repo (k8s/infra/databases/obsidian-vault-pvc.yaml)
-
----
-# Service for Obsidian server
-apiVersion: v1
-kind: Service
-metadata:
-  name: obsidian-server
-  namespace: poimen
-  labels:
-    app.kubernetes.io/name: obsidian-server
-spec:
-  type: ClusterIP
-  ports:
-  - name: http
-    port: 80
-    targetPort: 27124
-    protocol: TCP
-  selector:
-    app.kubernetes.io/name: obsidian-server
-
----
-# ServiceAccount for Obsidian
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: obsidian-server
-  namespace: poimen
-  labels:
-    app.kubernetes.io/name: obsidian-server
-
-# Ingress managed by homelab repo (obsidian.riotpiao.com)
-# See: homelab/k8s/bootstrap/ingress/ingress.yaml