fix docs on clients

.github/workflows/release.yml

@@ -219,6 +219,9 @@ jobs:
 
   release-helm-chart:
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
 
     steps:
     - uses: actions/checkout@v4
@@ -228,12 +231,18 @@ jobs:
       with:
         version: 'latest'
 
+    - name: Log in to GHCR
+      run: echo "${{ secrets.GITHUB_TOKEN }}" | helm registry login ghcr.io -u ${{ github.actor }} --password-stdin
+
     - name: Lint Helm chart
       run: helm lint helm/hindsight
 
     - name: Package Helm chart
       run: helm package helm/hindsight --destination ./helm-packages
 
+    - name: Push to GHCR OCI
+      run: helm push helm-packages/*.tgz oci://ghcr.io/${{ github.repository_owner }}/charts
+
     - name: Upload artifacts
       uses: actions/upload-artifact@v4
       with:

README.md

@@ -66,7 +66,7 @@ UI: http://localhost:9999
 Install client:
 
 ```bash
-pip install hindsight-client
+pip install hindsight-client -U
 # or
 npm install @vectorize-io/hindsight-client
 ```
@@ -91,7 +91,7 @@ client.reflect(bank_id="my-bank", query="Tell me about Alice")
 ### Python (embedded, no Docker)
 
 ```bash
-pip install hindsight-all
+pip install hindsight-all -U
 ```
 
 ```python
@@ -100,27 +100,27 @@ from hindsight import HindsightServer, HindsightClient
 
 with HindsightServer(
     llm_provider="openai",
-    llm_model="gpt-4o-mini", 
+    llm_model="gpt-5-mini", 
     llm_api_key=os.environ["OPENAI_API_KEY"]
 ) as server:
     client = HindsightClient(base_url=server.url)
-    client.retain(bank_id="my-agent", content="Alice works at Google")
+    client.retain(bank_id="my-bank", content="Alice works at Google")
-    results = client.recall(bank_id="my-agent", query="Where does Alice work?")
+    results = client.recall(bank_id="my-bank", query="Where does Alice work?")
 ```
 
-### TypeScript
+### Node.js / TypeScript
 
 ```bash
 npm install @vectorize-io/hindsight-client
 ```
 
-```typescript
+```javascript
-import { HindsightClient } from '@vectorize-io/hindsight-client';
+const { HindsightClient } = require('@vectorize-io/hindsight-client');
 
 const client = new HindsightClient({ baseUrl: 'http://localhost:8888' });
 
-await client.retain('my-agent', 'Alice loves hiking in Yosemite');
+await client.retain('my-bank', 'Alice loves hiking in Yosemite');
-const response = await client.recall('my-agent', 'What does Alice like?');
+await client.recall('my-bank', 'What does Alice like?');
 ```
 
 ---
@@ -168,9 +168,7 @@ client = Hindsight(base_url="http://localhost:8888")
 client.recall(bank_id="my-bank", query="What does Alice do?")
 
 # Temporal
-results = client.recall(bank_id="my-bank", query="What happened in June?")
+client.recall(bank_id="my-bank", query="What happened in June?")
-
-
 ```
 
 Recall performs 4 retrieval strategies in parallel:

docker/standalone/Dockerfile

@@ -177,6 +177,7 @@ ENV HINDSIGHT_API_PORT=8888
 ENV HINDSIGHT_API_LOG_LEVEL=info
 ENV HINDSIGHT_ENABLE_API=true
 ENV HINDSIGHT_ENABLE_CP=false
+ENV PYTHONUNBUFFERED=1
 
 CMD ["/app/start-all.sh"]
 
@@ -311,6 +312,7 @@ ENV NODE_ENV=production
 ENV HINDSIGHT_CP_DATAPLANE_API_URL=http://localhost:8888
 ENV HINDSIGHT_ENABLE_API=true
 ENV HINDSIGHT_ENABLE_CP=true
+ENV PYTHONUNBUFFERED=1
 
 CMD ["/app/start-all.sh"]
 

docker/standalone/start-all.sh

@@ -23,7 +23,7 @@ PIDS=()
 # Start API if enabled
 if [ "$ENABLE_API" = "true" ]; then
     cd /app/api
-    hindsight-api 2>&1 | sed 's/^/[api] /' &
+    hindsight-api 2>&1 | sed -u 's/^/[api] /' &
     API_PID=$!
     PIDS+=($API_PID)
 
@@ -42,7 +42,7 @@ fi
 if [ "$ENABLE_CP" = "true" ]; then
     echo "🎛️  Starting Control Plane..."
     cd /app/control-plane
-    PORT=9999 node server.js 2>&1 | grep -v -E "^[[:space:]]*(▲|✓|-|$)" | sed 's/^/[control-plane] /' &
+    PORT=9999 node server.js 2>&1 | grep -v -E "^[[:space:]]*(▲|✓|-|$)" | sed -u 's/^/[control-plane] /' &
     CP_PID=$!
     PIDS+=($CP_PID)
 else

hindsight-api/hindsight_api/engine/llm_wrapper.py

@@ -170,24 +170,38 @@ class LLMProvider:
                 "messages": messages,
             }
 
-            if max_completion_tokens is not None:
-                call_params["max_completion_tokens"] = max_completion_tokens
             # Check if model supports reasoning parameter (o1, o3, gpt-5 families)
             model_lower = self.model.lower()
             is_reasoning_model = any(x in model_lower for x in ["gpt-5", "o1", "o3"])
 
+            # For GPT-4 and GPT-4.1 models, cap max_completion_tokens to 32000
+            is_gpt4_model = any(x in model_lower for x in ["gpt-4.1", "gpt-4-"])
+            if max_completion_tokens is not None:
+                if is_gpt4_model and max_completion_tokens > 32000:
+                    max_completion_tokens = 32000
+                # For reasoning models, max_completion_tokens includes reasoning + output tokens
+                # Enforce minimum of 16000 to ensure enough space for both
+                if is_reasoning_model and max_completion_tokens < 16000:
+                    max_completion_tokens = 16000
+                call_params["max_completion_tokens"] = max_completion_tokens
+
             # GPT-5/o1/o3 family doesn't support custom temperature (only default 1)
             if temperature is not None and not is_reasoning_model:
                 call_params["temperature"] = temperature
 
+            # Set reasoning_effort for reasoning models (OpenAI gpt-5, o1, o3)
+            if is_reasoning_model and self.provider == "openai":
+                call_params["reasoning_effort"] = self.reasoning_effort
+
             # Provider-specific parameters
             if self.provider == "groq":
                 call_params["seed"] = DEFAULT_LLM_SEED
-                call_params["extra_body"] = {
+                extra_body = {"service_tier": "auto"}
-                    "service_tier": "auto",
+                # Only add reasoning parameters for reasoning models
-                    "reasoning_effort": self.reasoning_effort,
+                if is_reasoning_model:
-                    "include_reasoning": False,
+                    extra_body["reasoning_effort"] = self.reasoning_effort
-                }
+                    extra_body["include_reasoning"] = False
+                call_params["extra_body"] = extra_body
 
             last_exception = None
 

hindsight-api/tests/test_llm_provider.py

@@ -10,36 +10,30 @@ from hindsight_api.engine.llm_wrapper import LLMProvider
 MODEL_MATRIX = [
     # OpenAI models
     ("openai", "gpt-4o-mini"),
+    ("openai", "gpt-4.1-mini"),
+    ("openai", "gpt-4.1-nano"),
     ("openai", "gpt-5-mini"),
+    ("openai", "gpt-5-nano"),
+    ("openai", "gpt-5"),
     # Groq models
     ("groq", "llama-3.3-70b-versatile"),
     ("groq", "openai/gpt-oss-120b"),
+    ("groq", "openai/gpt-oss-20b"),
     # Gemini models
-    ("gemini", "gemini-2.0-flash"),
+    ("gemini", "gemini-2.5-flash"),
-    ("gemini", "gemini-2.5-flash-preview-05-20"),
+    ("gemini", "gemini-2.5-flash-lite"),
 ]
 
 
 def get_api_key_for_provider(provider: str) -> str | None:
     """Get API key for provider from environment variables."""
-    # Try provider-specific env vars first
     provider_key_map = {
-        "openai": ["OPENAI_API_KEY", "HINDSIGHT_API_LLM_API_KEY"],
+        "openai": "OPENAI_API_KEY",
-        "groq": ["GROQ_API_KEY", "HINDSIGHT_API_LLM_API_KEY"],
+        "groq": "GROQ_API_KEY",
-        "gemini": ["GEMINI_API_KEY", "GOOGLE_API_KEY", "HINDSIGHT_API_LLM_API_KEY"],
+        "gemini": "GEMINI_API_KEY",
     }
-
+    env_var = provider_key_map.get(provider)
-    for env_var in provider_key_map.get(provider, []):
+    return os.getenv(env_var) if env_var else None
-        key = os.getenv(env_var)
-        if key:
-            # For HINDSIGHT_API_LLM_API_KEY, only use if provider matches
-            if env_var == "HINDSIGHT_API_LLM_API_KEY":
-                configured_provider = os.getenv("HINDSIGHT_API_LLM_PROVIDER", "").lower()
-                if configured_provider == provider:
-                    return key
-            else:
-                return key
-    return None
 
 
 @pytest.mark.parametrize("provider,model", MODEL_MATRIX)
@@ -97,8 +91,10 @@ async def test_llm_provider_verify_connection(provider: str, model: str):
 # Models that support large output (65000+ tokens)
 LARGE_OUTPUT_MODELS = [
     ("openai", "gpt-5-mini"),
-    ("gemini", "gemini-2.0-flash"),
+    ("openai", "gpt-5-nano"),
-    ("gemini", "gemini-2.5-flash-preview-05-20"),
+    ("openai", "gpt-5"),
+    ("gemini", "gemini-2.5-flash"),
+    ("gemini", "gemini-2.5-flash-lite"),
 ]
 
 

hindsight-clients/python/hindsight_client/__init__.py

@@ -15,8 +15,8 @@ Example:
     print(result.success)
 
     # Search memories
-    results = client.recall(bank_id="alice", query="What does Alice like?")
+    response = client.recall(bank_id="alice", query="What does Alice like?")
-    for r in results:
+    for r in response.results:
         print(r.text)
 
     # Generate contextual answer
@@ -29,14 +29,59 @@ from .hindsight_client import Hindsight
 
 # Re-export response types for convenient access
 from hindsight_client_api.models.retain_response import RetainResponse
-from hindsight_client_api.models.recall_response import RecallResponse
+from hindsight_client_api.models.recall_response import RecallResponse as _RecallResponse
-from hindsight_client_api.models.recall_result import RecallResult
+from hindsight_client_api.models.recall_result import RecallResult as _RecallResult
 from hindsight_client_api.models.reflect_response import ReflectResponse
 from hindsight_client_api.models.reflect_fact import ReflectFact
 from hindsight_client_api.models.list_memory_units_response import ListMemoryUnitsResponse
 from hindsight_client_api.models.bank_profile_response import BankProfileResponse
 from hindsight_client_api.models.disposition_traits import DispositionTraits
 
+
+# Add cleaner __repr__ and __iter__ for REPL usability
+def _recall_result_repr(self):
+    text_preview = self.text[:80] + "..." if len(self.text) > 80 else self.text
+    return f"RecallResult(id='{self.id[:8]}...', type='{self.type}', text='{text_preview}')"
+
+
+def _recall_response_repr(self):
+    count = len(self.results) if self.results else 0
+    extras = []
+    if self.trace:
+        extras.append("trace=True")
+    if self.entities:
+        extras.append(f"entities={len(self.entities)}")
+    if self.chunks:
+        extras.append(f"chunks={len(self.chunks)}")
+    extras_str = ", " + ", ".join(extras) if extras else ""
+    return f"RecallResponse({count} results{extras_str})"
+
+
+def _recall_response_iter(self):
+    """Iterate directly over results for convenience."""
+    return iter(self.results or [])
+
+
+def _recall_response_len(self):
+    """Return number of results."""
+    return len(self.results) if self.results else 0
+
+
+def _recall_response_getitem(self, index):
+    """Access results by index."""
+    return self.results[index]
+
+
+_RecallResult.__repr__ = _recall_result_repr
+_RecallResponse.__repr__ = _recall_response_repr
+_RecallResponse.__iter__ = _recall_response_iter
+_RecallResponse.__len__ = _recall_response_len
+_RecallResponse.__getitem__ = _recall_response_getitem
+
+# Re-export with patched repr
+RecallResult = _RecallResult
+RecallResponse = _RecallResponse
+
 __all__ = [
     "Hindsight",
     # Response types

hindsight-clients/python/hindsight_client/hindsight_client.py

@@ -50,7 +50,9 @@ class Hindsight:
         client.retain(bank_id="alice", content="Alice loves AI")
 
         # Recall memories
-        results = client.recall(bank_id="alice", query="What does Alice like?")
+        response = client.recall(bank_id="alice", query="What does Alice like?")
+        for r in response.results:
+            print(r.text)
 
         # Generate contextual answer
         answer = client.reflect(bank_id="alice", query="What are my interests?")
@@ -125,8 +127,8 @@ class Hindsight:
 
         Args:
             bank_id: The memory bank ID
-            items: List of memory items with 'content' and optional 'timestamp', 'context', 'metadata'
+            items: List of memory items with 'content' and optional 'timestamp', 'context', 'metadata', 'document_id'
-            document_id: Optional document ID for grouping memories
+            document_id: Optional document ID for grouping memories (applied to items that don't have their own)
             retain_async: If True, process asynchronously in background (default: False)
 
         Returns:
@@ -138,13 +140,14 @@ class Hindsight:
                 timestamp=item.get("timestamp"),
                 context=item.get("context"),
                 metadata=item.get("metadata"),
+                # Use item's document_id if provided, otherwise fall back to batch-level document_id
+                document_id=item.get("document_id") or document_id,
             )
             for item in items
         ]
 
         request_obj = retain_request.RetainRequest(
             items=memory_items,
-            document_id=document_id,
             async_=retain_async,
         )
 
@@ -161,6 +164,8 @@ class Hindsight:
         query_timestamp: Optional[str] = None,
         include_entities: bool = False,
         max_entity_tokens: int = 500,
+        include_chunks: bool = False,
+        max_chunk_tokens: int = 8192,
     ) -> RecallResponse:
         """
         Recall memories using semantic similarity.
@@ -175,14 +180,17 @@ class Hindsight:
             query_timestamp: Optional ISO format date string (e.g., '2023-05-30T23:40:00')
             include_entities: Include entity observations in results (default: False)
             max_entity_tokens: Maximum tokens for entity observations (default: 500)
+            include_chunks: Include raw text chunks in results (default: False)
+            max_chunk_tokens: Maximum tokens for chunks (default: 8192)
 
         Returns:
-            RecallResponse with results, optional entities, and optional trace
+            RecallResponse with results, optional entities, optional chunks, and optional trace
         """
-        from hindsight_client_api.models import include_options, entity_include_options
+        from hindsight_client_api.models import include_options, entity_include_options, chunk_include_options
 
         include_opts = include_options.IncludeOptions(
-            entities=entity_include_options.EntityIncludeOptions(max_tokens=max_entity_tokens) if include_entities else None
+            entities=entity_include_options.EntityIncludeOptions(max_tokens=max_entity_tokens) if include_entities else None,
+            chunks=chunk_include_options.ChunkIncludeOptions(max_tokens=max_chunk_tokens) if include_chunks else None,
         )
 
         request_obj = recall_request.RecallRequest(
@@ -277,8 +285,8 @@ class Hindsight:
 
         Args:
             bank_id: The memory bank ID
-            items: List of memory items with 'content' and optional 'timestamp', 'context', 'metadata'
+            items: List of memory items with 'content' and optional 'timestamp', 'context', 'metadata', 'document_id'
-            document_id: Optional document ID for grouping memories
+            document_id: Optional document ID for grouping memories (applied to items that don't have their own)
             retain_async: If True, process asynchronously in background (default: False)
 
         Returns:
@@ -290,13 +298,14 @@ class Hindsight:
                 timestamp=item.get("timestamp"),
                 context=item.get("context"),
                 metadata=item.get("metadata"),
+                # Use item's document_id if provided, otherwise fall back to batch-level document_id
+                document_id=item.get("document_id") or document_id,
             )
             for item in items
         ]
 
         request_obj = retain_request.RetainRequest(
             items=memory_items,
-            document_id=document_id,
             async_=retain_async,
         )
 

hindsight-clients/typescript/src/index.ts

@@ -128,7 +128,17 @@ export class HindsightClient {
     async recall(
         bankId: string,
         query: string,
-        options?: { types?: string[]; maxTokens?: number; budget?: Budget; trace?: boolean }
+        options?: {
+            types?: string[];
+            maxTokens?: number;
+            budget?: Budget;
+            trace?: boolean;
+            queryTimestamp?: string;
+            includeEntities?: boolean;
+            maxEntityTokens?: number;
+            includeChunks?: boolean;
+            maxChunkTokens?: number;
+        }
     ): Promise<RecallResponse> {
         const response = await sdk.recallMemories({
             client: this.client,
@@ -139,6 +149,11 @@ export class HindsightClient {
                 max_tokens: options?.maxTokens,
                 budget: options?.budget || 'mid',
                 trace: options?.trace,
+                query_timestamp: options?.queryTimestamp,
+                include: {
+                    entities: options?.includeEntities ? { max_tokens: options?.maxEntityTokens ?? 500 } : undefined,
+                    chunks: options?.includeChunks ? { max_tokens: options?.maxChunkTokens ?? 8192 } : undefined,
+                },
             },
         });
 

hindsight-docs/docs/developer/api/think-vs-search.md

@@ -1,153 +0,0 @@
----
-sidebar_position: 4
----
-
-# Think vs Search
-
-When to use `search` vs `think`.
-
-## Quick Comparison
-
-| | Search | Think |
-|---|--------|-------|
-| **Returns** | Raw memory results | Generated response |
-| **Use case** | Retrieval, lookup | Q&A, reasoning |
-| **LLM calls** | 0 (retrieval only) | 1+ (generation) |
-| **Speed** | Fast (~100-200ms) | Slower (~500-2000ms) |
-| **Opinions** | Returns existing | Can form new ones |
-| **Disposition** | Not applied | Applied to response |
-
-## When to Use Search
-
-**Use Search when you need:**
-
-- Raw facts for your own processing
-- Fast retrieval without generation
-- To populate context for another LLM
-- To check what's in memory
-- Debugging retrieval quality
-
-```python
-# Get raw facts to inject into your own prompt
-results = client.search(agent_id="my-agent", query="Alice's preferences")
-
-context = "\n".join([r["text"] for r in results])
-# Use context in your own LLM call
-```
-
-**Examples:**
-
-```python
-# Lookup — just get the facts
-results = client.search(agent_id="my-agent", query="Alice's email address")
-
-# Context building — feed into another system
-results = client.search(agent_id="my-agent", query="Recent project discussions")
-context = format_for_prompt(results)
-
-# Verification — check what's stored
-results = client.search(agent_id="my-agent", query="What do I know about Bob?")
-```
-
-## When to Use Think
-
-**Use Think when you need:**
-
-- A natural language response
-- Disposition-aware answers
-- Opinion formation
-- Reasoning over multiple facts
-- Source attribution
-
-```python
-# Get a complete answer with disposition
-answer = client.think(agent_id="my-agent", query="What should I recommend to Alice?")
-print(answer["text"])  # Natural language response
-print(answer["based_on"])  # Sources used
-```
-
-**Examples:**
-
-```python
-# Q&A — need a response, not just facts
-answer = client.think(agent_id="my-agent", query="What does Alice do for work?")
-
-# Reasoning — synthesize multiple facts
-answer = client.think(agent_id="my-agent", query="How are Alice and Bob connected?")
-
-# Opinion — agent forms a view
-answer = client.think(agent_id="my-agent", query="What do you think about Python?")
-
-# Recommendation — disposition-influenced
-answer = client.think(agent_id="my-agent", query="What book should I read next?")
-```
-
-## Performance Comparison
-
-```mermaid
-graph LR
-    subgraph Search
-        S1[Query] --> S2[4-way Retrieval]
-        S2 --> S3[RRF + Rerank]
-        S3 --> S4[Results]
-    end
-
-    subgraph Think
-        T1[Query] --> T2[4-way Retrieval]
-        T2 --> T3[RRF + Rerank]
-        T3 --> T4[Load Disposition]
-        T4 --> T5[LLM Generation]
-        T5 --> T6[Store Opinions]
-        T6 --> T7[Response]
-    end
-```
-
-| Operation | Search | Think |
-|-----------|--------|-------|
-| Retrieval | ~100ms | ~100ms |
-| Reranking | ~35ms | ~35ms |
-| LLM Generation | — | ~500-1500ms |
-| Opinion Storage | — | ~50ms |
-| **Total** | **~135ms** | **~700-1700ms** |
-
-## Hybrid Pattern
-
-Use Search for context, Think for final response:
-
-```python
-# First: fast search to check relevance
-results = client.search(agent_id="my-agent", query="Alice project status")
-
-if len(results) > 0:
-    # Only call Think if we have relevant memories
-    answer = client.think(agent_id="my-agent", query="Summarize Alice's project status")
-else:
-    answer = {"text": "I don't have information about Alice's projects."}
-```
-
-## Decision Flowchart
-
-```mermaid
-graph TD
-    A[Need memory access] --> B{Need natural language response?}
-    B -->|No| C[Use Search]
-    B -->|Yes| D{Need disposition/opinions?}
-    D -->|No| E{Building context for another LLM?}
-    E -->|Yes| C
-    E -->|No| F[Use Think]
-    D -->|Yes| F
-```
-
-## Cost Considerations
-
-| Factor | Search | Think |
-|--------|--------|-------|
-| API calls | 1 | 1 |
-| LLM tokens | 0 | 500-2000 |
-| Latency | Low | Medium |
-| Cost | Low | Higher (LLM usage) |
-
-If you're making many requests or building a high-throughput system, consider:
-- Use Search for bulk operations
-- Use Think for user-facing responses
-- Cache Think responses when appropriate

hindsight-docs/docs/developer/installation.md

@@ -55,27 +55,29 @@ docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
 **Best for**: Production deployments, auto-scaling, cloud environments
 
 ```bash
-# Add Hindsight Helm repository
-helm repo add hindsight https://vectorize-io.github.io/hindsight
-helm repo update
-
 # Install with built-in PostgreSQL
-helm install hindsight hindsight/hindsight \
+helm install hindsight oci://ghcr.io/vectorize-io/charts/hindsight \
   --set api.llm.provider=groq \
   --set api.llm.apiKey=gsk_xxxxxxxxxxxx \
   --set postgresql.enabled=true
 
 # Or use external PostgreSQL
-helm install hindsight hindsight/hindsight \
+helm install hindsight oci://ghcr.io/vectorize-io/charts/hindsight \
   --set api.llm.provider=groq \
   --set api.llm.apiKey=gsk_xxxxxxxxxxxx \
   --set postgresql.enabled=false \
   --set api.database.url=postgresql://user:pass@postgres.example.com:5432/hindsight
+
+# Install a specific version
+helm install hindsight oci://ghcr.io/vectorize-io/charts/hindsight --version 0.1.3
+
+# Upgrade to latest
+helm upgrade hindsight oci://ghcr.io/vectorize-io/charts/hindsight
 ```
 
 **Requirements**:
 - Kubernetes cluster (GKE, EKS, AKS, or self-hosted)
-- Helm 3+
+- Helm 3.8+
 
 See the [Helm chart documentation](https://github.com/vectorize-io/hindsight/tree/main/helm) for advanced configuration.
 

hindsight-docs/docs/sdks/nodejs.md

@@ -15,21 +15,21 @@ npm install @vectorize-io/hindsight-client
 ## Quick Start
 
 ```typescript
-import { HindsightClient } from '@vectorize-io/hindsight-client';
+const { HindsightClient } = require('@vectorize-io/hindsight-client');
 
 const client = new HindsightClient({ baseUrl: 'http://localhost:8888' });
 
 // Retain a memory
-await client.retain('my-agent', 'Alice works at Google');
+await client.retain('my-bank', 'Alice works at Google');
 
 // Recall memories
-const response = await client.recall('my-agent', 'What does Alice do?');
+const response = await client.recall('my-bank', 'What does Alice do?');
 for (const r of response.results) {
     console.log(r.text);
 }
 
 // Reflect - generate response with disposition
-const answer = await client.reflect('my-agent', 'Tell me about Alice');
+const answer = await client.reflect('my-bank', 'Tell me about Alice');
 console.log(answer.text);
 ```
 
@@ -49,10 +49,10 @@ const client = new HindsightClient({
 
 ```typescript
 // Simple
-await client.retain('my-agent', 'Alice works at Google');
+await client.retain('my-bank', 'Alice works at Google');
 
 // With options
-await client.retain('my-agent', 'Alice got promoted', {
+await client.retain('my-bank', 'Alice got promoted', {
     timestamp: new Date('2024-01-15'),
     context: 'career update',
     metadata: { source: 'slack' },
@@ -63,11 +63,10 @@ await client.retain('my-agent', 'Alice got promoted', {
 ### Retain Batch
 
 ```typescript
-await client.retainBatch('my-agent', [
+await client.retainBatch('my-bank', [
     { content: 'Alice works at Google', context: 'career' },
     { content: 'Bob is a data scientist', context: 'career' },
 ], {
-    documentId: 'conversation_001',
     async: false,
 });
 ```
@@ -76,31 +75,29 @@ await client.retainBatch('my-agent', [
 
 ```typescript
 // Simple - returns RecallResponse
-const response = await client.recall('my-agent', 'What does Alice do?');
+const response = await client.recall('my-bank', 'What does Alice do?');
 
 for (const r of response.results) {
     console.log(`${r.text} (type: ${r.type})`);
 }
 
 // With options
-const response = await client.recall('my-agent', 'What does Alice do?', {
+const response = await client.recall('my-bank', 'What does Alice do?', {
     types: ['world', 'opinion'],  // Filter by fact type
     maxTokens: 4096,
     budget: 'high',  // 'low', 'mid', or 'high'
-    trace: true,
 });
 ```
 
 ### Reflect (Generate Response)
 
 ```typescript
-const answer = await client.reflect('my-agent', 'What should I know about Alice?', {
+const answer = await client.reflect('my-bank', 'What should I know about Alice?', {
     budget: 'low',  // 'low', 'mid', or 'high'
     context: 'preparing for a meeting',
 });
 
 console.log(answer.text);       // Generated response
-console.log(answer.based_on);   // Memories used
 ```
 
 ## Bank Management
@@ -108,7 +105,7 @@ console.log(answer.based_on);   // Memories used
 ### Create Bank
 
 ```typescript
-await client.createBank('my-agent', {
+await client.createBank('my-bank', {
     name: 'Assistant',
     background: 'I am a helpful AI assistant',
     disposition: {
@@ -119,117 +116,14 @@ await client.createBank('my-agent', {
 });
 ```
 
-### Get Bank Profile
-
-```typescript
-const profile = await client.getBankProfile('my-agent');
-console.log(profile.disposition);
-console.log(profile.background);
-```
-
 ### List Memories
 
 ```typescript
-const response = await client.listMemories('my-agent', {
+const response = await client.listMemories('my-bank', {
     type: 'world',  // Optional filter
     q: 'Alice',     // Optional text search
     limit: 100,
     offset: 0,
 });
-
+console.log(response)
-for (const memory of response.memories) {
-    console.log(`${memory.id}: ${memory.text}`);
-}
-```
-
-## TypeScript Types
-
-The client exports all types for full TypeScript support:
-
-```typescript
-import type {
-    RetainResponse,
-    RecallResponse,
-    RecallResult,
-    ReflectResponse,
-    BankProfileResponse,
-    Budget,
-} from '@vectorize-io/hindsight-client';
-
-// Budget is a union type: 'low' | 'mid' | 'high'
-const budget: Budget = 'mid';
-```
-
-## Advanced: Low-Level SDK
-
-For advanced use cases, access the auto-generated SDK directly:
-
-```typescript
-import { sdk, createClient, createConfig } from '@vectorize-io/hindsight-client';
-
-const client = createClient(createConfig({ baseUrl: 'http://localhost:8888' }));
-
-// Use sdk functions directly
-const response = await sdk.recallMemories({
-    client,
-    path: { bank_id: 'my-agent' },
-    body: {
-        query: 'What does Alice do?',
-        budget: 'mid',
-        max_tokens: 4096,
-    },
-});
-```
-
-## Error Handling
-
-```typescript
-import { HindsightClient } from '@vectorize-io/hindsight-client';
-
-const client = new HindsightClient({ baseUrl: 'http://localhost:8888' });
-
-try {
-    const response = await client.recall('unknown-agent', 'test');
-} catch (error) {
-    console.error('Error:', error.message);
-}
-```
-
-## Example: Full Workflow
-
-```typescript
-import { HindsightClient } from '@vectorize-io/hindsight-client';
-
-async function main() {
-    const client = new HindsightClient({ baseUrl: 'http://localhost:8888' });
-
-    // Create a bank with disposition
-    await client.createBank('demo', {
-        name: 'Demo Agent',
-        background: 'A helpful assistant for demos',
-        disposition: {
-            skepticism: 2,   // Trusting
-            literalism: 3,   // Balanced
-            empathy: 4,      // Empathetic
-        },
-    });
-
-    // Store some memories
-    await client.retain('demo', 'Alice works at Google');
-    await client.retain('demo', 'Bob is a data scientist at Google');
-    await client.retain('demo', 'Alice and Bob collaborate on ML projects');
-
-    // Search for memories
-    const searchResults = await client.recall('demo', 'Who works at Google?');
-    console.log('Search results:');
-    for (const r of searchResults.results) {
-        console.log(`  - ${r.text}`);
-    }
-
-    // Generate a response
-    const answer = await client.reflect('demo', 'What do you know about the team?');
-    console.log('\nReflection:', answer.text);
-}
-
-main().catch(console.error);
 ```

hindsight-docs/docs/sdks/python.md

@@ -49,15 +49,15 @@ with HindsightServer(
     client = HindsightClient(base_url=server.url)
 
     # Retain a memory
-    client.retain(bank_id="my-agent", content="Alice works at Google")
+    client.retain(bank_id="my-bank", content="Alice works at Google")
 
     # Recall memories
-    results = client.recall(bank_id="my-agent", query="What does Alice do?")
+    results = client.recall(bank_id="my-bank", query="What does Alice do?")
     for r in results:
         print(r.text)
 
     # Reflect - generate response with disposition
-    answer = client.reflect(bank_id="my-agent", query="Tell me about Alice")
+    answer = client.reflect(bank_id="my-bank", query="Tell me about Alice")
     print(answer.text)
 ```
 
@@ -70,15 +70,15 @@ from hindsight_client import Hindsight
 client = Hindsight(base_url="http://localhost:8888")
 
 # Retain a memory
-client.retain(bank_id="my-agent", content="Alice works at Google")
+client.retain(bank_id="my-bank", content="Alice works at Google")
 
 # Recall memories
-results = client.recall(bank_id="my-agent", query="What does Alice do?")
+results = client.recall(bank_id="my-bank", query="What does Alice do?")
 for r in results:
     print(r.text)
 
 # Reflect - generate response with disposition
-answer = client.reflect(bank_id="my-agent", query="Tell me about Alice")
+answer = client.reflect(bank_id="my-bank", query="Tell me about Alice")
 print(answer.text)
 ```
 
@@ -103,7 +103,7 @@ client = Hindsight(
 ```python
 # Simple
 client.retain(
-    bank_id="my-agent",
+    bank_id="my-bank",
     content="Alice works at Google as a software engineer",
 )
 
@@ -111,7 +111,7 @@ client.retain(
 from datetime import datetime
 
 client.retain(
-    bank_id="my-agent",
+    bank_id="my-bank",
     content="Alice got promoted",
     context="career update",
     timestamp=datetime(2024, 1, 15),
@@ -124,7 +124,7 @@ client.retain(
 
 ```python
 client.retain_batch(
-    bank_id="my-agent",
+    bank_id="my-bank",
     items=[
         {"content": "Alice works at Google", "context": "career"},
         {"content": "Bob is a data scientist", "context": "career"},
@@ -139,16 +139,16 @@ client.retain_batch(
 ```python
 # Simple - returns list of RecallResult
 results = client.recall(
-    bank_id="my-agent",
+    bank_id="my-bank",
     query="What does Alice do?",
 )
 
-for r in results:
+for r in results.results:
     print(f"{r.text} (type: {r.type})")
 
 # With options
 results = client.recall(
-    bank_id="my-agent",
+    bank_id="my-bank",
     query="What does Alice do?",
     types=["world", "opinion"],  # Filter by fact type
     max_tokens=4096,
@@ -159,16 +159,15 @@ results = client.recall(
 ### Recall with Full Response
 
 ```python
-# Returns RecallResponse with entities and trace info
+# Returns RecallResponse with entities and chunks
-response = client.recall_memories(
+response = client.recall(
-    bank_id="my-agent",
+    bank_id="my-bank",
     query="What does Alice do?",
     types=["world", "experience"],
     budget="mid",
     max_tokens=4096,
-    trace=True,
     include_entities=True,
-    max_entity_tokens=500,
+    max_entity_tokens=500
 )
 
 print(f"Found {len(response.results)} memories")
@@ -185,14 +184,13 @@ if response.entities:
 
 ```python
 answer = client.reflect(
-    bank_id="my-agent",
+    bank_id="my-bank",
     query="What should I know about Alice?",
     budget="low",  # low, mid, or high
     context="preparing for a meeting",
 )
 
 print(answer.text)  # Generated response
-print(answer.based_on)  # Memories used
 ```
 
 ## Bank Management
@@ -201,7 +199,7 @@ print(answer.based_on)  # Memories used
 
 ```python
 client.create_bank(
-    bank_id="my-agent",
+    bank_id="my-bank",
     name="Assistant",
     background="I am a helpful AI assistant",
     disposition={
@@ -215,16 +213,13 @@ client.create_bank(
 ### List Memories
 
 ```python
-response = client.list_memories(
+client.list_memories(
-    bank_id="my-agent",
+    bank_id="my-bank",
     type="world",  # Optional: filter by type
     search_query="Alice",  # Optional: text search
     limit=100,
     offset=0,
 )
-
-for memory in response.memories:
-    print(f"{memory.id}: {memory.text}")
 ```
 
 ## Async Support
@@ -239,15 +234,15 @@ async def main():
     client = Hindsight(base_url="http://localhost:8888")
 
     # Async retain
-    await client.aretain(bank_id="my-agent", content="Hello world")
+    await client.aretain(bank_id="my-bank", content="Hello world")
 
     # Async recall
-    results = await client.arecall(bank_id="my-agent", query="Hello")
+    results = await client.arecall(bank_id="my-bank", query="Hello")
     for r in results:
         print(r.text)
 
     # Async reflect
-    answer = await client.areflect(bank_id="my-agent", query="What did I say?")
+    answer = await client.areflect(bank_id="my-bank", query="What did I say?")
     print(answer.text)
 
     client.close()
@@ -255,29 +250,13 @@ async def main():
 asyncio.run(main())
 ```
 
-## Response Types
-
-The client exports response types for type hints:
-
-```python
-from hindsight_client import (
-    Hindsight,
-    RetainResponse,
-    RecallResponse,
-    RecallResult,
-    ReflectResponse,
-    BankProfileResponse,
-    DispositionTraits,
-)
-```
-
 ## Context Manager
 
 ```python
 from hindsight_client import Hindsight
 
 with Hindsight(base_url="http://localhost:8888") as client:
-    client.retain(bank_id="my-agent", content="Hello")
+    client.retain(bank_id="my-bank", content="Hello")
-    results = client.recall(bank_id="my-agent", query="Hello")
+    results = client.recall(bank_id="my-bank", query="Hello")
 # Client automatically closed
 ```

hindsight-docs/docusaurus.config.ts

@@ -128,39 +128,38 @@ const config: Config = {
       },
       items: [
         {
-          type: 'custom-iconLink',
+          type: 'doc',
+          docId: 'developer/index',
           position: 'left',
-          icon: 'code',
           label: 'Developer',
-          to: '/',
+          className: 'navbar-item-developer',
         },
         {
-          type: 'custom-iconLink',
+          type: 'doc',
+          docId: 'sdks/python',
           position: 'left',
-          icon: 'package',
           label: 'SDKs',
-          to: '/sdks/python',
+          className: 'navbar-item-sdks',
         },
         {
-          type: 'custom-iconLink',
-          position: 'left',
-          icon: 'file-code',
-          label: 'API Reference',
           to: '/api-reference',
+          position: 'left',
+          label: 'API Reference',
+          className: 'navbar-item-api',
         },
         {
-          type: 'custom-iconLink',
+          type: 'doc',
+          docId: 'cookbook/index',
           position: 'left',
-          icon: 'book-open',
           label: 'Cookbook',
-          to: '/cookbook',
+          className: 'navbar-item-cookbook',
         },
         {
-          type: 'custom-iconLink',
+          type: 'doc',
+          docId: 'changelog/index',
           position: 'left',
-          icon: 'clock',
           label: 'Changelog',
-          to: '/changelog',
+          className: 'navbar-item-changelog',
         },
         {
           href: 'https://github.com/vectorize-io/hindsight',
@@ -200,7 +199,7 @@ const config: Config = {
           ],
         },
       ],
-      copyright: `Copyright © ${new Date().getFullYear()} Hindsight. Built with Docusaurus.`,
+      copyright: `Copyright © ${new Date().getFullYear()} Hindsight.`,
     },
     prism: {
       theme: prismThemes.github,

hindsight-docs/package-lock.json

@@ -13,7 +13,6 @@
         "@docusaurus/theme-common": "^3.9.2",
         "@docusaurus/theme-mermaid": "^3.9.2",
         "@mdx-js/react": "^3.0.0",
-        "@phosphor-icons/react": "^2.1.10",
         "clsx": "^2.0.0",
         "prism-react-renderer": "^2.3.0",
         "react": "^19.0.0",
@@ -4534,19 +4533,6 @@
         "node": ">=8.0.0"
       }
     },
-    "node_modules/@phosphor-icons/react": {
-      "version": "2.1.10",
-      "resolved": "https://registry.npmjs.org/@phosphor-icons/react/-/react-2.1.10.tgz",
-      "integrity": "sha512-vt8Tvq8GLjheAZZYa+YG/pW7HDbov8El/MANW8pOAz4eGxrwhnbfrQZq0Cp4q8zBEu8NIhHdnr+r8thnfRSNYA==",
-      "license": "MIT",
-      "engines": {
-        "node": ">=10"
-      },
-      "peerDependencies": {
-        "react": ">= 16.8",
-        "react-dom": ">= 16.8"
-      }
-    },
     "node_modules/@pnpm/config.env-replace": {
       "version": "1.1.0",
       "resolved": "https://registry.npmjs.org/@pnpm/config.env-replace/-/config.env-replace-1.1.0.tgz",

hindsight-docs/package.json

@@ -21,7 +21,6 @@
     "@docusaurus/theme-common": "^3.9.2",
     "@docusaurus/theme-mermaid": "^3.9.2",
     "@mdx-js/react": "^3.0.0",
-    "@phosphor-icons/react": "^2.1.10",
     "clsx": "^2.0.0",
     "prism-react-renderer": "^2.3.0",
     "react": "^19.0.0",

hindsight-docs/src/components/NavbarIconLink.tsx

@@ -1,42 +0,0 @@
-import React from 'react';
-import Link from '@docusaurus/Link';
-import {
-  House,
-  Code,
-  Package,
-  FileCode,
-  BookOpen,
-  ClockCounterClockwise,
-} from '@phosphor-icons/react';
-
-const iconMap = {
-  house: House,
-  code: Code,
-  package: Package,
-  'file-code': FileCode,
-  'book-open': BookOpen,
-  clock: ClockCounterClockwise,
-};
-
-export default function NavbarIconLink({
-  icon,
-  label,
-  to,
-  className,
-}: {
-  icon: keyof typeof iconMap;
-  label: string;
-  to: string;
-  className?: string;
-}) {
-  const IconComponent = iconMap[icon];
-
-  return (
-    <Link to={to} className={`navbar__link ${className || ''}`}>
-      {IconComponent && (
-        <IconComponent size={16} weight="bold" style={{ marginRight: '6px', verticalAlign: 'middle' }} />
-      )}
-      <span style={{ verticalAlign: 'middle' }}>{label}</span>
-    </Link>
-  );
-}

hindsight-docs/src/css/custom.css

@@ -94,6 +94,66 @@
   transition: background-color 0.15s ease;
 }
 
+/* Navbar icons (desktop only) */
+@media (min-width: 997px) {
+  .navbar-item-developer::before,
+  .navbar-item-sdks::before,
+  .navbar-item-api::before,
+  .navbar-item-cookbook::before,
+  .navbar-item-changelog::before {
+    display: inline-block;
+    width: 16px;
+    height: 16px;
+    margin-right: 6px;
+    vertical-align: middle;
+    background-size: contain;
+    background-repeat: no-repeat;
+    background-position: center;
+    content: '';
+  }
+
+  .navbar-item-developer::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23666' d='M71.68 97.22 34.74 128l36.94 30.78a12 12 0 1 1-15.36 18.44l-48-40a12 12 0 0 1 0-18.44l48-40a12 12 0 0 1 15.36 18.44Zm176 21.56-48-40a12 12 0 1 0-15.36 18.44L221.26 128l-36.94 30.78a12 12 0 1 0 15.36 18.44l48-40a12 12 0 0 0 0-18.44ZM164.1 28.72a12 12 0 0 0-15.38 7.18l-64 176a12 12 0 0 0 7.18 15.37 11.79 11.79 0 0 0 4.1.73 12 12 0 0 0 11.28-7.9l64-176a12 12 0 0 0-7.18-15.38Z'/%3E%3C/svg%3E");
+  }
+
+  .navbar-item-sdks::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23666' d='m225.6 62.64-88-48.17a19.91 19.91 0 0 0-19.2 0l-88 48.17A20 20 0 0 0 20 80.19v95.62a20 20 0 0 0 10.4 17.55l88 48.17a19.89 19.89 0 0 0 19.2 0l88-48.17a20 20 0 0 0 10.4-17.55V80.19a20 20 0 0 0-10.4-17.55ZM128 36.57 200 76l-72 39.42L56 76ZM44 96.82l72 39.43v76.89l-72-39.42Zm96 116.32v-76.89l72-39.43v76.89Z'/%3E%3C/svg%3E");
+  }
+
+  .navbar-item-api::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23666' d='M180.49 143.51a12 12 0 0 1 0 17l-24 24a12 12 0 0 1-17-17L155 152l-15.52-15.51a12 12 0 0 1 17-17ZM112.49 120.49a12 12 0 0 0-17 0l-24 24a12 12 0 0 0 0 17l24 24a12 12 0 0 0 17-17L97 153l15.52-15.51a12 12 0 0 0-.03-17ZM220 88v24a12 12 0 0 1-24 0v-16h-44a12 12 0 0 1-12-12V40H60v68a12 12 0 0 1-24 0V40a20 20 0 0 1 20-20h96a12 12 0 0 1 8.49 3.52l56 56A12 12 0 0 1 220 88Zm-60-8h23L160 57Zm-4 132H60v-12a12 12 0 0 0-24 0v12a20 20 0 0 0 20 20h100a12 12 0 0 0 0-24Zm64-44a12 12 0 0 0-12 12v36h-44a12 12 0 0 0 0 24h44a20 20 0 0 0 20-20v-40a12 12 0 0 0-8-12Z'/%3E%3C/svg%3E");
+  }
+
+  .navbar-item-cookbook::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23666' d='M224 44H160a43.86 43.86 0 0 0-32 13.85A43.86 43.86 0 0 0 96 44H32a20 20 0 0 0-20 20v128a20 20 0 0 0 20 20h64a20 20 0 0 1 20 20 12 12 0 0 0 24 0 20 20 0 0 1 20-20h64a20 20 0 0 0 20-20V64a20 20 0 0 0-20-20ZM96 188H36V68h60a20 20 0 0 1 20 20v108.69A43.74 43.74 0 0 0 96 188Zm124 0h-60a43.74 43.74 0 0 0-20 8.69V88a20 20 0 0 1 20-20h60Z'/%3E%3C/svg%3E");
+  }
+
+  .navbar-item-changelog::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23666' d='M140 80v41.21l34.17 20.5a12 12 0 1 1-12.34 20.58l-40-24A12 12 0 0 1 116 128V80a12 12 0 0 1 24 0Zm-12-52a99.38 99.38 0 0 0-70.76 29.34c-4.69 4.74-9 9.37-13.24 14V64a12 12 0 0 0-24 0v40a12 12 0 0 0 12 12h40a12 12 0 0 0 0-24H53.41c4.24-5.95 8.53-11.93 13.49-16.95A76 76 0 1 1 52 128a12 12 0 0 0-24 0 100 100 0 1 0 100-100Z'/%3E%3C/svg%3E");
+  }
+
+  /* Dark mode icons */
+  [data-theme='dark'] .navbar-item-developer::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23ccc' d='M71.68 97.22 34.74 128l36.94 30.78a12 12 0 1 1-15.36 18.44l-48-40a12 12 0 0 1 0-18.44l48-40a12 12 0 0 1 15.36 18.44Zm176 21.56-48-40a12 12 0 1 0-15.36 18.44L221.26 128l-36.94 30.78a12 12 0 1 0 15.36 18.44l48-40a12 12 0 0 0 0-18.44ZM164.1 28.72a12 12 0 0 0-15.38 7.18l-64 176a12 12 0 0 0 7.18 15.37 11.79 11.79 0 0 0 4.1.73 12 12 0 0 0 11.28-7.9l64-176a12 12 0 0 0-7.18-15.38Z'/%3E%3C/svg%3E");
+  }
+
+  [data-theme='dark'] .navbar-item-sdks::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23ccc' d='m225.6 62.64-88-48.17a19.91 19.91 0 0 0-19.2 0l-88 48.17A20 20 0 0 0 20 80.19v95.62a20 20 0 0 0 10.4 17.55l88 48.17a19.89 19.89 0 0 0 19.2 0l88-48.17a20 20 0 0 0 10.4-17.55V80.19a20 20 0 0 0-10.4-17.55ZM128 36.57 200 76l-72 39.42L56 76ZM44 96.82l72 39.43v76.89l-72-39.42Zm96 116.32v-76.89l72-39.43v76.89Z'/%3E%3C/svg%3E");
+  }
+
+  [data-theme='dark'] .navbar-item-api::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23ccc' d='M180.49 143.51a12 12 0 0 1 0 17l-24 24a12 12 0 0 1-17-17L155 152l-15.52-15.51a12 12 0 0 1 17-17ZM112.49 120.49a12 12 0 0 0-17 0l-24 24a12 12 0 0 0 0 17l24 24a12 12 0 0 0 17-17L97 153l15.52-15.51a12 12 0 0 0-.03-17ZM220 88v24a12 12 0 0 1-24 0v-16h-44a12 12 0 0 1-12-12V40H60v68a12 12 0 0 1-24 0V40a20 20 0 0 1 20-20h96a12 12 0 0 1 8.49 3.52l56 56A12 12 0 0 1 220 88Zm-60-8h23L160 57Zm-4 132H60v-12a12 12 0 0 0-24 0v12a20 20 0 0 0 20 20h100a12 12 0 0 0 0-24Zm64-44a12 12 0 0 0-12 12v36h-44a12 12 0 0 0 0 24h44a20 20 0 0 0 20-20v-40a12 12 0 0 0-8-12Z'/%3E%3C/svg%3E");
+  }
+
+  [data-theme='dark'] .navbar-item-cookbook::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23ccc' d='M224 44H160a43.86 43.86 0 0 0-32 13.85A43.86 43.86 0 0 0 96 44H32a20 20 0 0 0-20 20v128a20 20 0 0 0 20 20h64a20 20 0 0 1 20 20 12 12 0 0 0 24 0 20 20 0 0 1 20-20h64a20 20 0 0 0 20-20V64a20 20 0 0 0-20-20ZM96 188H36V68h60a20 20 0 0 1 20 20v108.69A43.74 43.74 0 0 0 96 188Zm124 0h-60a43.74 43.74 0 0 0-20 8.69V88a20 20 0 0 1 20-20h60Z'/%3E%3C/svg%3E");
+  }
+
+  [data-theme='dark'] .navbar-item-changelog::before {
+    background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 256 256'%3E%3Cpath fill='%23ccc' d='M140 80v41.21l34.17 20.5a12 12 0 1 1-12.34 20.58l-40-24A12 12 0 0 1 116 128V80a12 12 0 0 1 24 0Zm-12-52a99.38 99.38 0 0 0-70.76 29.34c-4.69 4.74-9 9.37-13.24 14V64a12 12 0 0 0-24 0v40a12 12 0 0 0 12 12h40a12 12 0 0 0 0-24H53.41c4.24-5.95 8.53-11.93 13.49-16.95A76 76 0 1 1 52 128a12 12 0 0 0-24 0 100 100 0 1 0 100-100Z'/%3E%3C/svg%3E");
+  }
+}
+
 /* GitHub icon link */
 .header-github-link::before {
   content: '';
@@ -126,6 +186,95 @@
   background-color: #27272a;
 }
 
+/* Mobile navbar */
+@media (max-width: 996px) {
+  :root {
+    --ifm-navbar-height: 3.5rem;
+  }
+
+  .navbar {
+    padding: 0 0.75rem;
+  }
+
+  .navbar__logo {
+    margin-bottom: 0;
+    height: 24px !important;
+  }
+
+  .navbar__logo img {
+    height: 24px !important;
+  }
+
+  /* Hamburger menu toggle */
+  .navbar__toggle {
+    color: var(--ifm-color-primary);
+  }
+
+  /* Mobile sidebar */
+  .navbar-sidebar {
+    background: #ffffff !important;
+  }
+
+  .navbar-sidebar__brand {
+    padding: 1rem;
+    border-bottom: 1px solid var(--ifm-toc-border-color);
+    background: #ffffff !important;
+  }
+
+  .navbar-sidebar__items {
+    padding: 1rem 0;
+    background: #ffffff !important;
+  }
+
+  .navbar-sidebar .menu__link {
+    font-family: 'Space Grotesk', -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+    font-weight: 600;
+    font-size: 1rem;
+    padding: 0.75rem 1.25rem;
+    color: #1e293b !important;
+  }
+
+  .navbar-sidebar .menu__link--active {
+    background: var(--hindsight-gradient);
+    -webkit-background-clip: text;
+    -webkit-text-fill-color: transparent;
+    background-clip: text;
+  }
+
+  /* Close button */
+  .navbar-sidebar__close {
+    color: #1e293b !important;
+  }
+
+  /* Backdrop overlay */
+  .navbar-sidebar__backdrop {
+    background: rgba(0, 0, 0, 0.5) !important;
+  }
+}
+
+/* Dark mode mobile sidebar */
+@media (max-width: 996px) {
+  [data-theme='dark'] .navbar-sidebar {
+    background: #09090b !important;
+  }
+
+  [data-theme='dark'] .navbar-sidebar__brand {
+    background: #09090b !important;
+  }
+
+  [data-theme='dark'] .navbar-sidebar__items {
+    background: #09090b !important;
+  }
+
+  [data-theme='dark'] .navbar-sidebar .menu__link {
+    color: #e2e8f0 !important;
+  }
+
+  [data-theme='dark'] .navbar-sidebar__close {
+    color: #e2e8f0 !important;
+  }
+}
+
 /* Hero section */
 .hero {
   padding: 4rem 0;

hindsight-docs/src/theme/NavbarItem/ComponentTypes.tsx

@@ -1,7 +0,0 @@
-import ComponentTypes from '@theme-original/NavbarItem/ComponentTypes';
-import NavbarIconLink from '@site/src/components/NavbarIconLink';
-
-export default {
-  ...ComponentTypes,
-  'custom-iconLink': NavbarIconLink,
-};

hindsight-docs/static/llms-full.txt

@@ -3,7 +3,7 @@
 > Agent Memory that Works Like Human Memory
 
 This file contains the complete Hindsight documentation for LLM consumption.
-Generated: 2025-12-11T11:54:08.183Z
+Generated: 2025-12-11T12:49:49.534Z
 
 ---
 
@@ -2454,27 +2454,29 @@ docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
 **Best for**: Production deployments, auto-scaling, cloud environments
 
 ```bash
-# Add Hindsight Helm repository
-helm repo add hindsight https://vectorize-io.github.io/hindsight
-helm repo update
-
 # Install with built-in PostgreSQL
-helm install hindsight hindsight/hindsight \
+helm install hindsight oci://ghcr.io/vectorize-io/charts/hindsight \
   --set api.llm.provider=groq \
   --set api.llm.apiKey=gsk_xxxxxxxxxxxx \
   --set postgresql.enabled=true
 
 # Or use external PostgreSQL
-helm install hindsight hindsight/hindsight \
+helm install hindsight oci://ghcr.io/vectorize-io/charts/hindsight \
   --set api.llm.provider=groq \
   --set api.llm.apiKey=gsk_xxxxxxxxxxxx \
   --set postgresql.enabled=false \
   --set api.database.url=postgresql://user:pass@postgres.example.com:5432/hindsight
+
+# Install a specific version
+helm install hindsight oci://ghcr.io/vectorize-io/charts/hindsight --version 0.1.3
+
+# Upgrade to latest
+helm upgrade hindsight oci://ghcr.io/vectorize-io/charts/hindsight
 ```
 
 **Requirements**:
 - Kubernetes cluster (GKE, EKS, AKS, or self-hosted)
-- Helm 3+
+- Helm 3.8+
 
 See the [Helm chart documentation](https://github.com/vectorize-io/hindsight/tree/main/helm) for advanced configuration.
 

hindsight/tests/test_server_integration.py

@@ -27,7 +27,7 @@ def llm_config():
     model = os.getenv("HINDSIGHT_LLM_MODEL", "openai/gpt-oss-120b")
 
     if not api_key:
-        pytest.skip("LLM API key not configured. Set HINDSIGHT_LLM_API_KEY environment variable.")
+        raise Exception("LLM API key not configured. Set HINDSIGHT_LLM_API_KEY environment variable.")
 
     return {
         "llm_provider": provider,

uv.lock

@@ -1141,7 +1141,7 @@ wheels = [
 
 [[package]]
 name = "hindsight-all"
-version = "0.1.2"
+version = "0.1.3"
 source = { editable = "hindsight" }
 dependencies = [
     { name = "hindsight-api" },
@@ -1165,7 +1165,7 @@ provides-extras = ["test"]
 
 [[package]]
 name = "hindsight-api"
-version = "0.1.2"
+version = "0.1.3"
 source = { editable = "hindsight-api" }
 dependencies = [
     { name = "alembic" },
@@ -1265,7 +1265,7 @@ dev = [
 
 [[package]]
 name = "hindsight-client"
-version = "0.1.2"
+version = "0.1.3"
 source = { editable = "hindsight-clients/python" }
 dependencies = [
     { name = "aiohttp" },
@@ -1297,7 +1297,7 @@ provides-extras = ["test"]
 
 [[package]]
 name = "hindsight-dev"
-version = "0.1.2"
+version = "0.1.3"
 source = { editable = "hindsight-dev" }
 dependencies = [
     { name = "hindsight-api" },