Update prompts & docs. Remove docker sandbox workflow

.github/workflows/test.yml

@@ -76,22 +76,3 @@ jobs:
           token: ${{ secrets.CODECOV_TOKEN }}
           files: ./coverage.xml
           fail_ci_if_error: false
-
-  test-docker-sandbox:
-    needs: [lint]
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: astral-sh/setup-uv@v4
-        with:
-          enable-cache: true
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version-file: "pyproject.toml"
-      - name: Install dependencies
-        run: uv sync --all-extras
-      - name: Build Docker image
-        run: docker build -t haiku-rag-slim:test -f docker/Dockerfile.slim .
-      - name: Run Docker integration tests
-        run: uv run pytest tests/agents/rlm/test_sandbox.py -v

docs/agents/rlm.md

@@ -5,13 +5,13 @@ The RLM agent enables complex analytical tasks by writing and executing Python c
 - **Aggregation**: "How many documents mention security vulnerabilities?"
 - **Computation**: "What's the average revenue across all quarterly reports?"
 - **Multi-document analysis**: "Compare the key findings between Report A and Report B"
-- **Structured data extraction**: "Extract all tables from the document and summarize them"
+- **Structured data extraction**: "Extract all dollar amounts and compute totals"
 
 ## How It Works
 
 1. The agent receives a question
 2. It writes Python code to explore the knowledge base
-3. Code executes in a sandboxed environment with access to haiku.rag functions
+3. Code executes in a sandboxed Python interpreter with access to haiku.rag functions
 4. The agent iterates: run code, examine results, refine approach
 5. Final answer is synthesized from the gathered data
 
@@ -93,22 +93,19 @@ if content:
 
 Returns the document content as a string, or `None` if not found.
 
-### get_docling_document(id_or_title)
+### get_chunk(chunk_id)
 
-Get the structured DoclingDocument object for advanced analysis of tables, figures, and document structure.
+Get a specific chunk by its ID (from search results). Use this to retrieve full chunk details and metadata for citations.
 
 ```python
-doc = get_docling_document("Technical Manual")
+results = search("safety requirements", limit=5)
-if doc:
+for r in results:
-    print(f"Tables: {len(doc.tables)}")
+    chunk = get_chunk(r['chunk_id'])
-    print(f"Pictures: {len(doc.pictures)}")
+    print(f"From '{chunk['document_title']}', page {chunk['page_numbers']}: {chunk['content'][:100]}")
-
-    # Extract table data
-    for table in doc.tables:
-        for cell in table.data.table_cells:
-            print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
 ```
 
+Returns dict with keys: `chunk_id`, `content`, `document_id`, `document_title`, `headings`, `page_numbers`, `labels`
+
 ### llm(prompt)
 
 Call an LLM directly for classification, summarization, or extraction tasks.
@@ -133,36 +130,39 @@ for doc in documents:
 
 Each document dict has keys: `id`, `title`, `uri`, `content`
 
-## Imports
+## Python Features
 
-The sandbox runs in a Docker container with full Python available. Any module installed in the container image can be imported:
+The sandbox uses [pydantic-monty](https://github.com/pydantic/monty), a minimal secure Python interpreter written in Rust. It supports a subset of Python:
+
+**Supported:** variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, try/except, and the `json` module.
+
+**Not supported:** imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements.
+
+For pattern matching or text extraction, use string methods (`str.split`, `str.find`, `str.startswith`, `in` operator) or the `llm()` function:
 
 ```python
-import re
+# Extract data with llm() instead of regex
-import json
+numbers = []
-from collections import Counter
+results = search("financial data", limit=20)
-
-# Extract and count patterns
-results = search("error", limit=50)
-error_types = []
 for r in results:
-    matches = re.findall(r'Error: (\w+)', r['content'])
+    extracted = llm(f"Extract all dollar amounts as a comma-separated list of numbers (no $ signs): {r['content']}")
-    error_types.extend(matches)
+    for part in extracted.split(','):
-
+        part = part.strip().replace(',', '')
-print(Counter(error_types).most_common(10))
+        if part.isdigit():
+            numbers.append(int(part))
+if numbers:
+    print(f"Average: {sum(numbers) / len(numbers)}")
 ```
 
-The default image (`ghcr.io/ggozad/haiku.rag-slim`) includes the Python standard library. Custom images can add additional packages like `pandas` or `numpy`.
+## Sandboxed Execution
 
-## Docker Sandbox
+Code executes in an isolated interpreter with:
 
-Code executes in an isolated Docker container with:
+- **No filesystem access**: Code cannot read or write files
-
+- **No network access**: Code cannot make HTTP requests or open sockets
-- **Read-only database**: The LanceDB database is mounted read-only
+- **No imports**: Only the `json` module is available
-- **Memory limits**: Configurable memory limit (default 512MB)
 - **Execution timeout**: Code times out after configurable limit (default 60s)
 - **Output truncation**: Large outputs are truncated to prevent memory issues
-- **Container reuse**: Within a single `rlm()` call, the container stays warm for multiple code executions
 
 ## Context Filter
 
@@ -193,26 +193,4 @@ rlm:
     name: claude-sonnet-4-20250514
   code_timeout: 60.0      # Max seconds for code execution
   max_output_chars: 50000 # Truncate output after this many chars
-  docker_image: "ghcr.io/ggozad/haiku.rag-slim:latest"  # Container image
-  docker_memory_limit: "512m"  # Container memory limit
-```
-
-### Custom Docker Image
-
-To add additional Python packages, create a custom Dockerfile:
-
-```dockerfile
-FROM ghcr.io/ggozad/haiku.rag-slim:latest
-RUN pip install pandas numpy
-```
-
-Build and configure:
-
-```bash
-docker build -t my-rlm-image .
-```
-
-```yaml
-rlm:
-  docker_image: "my-rlm-image"
 ```

haiku_rag_slim/haiku/rag/agents/rlm/prompts.py

@@ -6,7 +6,7 @@ CRITICAL: Inside execute_code, these functions are ALREADY available in the name
 - search("query")  ✓ CORRECT
 - from haiku.rag import search  ✗ WRONG - will fail
 
-You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
+You have access to a sandboxed Python interpreter with these haiku.rag functions (use them directly, no imports needed):
 
 ## Available Functions
 
@@ -22,10 +22,10 @@ Returns list of dicts with keys: id, title, uri, created_at
 Get the full text content of a document by ID, title, or URI.
 Returns the document content as a string, or None if not found.
 
-### get_docling_document(id_or_title) -> DoclingDocument | None
+### get_chunk(chunk_id) -> dict | None
-Get the structured DoclingDocument object for advanced analysis.
+Get a specific chunk by its ID (from search results).
-Returns a DoclingDocument object, or None if not found.
+Returns dict with keys: chunk_id, content, document_id, document_title, headings, page_numbers, labels
-See "DoclingDocument API" section below for how to use it.
+Use this to retrieve full chunk details and metadata for citation.
 
 ### llm(prompt) -> str
 Call an LLM directly with the given prompt. Returns the response as a string.
@@ -42,8 +42,13 @@ for doc in documents:
 ```
 Check if it exists with: `if 'documents' in dir(): ...`
 
-## Standard Library Modules
+## Available Python Features
-You can import any Python standard library module.
+
+The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, try/except, and the `json` module.
+
+Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements.
+
+For pattern matching or text extraction, use string methods (`str.split`, `str.find`, `str.startswith`, `in` operator) or the `llm()` function.
 
 ## Strategy Guide
 
@@ -51,51 +56,9 @@ You can import any Python standard library module.
 2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
 3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
 4. **Use print() Liberally**: The sandbox captures stdout - print intermediate results to see what you're working with.
-5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
+5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and data structures.
 6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
-7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
+7. **Cite Your Sources**: Use get_chunk() to retrieve chunk metadata for citations. Track which documents/chunks informed your answer.
-
-## DoclingDocument API
-
-When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
-
-### Properties
-- `doc.texts` - List of all text items (paragraphs, headings, etc.)
-- `doc.tables` - List of all tables
-- `doc.pictures` - List of all pictures/figures
-- `doc.name` - Document name
-
-### Methods
-- `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
-  Returns tuples of (item, level) where level is nesting depth
-- `doc.export_to_markdown()` - Export entire document as markdown string
-
-### Text Item Properties
-- `item.text` - The text content
-- `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
-- `item.prov` - Provenance (page numbers, bounding boxes)
-
-### Table Access
-- `table.data.num_rows`, `table.data.num_cols` - Dimensions
-- `table.data.table_cells` - List of TableCell objects
-- `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
-
-### Example Usage
-```python
-doc = get_docling_document("My Document")
-
-# Get all headings
-headings = [t.text for t in doc.texts if "header" in str(t.label)]
-
-# Iterate with structure
-for item, level in doc.iterate_items():
-    print("  " * level + item.text[:50])
-
-# Extract table data
-for table in doc.tables:
-    for cell in table.data.table_cells:
-        print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
-```
 
 ## Example Patterns
 
@@ -111,23 +74,31 @@ for doc in docs:
 print(f"Total: {count}")
 ```
 
-### Aggregating data across documents
+### Extracting data with llm()
 ```python
-import re
 numbers = []
 results = search("financial data", limit=20)
 for r in results:
-    matches = re.findall(r'\\$([\\d,]+)', r['content'])
+    extracted = llm(f"Extract all dollar amounts from this text as a comma-separated list of numbers (no $ signs): {r['content']}")
-    for m in matches:
+    for part in extracted.split(','):
-        numbers.append(int(m.replace(',', '')))
+        part = part.strip().replace(',', '')
-print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
+        if part.isdigit():
+            numbers.append(int(part))
+if numbers:
+    print(f"Average: {sum(numbers) / len(numbers)}")
+```
+
+### Using search results with get_chunk for citations
+```python
+results = search("safety requirements", limit=5)
+for r in results:
+    chunk = get_chunk(r['chunk_id'])
+    print(f"From '{chunk['document_title']}', page {chunk['page_numbers']}: {chunk['content'][:100]}")
 ```
 
 ### Using llm() for classification
 ```python
-# Get document content
 content = get_document("Q1 Report")
-# Use llm() to classify sentiment
 sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
 print(sentiment)
 ```

tests/cassettes/test_rlm/TestClientRLMIntegration.test_rlm_count_documents.yaml

@@ -128,7 +128,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '7719'
+      - '7083'
       content-type:
       - application/json
       host:
@@ -145,7 +145,7 @@ interactions:
           - search("query")  ✓ CORRECT
           - from haiku.rag import search  ✗ WRONG - will fail
 
-          You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
+          You have access to a sandboxed Python interpreter with these haiku.rag functions (use them directly, no imports needed):
 
           ## Available Functions
 
@@ -161,10 +161,10 @@ interactions:
           Get the full text content of a document by ID, title, or URI.
           Returns the document content as a string, or None if not found.
 
-          ### get_docling_document(id_or_title) -> DoclingDocument | None
+          ### get_chunk(chunk_id) -> dict | None
-          Get the structured DoclingDocument object for advanced analysis.
+          Get a specific chunk by its ID (from search results).
-          Returns a DoclingDocument object, or None if not found.
+          Returns dict with keys: chunk_id, content, document_id, document_title, headings, page_numbers, labels
-          See "DoclingDocument API" section below for how to use it.
+          Use this to retrieve full chunk details and metadata for citation.
 
           ### llm(prompt) -> str
           Call an LLM directly with the given prompt. Returns the response as a string.
@@ -181,8 +181,13 @@ interactions:
           ```
           Check if it exists with: `if 'documents' in dir(): ...`
 
-          ## Standard Library Modules
+          ## Available Python Features
-          You can import any Python standard library module.
+
+          The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, try/except, and the `json` module.
+
+          Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements.
+
+          For pattern matching or text extraction, use string methods (`str.split`, `str.find`, `str.startswith`, `in` operator) or the `llm()` function.
 
           ## Strategy Guide
 
@@ -190,51 +195,9 @@ interactions:
           2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
           3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
           4. **Use print() Liberally**: The sandbox captures stdout - print intermediate results to see what you're working with.
-          5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
+          5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and data structures.
           6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
-          7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
+          7. **Cite Your Sources**: Use get_chunk() to retrieve chunk metadata for citations. Track which documents/chunks informed your answer.
-
-          ## DoclingDocument API
-
-          When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
-
-          ### Properties
-          - `doc.texts` - List of all text items (paragraphs, headings, etc.)
-          - `doc.tables` - List of all tables
-          - `doc.pictures` - List of all pictures/figures
-          - `doc.name` - Document name
-
-          ### Methods
-          - `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
-            Returns tuples of (item, level) where level is nesting depth
-          - `doc.export_to_markdown()` - Export entire document as markdown string
-
-          ### Text Item Properties
-          - `item.text` - The text content
-          - `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
-          - `item.prov` - Provenance (page numbers, bounding boxes)
-
-          ### Table Access
-          - `table.data.num_rows`, `table.data.num_cols` - Dimensions
-          - `table.data.table_cells` - List of TableCell objects
-          - `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
-
-          ### Example Usage
-          ```python
-          doc = get_docling_document("My Document")
-
-          # Get all headings
-          headings = [t.text for t in doc.texts if "header" in str(t.label)]
-
-          # Iterate with structure
-          for item, level in doc.iterate_items():
-              print("  " * level + item.text[:50])
-
-          # Extract table data
-          for table in doc.tables:
-              for cell in table.data.table_cells:
-                  print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
-          ```
 
           ## Example Patterns
 
@@ -250,23 +213,31 @@ interactions:
           print(f"Total: {count}")
           ```
 
-          ### Aggregating data across documents
+          ### Extracting data with llm()
           ```python
-          import re
           numbers = []
           results = search("financial data", limit=20)
           for r in results:
-              matches = re.findall(r'\$([\d,]+)', r['content'])
+              extracted = llm(f"Extract all dollar amounts from this text as a comma-separated list of numbers (no $ signs): {r['content']}")
-              for m in matches:
+              for part in extracted.split(','):
-                  numbers.append(int(m.replace(',', '')))
+                  part = part.strip().replace(',', '')
-          print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
+                  if part.isdigit():
+                      numbers.append(int(part))
+          if numbers:
+              print(f"Average: {sum(numbers) / len(numbers)}")
+          ```
+
+          ### Using search results with get_chunk for citations
+          ```python
+          results = search("safety requirements", limit=5)
+          for r in results:
+              chunk = get_chunk(r['chunk_id'])
+              print(f"From '{chunk['document_title']}', page {chunk['page_numbers']}: {chunk['content'][:100]}")
           ```
 
           ### Using llm() for classification
           ```python
-          # Get document content
           content = get_document("Q1 Report")
-          # Use llm() to classify sentiment
           sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
           print(sentiment)
           ```
@@ -343,7 +314,7 @@ interactions:
   response:
     headers:
       content-length:
-      - '585'
+      - '552'
       content-type:
       - application/json
     parsed_body:
@@ -352,24 +323,24 @@ interactions:
         index: 0
         message:
           content: ''
-          reasoning: We need to list documents via list_documents to count.
+          reasoning: Need to list documents.
           role: assistant
           tool_calls:
           - function:
               arguments: '{"code":"docs=list_documents(limit=1000)\nprint(len(docs))\nfor d in docs:\n    print(d[''title''])"}'
               name: execute_code
-            id: call_1he6vvcy
+            id: call_tumky965
             index: 0
             type: function
-      created: 1771336260
+      created: 1771336699
-      id: chatcmpl-619
+      id: chatcmpl-910
       model: gpt-oss
       object: chat.completion
       system_fingerprint: fp_ollama
       usage:
-        completion_tokens: 63
+        completion_tokens: 56
-        prompt_tokens: 1734
+        prompt_tokens: 1562
-        total_tokens: 1797
+        total_tokens: 1618
     status:
       code: 200
       message: OK
@@ -382,7 +353,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '8283'
+      - '7612'
       content-type:
       - application/json
       host:
@@ -399,7 +370,7 @@ interactions:
           - search("query")  ✓ CORRECT
           - from haiku.rag import search  ✗ WRONG - will fail
 
-          You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
+          You have access to a sandboxed Python interpreter with these haiku.rag functions (use them directly, no imports needed):
 
           ## Available Functions
 
@@ -415,10 +386,10 @@ interactions:
           Get the full text content of a document by ID, title, or URI.
           Returns the document content as a string, or None if not found.
 
-          ### get_docling_document(id_or_title) -> DoclingDocument | None
+          ### get_chunk(chunk_id) -> dict | None
-          Get the structured DoclingDocument object for advanced analysis.
+          Get a specific chunk by its ID (from search results).
-          Returns a DoclingDocument object, or None if not found.
+          Returns dict with keys: chunk_id, content, document_id, document_title, headings, page_numbers, labels
-          See "DoclingDocument API" section below for how to use it.
+          Use this to retrieve full chunk details and metadata for citation.
 
           ### llm(prompt) -> str
           Call an LLM directly with the given prompt. Returns the response as a string.
@@ -435,8 +406,13 @@ interactions:
           ```
           Check if it exists with: `if 'documents' in dir(): ...`
 
-          ## Standard Library Modules
+          ## Available Python Features
-          You can import any Python standard library module.
+
+          The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, try/except, and the `json` module.
+
+          Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements.
+
+          For pattern matching or text extraction, use string methods (`str.split`, `str.find`, `str.startswith`, `in` operator) or the `llm()` function.
 
           ## Strategy Guide
 
@@ -444,51 +420,9 @@ interactions:
           2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
           3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
           4. **Use print() Liberally**: The sandbox captures stdout - print intermediate results to see what you're working with.
-          5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
+          5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and data structures.
           6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
-          7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
+          7. **Cite Your Sources**: Use get_chunk() to retrieve chunk metadata for citations. Track which documents/chunks informed your answer.
-
-          ## DoclingDocument API
-
-          When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
-
-          ### Properties
-          - `doc.texts` - List of all text items (paragraphs, headings, etc.)
-          - `doc.tables` - List of all tables
-          - `doc.pictures` - List of all pictures/figures
-          - `doc.name` - Document name
-
-          ### Methods
-          - `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
-            Returns tuples of (item, level) where level is nesting depth
-          - `doc.export_to_markdown()` - Export entire document as markdown string
-
-          ### Text Item Properties
-          - `item.text` - The text content
-          - `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
-          - `item.prov` - Provenance (page numbers, bounding boxes)
-
-          ### Table Access
-          - `table.data.num_rows`, `table.data.num_cols` - Dimensions
-          - `table.data.table_cells` - List of TableCell objects
-          - `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
-
-          ### Example Usage
-          ```python
-          doc = get_docling_document("My Document")
-
-          # Get all headings
-          headings = [t.text for t in doc.texts if "header" in str(t.label)]
-
-          # Iterate with structure
-          for item, level in doc.iterate_items():
-              print("  " * level + item.text[:50])
-
-          # Extract table data
-          for table in doc.tables:
-              for cell in table.data.table_cells:
-                  print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
-          ```
 
           ## Example Patterns
 
@@ -504,23 +438,31 @@ interactions:
           print(f"Total: {count}")
           ```
 
-          ### Aggregating data across documents
+          ### Extracting data with llm()
           ```python
-          import re
           numbers = []
           results = search("financial data", limit=20)
           for r in results:
-              matches = re.findall(r'\$([\d,]+)', r['content'])
+              extracted = llm(f"Extract all dollar amounts from this text as a comma-separated list of numbers (no $ signs): {r['content']}")
-              for m in matches:
+              for part in extracted.split(','):
-                  numbers.append(int(m.replace(',', '')))
+                  part = part.strip().replace(',', '')
-          print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
+                  if part.isdigit():
+                      numbers.append(int(part))
+          if numbers:
+              print(f"Average: {sum(numbers) / len(numbers)}")
+          ```
+
+          ### Using search results with get_chunk for citations
+          ```python
+          results = search("safety requirements", limit=5)
+          for r in results:
+              chunk = get_chunk(r['chunk_id'])
+              print(f"From '{chunk['document_title']}', page {chunk['page_numbers']}: {chunk['content'][:100]}")
           ```
 
           ### Using llm() for classification
           ```python
-          # Get document content
           content = get_document("Q1 Report")
-          # Use llm() to classify sentiment
           sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
           print(sentiment)
           ```
@@ -548,18 +490,18 @@ interactions:
       - content: How many documents are in the database?
         role: user
       - content: null
-        reasoning: We need to list documents via list_documents to count.
+        reasoning: Need to list documents.
         role: assistant
         tool_calls:
         - function:
             arguments: '{"code":"docs=list_documents(limit=1000)\nprint(len(docs))\nfor d in docs:\n    print(d[''title''])"}'
             name: execute_code
-          id: call_1he6vvcy
+          id: call_tumky965
           type: function
       - content: '{"code":"docs=list_documents(limit=1000)\nprint(len(docs))\nfor d in docs:\n    print(d[''title''])","stdout":"3\nDoc
           1\nDoc 2\nDoc 3\n","stderr":"","success":true}'
         role: tool
-        tool_call_id: call_1he6vvcy
+        tool_call_id: call_tumky965
       model: gpt-oss
       reasoning_effort: low
       stream: false
@@ -610,7 +552,7 @@ interactions:
   response:
     headers:
       content-length:
-      - '577'
+      - '517'
       content-type:
       - application/json
     parsed_body:
@@ -618,19 +560,18 @@ interactions:
       - finish_reason: stop
         index: 0
         message:
-          content: '{"answer":"There are 3 documents in the database. They are titled: Doc 1, Doc 2, and Doc 3.","program":"#
+          content: '{"answer":"There are 3 documents in the database.","program":"docs = list_documents(limit=1000)\nprint(f\"Number
-            Count documents in the database\n\ndocs = list_documents(limit=1000)\nprint(f\"Number of documents: {len(docs)}\")\nfor
+            of documents: {len(docs)}\")\nfor doc in docs:\n    print(f\"- {doc[''title'']} (ID: {doc[''id'']})\")"}'
-            d in docs:\n    print(f\"- {d[''title'']}\")"}'
           role: assistant
-      created: 1771336262
+      created: 1771336701
-      id: chatcmpl-256
+      id: chatcmpl-57
       model: gpt-oss
       object: chat.completion
       system_fingerprint: fp_ollama
       usage:
-        completion_tokens: 91
+        completion_tokens: 82
-        prompt_tokens: 1864
+        prompt_tokens: 1684
-        total_tokens: 1955
+        total_tokens: 1766
     status:
       code: 200
       message: OK

tests/cassettes/test_rlm/TestClientRLMIntegration.test_rlm_with_filter.yaml

@@ -128,7 +128,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '7713'
+      - '7077'
       content-type:
       - application/json
       host:
@@ -145,7 +145,7 @@ interactions:
           - search("query")  ✓ CORRECT
           - from haiku.rag import search  ✗ WRONG - will fail
 
-          You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
+          You have access to a sandboxed Python interpreter with these haiku.rag functions (use them directly, no imports needed):
 
           ## Available Functions
 
@@ -161,10 +161,10 @@ interactions:
           Get the full text content of a document by ID, title, or URI.
           Returns the document content as a string, or None if not found.
 
-          ### get_docling_document(id_or_title) -> DoclingDocument | None
+          ### get_chunk(chunk_id) -> dict | None
-          Get the structured DoclingDocument object for advanced analysis.
+          Get a specific chunk by its ID (from search results).
-          Returns a DoclingDocument object, or None if not found.
+          Returns dict with keys: chunk_id, content, document_id, document_title, headings, page_numbers, labels
-          See "DoclingDocument API" section below for how to use it.
+          Use this to retrieve full chunk details and metadata for citation.
 
           ### llm(prompt) -> str
           Call an LLM directly with the given prompt. Returns the response as a string.
@@ -181,8 +181,13 @@ interactions:
           ```
           Check if it exists with: `if 'documents' in dir(): ...`
 
-          ## Standard Library Modules
+          ## Available Python Features
-          You can import any Python standard library module.
+
+          The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, try/except, and the `json` module.
+
+          Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements.
+
+          For pattern matching or text extraction, use string methods (`str.split`, `str.find`, `str.startswith`, `in` operator) or the `llm()` function.
 
           ## Strategy Guide
 
@@ -190,51 +195,9 @@ interactions:
           2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
           3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
           4. **Use print() Liberally**: The sandbox captures stdout - print intermediate results to see what you're working with.
-          5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
+          5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and data structures.
           6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
-          7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
+          7. **Cite Your Sources**: Use get_chunk() to retrieve chunk metadata for citations. Track which documents/chunks informed your answer.
-
-          ## DoclingDocument API
-
-          When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
-
-          ### Properties
-          - `doc.texts` - List of all text items (paragraphs, headings, etc.)
-          - `doc.tables` - List of all tables
-          - `doc.pictures` - List of all pictures/figures
-          - `doc.name` - Document name
-
-          ### Methods
-          - `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
-            Returns tuples of (item, level) where level is nesting depth
-          - `doc.export_to_markdown()` - Export entire document as markdown string
-
-          ### Text Item Properties
-          - `item.text` - The text content
-          - `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
-          - `item.prov` - Provenance (page numbers, bounding boxes)
-
-          ### Table Access
-          - `table.data.num_rows`, `table.data.num_cols` - Dimensions
-          - `table.data.table_cells` - List of TableCell objects
-          - `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
-
-          ### Example Usage
-          ```python
-          doc = get_docling_document("My Document")
-
-          # Get all headings
-          headings = [t.text for t in doc.texts if "header" in str(t.label)]
-
-          # Iterate with structure
-          for item, level in doc.iterate_items():
-              print("  " * level + item.text[:50])
-
-          # Extract table data
-          for table in doc.tables:
-              for cell in table.data.table_cells:
-                  print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
-          ```
 
           ## Example Patterns
 
@@ -250,23 +213,31 @@ interactions:
           print(f"Total: {count}")
           ```
 
-          ### Aggregating data across documents
+          ### Extracting data with llm()
           ```python
-          import re
           numbers = []
           results = search("financial data", limit=20)
           for r in results:
-              matches = re.findall(r'\$([\d,]+)', r['content'])
+              extracted = llm(f"Extract all dollar amounts from this text as a comma-separated list of numbers (no $ signs): {r['content']}")
-              for m in matches:
+              for part in extracted.split(','):
-                  numbers.append(int(m.replace(',', '')))
+                  part = part.strip().replace(',', '')
-          print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
+                  if part.isdigit():
+                      numbers.append(int(part))
+          if numbers:
+              print(f"Average: {sum(numbers) / len(numbers)}")
+          ```
+
+          ### Using search results with get_chunk for citations
+          ```python
+          results = search("safety requirements", limit=5)
+          for r in results:
+              chunk = get_chunk(r['chunk_id'])
+              print(f"From '{chunk['document_title']}', page {chunk['page_numbers']}: {chunk['content'][:100]}")
           ```
 
           ### Using llm() for classification
           ```python
-          # Get document content
           content = get_document("Q1 Report")
-          # Use llm() to classify sentiment
           sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
           print(sentiment)
           ```
@@ -343,7 +314,7 @@ interactions:
   response:
     headers:
       content-length:
-      - '527'
+      - '526'
       content-type:
       - application/json
     parsed_body:
@@ -352,24 +323,24 @@ interactions:
         index: 0
         message:
           content: ''
-          reasoning: Need to call list_documents to count.
+          reasoning: Need to list_documents.
           role: assistant
           tool_calls:
           - function:
-              arguments: '{"code":"docs = list_documents(limit=1000)\nprint(len(docs))"}'
+              arguments: '{"code":"docs=list_documents(limit=1000);print(len(docs)); print(docs[:3])"}'
               name: execute_code
-            id: call_9nd3m1g0
+            id: call_rpfcy176
             index: 0
             type: function
-      created: 1771336314
+      created: 1771336720
-      id: chatcmpl-255
+      id: chatcmpl-390
       model: gpt-oss
       object: chat.completion
       system_fingerprint: fp_ollama
       usage:
-        completion_tokens: 46
+        completion_tokens: 47
-        prompt_tokens: 1732
+        prompt_tokens: 1560
-        total_tokens: 1778
+        total_tokens: 1607
     status:
       code: 200
       message: OK
@@ -382,7 +353,7 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '8154'
+      - '7655'
       content-type:
       - application/json
       host:
@@ -399,7 +370,7 @@ interactions:
           - search("query")  ✓ CORRECT
           - from haiku.rag import search  ✗ WRONG - will fail
 
-          You have access to a sandboxed Python environment with these haiku.rag functions (use them directly, no imports needed):
+          You have access to a sandboxed Python interpreter with these haiku.rag functions (use them directly, no imports needed):
 
           ## Available Functions
 
@@ -415,10 +386,10 @@ interactions:
           Get the full text content of a document by ID, title, or URI.
           Returns the document content as a string, or None if not found.
 
-          ### get_docling_document(id_or_title) -> DoclingDocument | None
+          ### get_chunk(chunk_id) -> dict | None
-          Get the structured DoclingDocument object for advanced analysis.
+          Get a specific chunk by its ID (from search results).
-          Returns a DoclingDocument object, or None if not found.
+          Returns dict with keys: chunk_id, content, document_id, document_title, headings, page_numbers, labels
-          See "DoclingDocument API" section below for how to use it.
+          Use this to retrieve full chunk details and metadata for citation.
 
           ### llm(prompt) -> str
           Call an LLM directly with the given prompt. Returns the response as a string.
@@ -435,8 +406,13 @@ interactions:
           ```
           Check if it exists with: `if 'documents' in dir(): ...`
 
-          ## Standard Library Modules
+          ## Available Python Features
-          You can import any Python standard library module.
+
+          The interpreter supports: variables, arithmetic, strings, f-strings, lists, dicts, tuples, sets, loops, conditionals, comprehensions, functions, try/except, and the `json` module.
+
+          Not supported: imports (other than `json`), class definitions, generators/yield, match statements, decorators, `with` statements.
+
+          For pattern matching or text extraction, use string methods (`str.split`, `str.find`, `str.startswith`, `in` operator) or the `llm()` function.
 
           ## Strategy Guide
 
@@ -444,51 +420,9 @@ interactions:
           2. **If get_document returns None**: Use `list_documents()` to see actual document titles, or `search()` to find relevant content.
           3. **Iterative Refinement**: Run code, examine results, adjust your approach based on what you find.
           4. **Use print() Liberally**: The sandbox captures stdout - print intermediate results to see what you're working with.
-          5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and use collections.
+          5. **Aggregate with Code**: For counting, averaging, or comparing across documents, write loops and data structures.
           6. **Use llm() for Classification/Extraction**: When you need to classify, summarize, or extract structured data from content you already have, use llm().
-          7. **Cite Your Sources**: Track which documents/chunks informed your answer for citation.
+          7. **Cite Your Sources**: Use get_chunk() to retrieve chunk metadata for citations. Track which documents/chunks informed your answer.
-
-          ## DoclingDocument API
-
-          When you call `get_docling_document(id_or_title)`, you get a DoclingDocument object for structured document analysis.
-
-          ### Properties
-          - `doc.texts` - List of all text items (paragraphs, headings, etc.)
-          - `doc.tables` - List of all tables
-          - `doc.pictures` - List of all pictures/figures
-          - `doc.name` - Document name
-
-          ### Methods
-          - `doc.iterate_items(with_groups=False)` - Iterate all items with hierarchy level
-            Returns tuples of (item, level) where level is nesting depth
-          - `doc.export_to_markdown()` - Export entire document as markdown string
-
-          ### Text Item Properties
-          - `item.text` - The text content
-          - `item.label` - Type: title, paragraph, section_header, list_item, etc. (lowercase enum values)
-          - `item.prov` - Provenance (page numbers, bounding boxes)
-
-          ### Table Access
-          - `table.data.num_rows`, `table.data.num_cols` - Dimensions
-          - `table.data.table_cells` - List of TableCell objects
-          - `cell.text`, `cell.start_row_offset_idx`, `cell.start_col_offset_idx`
-
-          ### Example Usage
-          ```python
-          doc = get_docling_document("My Document")
-
-          # Get all headings
-          headings = [t.text for t in doc.texts if "header" in str(t.label)]
-
-          # Iterate with structure
-          for item, level in doc.iterate_items():
-              print("  " * level + item.text[:50])
-
-          # Extract table data
-          for table in doc.tables:
-              for cell in table.data.table_cells:
-                  print(f"Row {cell.start_row_offset_idx}, Col {cell.start_col_offset_idx}: {cell.text}")
-          ```
 
           ## Example Patterns
 
@@ -504,23 +438,31 @@ interactions:
           print(f"Total: {count}")
           ```
 
-          ### Aggregating data across documents
+          ### Extracting data with llm()
           ```python
-          import re
           numbers = []
           results = search("financial data", limit=20)
           for r in results:
-              matches = re.findall(r'\$([\d,]+)', r['content'])
+              extracted = llm(f"Extract all dollar amounts from this text as a comma-separated list of numbers (no $ signs): {r['content']}")
-              for m in matches:
+              for part in extracted.split(','):
-                  numbers.append(int(m.replace(',', '')))
+                  part = part.strip().replace(',', '')
-          print(f"Average: ${sum(numbers)/len(numbers):,.2f}")
+                  if part.isdigit():
+                      numbers.append(int(part))
+          if numbers:
+              print(f"Average: {sum(numbers) / len(numbers)}")
+          ```
+
+          ### Using search results with get_chunk for citations
+          ```python
+          results = search("safety requirements", limit=5)
+          for r in results:
+              chunk = get_chunk(r['chunk_id'])
+              print(f"From '{chunk['document_title']}', page {chunk['page_numbers']}: {chunk['content'][:100]}")
           ```
 
           ### Using llm() for classification
           ```python
-          # Get document content
           content = get_document("Q1 Report")
-          # Use llm() to classify sentiment
           sentiment = llm(f"Classify the sentiment as positive, negative, or mixed: {content}")
           print(sentiment)
           ```
@@ -548,17 +490,18 @@ interactions:
       - content: How many documents are available?
         role: user
       - content: null
-        reasoning: Need to call list_documents to count.
+        reasoning: Need to list_documents.
         role: assistant
         tool_calls:
         - function:
-            arguments: '{"code":"docs = list_documents(limit=1000)\nprint(len(docs))"}'
+            arguments: '{"code":"docs=list_documents(limit=1000);print(len(docs)); print(docs[:3])"}'
             name: execute_code
-          id: call_9nd3m1g0
+          id: call_rpfcy176
           type: function
-      - content: '{"code":"docs = list_documents(limit=1000)\nprint(len(docs))","stdout":"1\n","stderr":"","success":true}'
+      - content: '{"code":"docs=list_documents(limit=1000);print(len(docs)); print(docs[:3])","stdout":"1\n[{''id'': ''50c659ee-70c5-4854-a418-12ae2abdcf40'',
+          ''title'': ''Cats'', ''uri'': None, ''created_at'': ''2026-02-17 15:58:36.831575''}]\n","stderr":"","success":true}'
         role: tool
-        tool_call_id: call_9nd3m1g0
+        tool_call_id: call_rpfcy176
       model: gpt-oss
       reasoning_effort: low
       stream: false
@@ -609,7 +552,7 @@ interactions:
   response:
     headers:
       content-length:
-      - '424'
+      - '453'
       content-type:
       - application/json
     parsed_body:
@@ -617,17 +560,18 @@ interactions:
       - finish_reason: stop
         index: 0
         message:
-          content: '{"answer":"There is 1 document available in the knowledge base.","program":"docs = list_documents(limit=1000)\nprint(len(docs))"}'
+          content: '{"answer":"There is 1 document available in the knowledge base.","program":"docs=list_documents(limit=1000)\nprint(f\"Number
+            of documents: {len(docs)}\")"}'
           role: assistant
-      created: 1771336315
+      created: 1771336721
-      id: chatcmpl-500
+      id: chatcmpl-97
       model: gpt-oss
       object: chat.completion
       system_fingerprint: fp_ollama
       usage:
-        completion_tokens: 39
+        completion_tokens: 46
-        prompt_tokens: 1819
+        prompt_tokens: 1713
-        total_tokens: 1858
+        total_tokens: 1759
     status:
       code: 200
       message: OK