ci: add deploy workflow — retag SHA as latest on main merge

deploy.yaml (main push only):
  - Pull image by SHA tag (already pushed during PR CI)
  - Tag as :latest and push
  - No rebuild needed

.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

crates/mem-cli/src/ingest_worker.rs

@@ -2,7 +2,7 @@ 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, LlmEntityExtractor};
+use mem_ingest::entity_extractor::WikiLinkFallbackExtractor;
 use mem_ingest::fact_extractor::SimpleFactExtractor;
 use mem_ingest::contradiction_detector::ContradictionHandler;
 use sqlx::PgPool;
@@ -26,16 +26,9 @@ impl IngestWorker {
     ) -> Self {
         let vector_store = Arc::new(VectorStore::new(pool.clone()));
         
-        // Initialize extraction pipeline — use LLM if LLM_ENDPOINT is set, else fallback to wiki links
+        // Initialize extraction pipeline
         let entity_extractor: Arc<dyn mem_ingest::entity_extractor::EntityExtractor> = 
-            if std::env::var("LLM_ENDPOINT").is_ok() {
+            Arc::new(WikiLinkFallbackExtractor);
-                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);
         let contradiction_detector = Arc::new(ContradictionHandler::default());

crates/mem-ingest/src/entity_extractor.rs

@@ -22,15 +22,11 @@ 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 {
@@ -66,25 +62,6 @@ impl LlmEntityExtractor {
 
     /// Parse extraction response JSON
     /// Format: { "entities": [{ "name": "...", "type": "...", "summary": "..." }, ...] }
-    /// Strip <think>...</think> tags from reasoning model output and extract JSON
-    fn strip_thinking_tags(text: &str) -> String {
-        let mut result = text.to_string();
-        // Remove <think>...</think> blocks
-        if let Some(start) = result.find("<think>") {
-            if let Some(end) = result.find("</think>") {
-                result = format!("{}{}", &result[..start], &result[end + 8..]);
-            }
-        }
-        // Try to find JSON object in remaining text
-        let trimmed = result.trim();
-        if let Some(start) = trimmed.find('{') {
-            if let Some(end) = trimmed.rfind('}') {
-                return trimmed[start..=end].to_string();
-            }
-        }
-        trimmed.to_string()
-    }
-
     fn parse_extraction(response: &str) -> Result<Vec<ExtractedEntity>> {
         #[derive(Deserialize)]
         struct Response {
@@ -169,16 +146,12 @@ impl LlmEntityExtractor {
         }
         
         let data: serde_json::Value = response.json().await?;
-        let raw_content = data["choices"][0]["message"]["content"]
+        let content = data["choices"][0]["message"]["content"]
             .as_str()
             .unwrap_or("{}")
             .to_string();
         
-        // Strip <think>...</think> tags from reasoning models
+        tracing::debug!("LLM response (via Authentik JWT): {}", content);
-        let content = Self::strip_thinking_tags(&raw_content);
-        
-        tracing::debug!("LLM raw response length={}, cleaned length={}", raw_content.len(), content.len());
-        tracing::debug!("LLM cleaned content: {}", content);
         Ok(content)
     }
     
@@ -260,27 +233,14 @@ Respond in JSON:
             );
 
             let reflection = if std::env::var("LLM_ENDPOINT").is_ok() {
-                self.call_llm_endpoint(&reflection_prompt).await.unwrap_or_else(|e| {
+                self.call_llm_endpoint(&reflection_prompt).await.unwrap_or_else(|_| self.simulate_llm(&reflection_prompt).unwrap_or_default())
-                    tracing::warn!("Reflection LLM call failed: {}, skipping verification", e);
-                    String::new()
-                })
             } else {
                 self.simulate_llm(&reflection_prompt)?
             };
+            let verified = Self::parse_reflection(&reflection)?;
 
-            // If reflection succeeded, filter entities; otherwise keep all
+            // Filter: keep only entities marked present
-            if !reflection.is_empty() {
+            entities.retain(|e| verified.iter().any(|(name, present)| name == &e.name && *present));
-                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 {

k8s/app/deployment.yaml

@@ -78,7 +78,6 @@ spec:
                 name: poimen-memory-auth
             - secretRef:
                 name: poimen-memory-secrets
-          command: ["/app/mem"]
           args:
             - serve
             - --port