Merge remote-tracking branch 'origin/dev' into fix/copilot-transcript-compaction

Scenarios 4 and 6 (and parts of 5, 7) were testing Python if/for logic that
mimicked the retry tree instead of calling production code. Replaced with
direct calls to _reduce_context which exercises the actual decision path.

autogpt_platform/backend/backend/api/features/store/content_handlers.py

@@ -5,26 +5,16 @@ Pluggable system for different content sources (store agents, blocks, docs).
 Each handler knows how to fetch and process its content type for embedding.
 """
 
-from __future__ import annotations
-
-import asyncio
-import functools
-import itertools
 import logging
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, get_args, get_origin
+from typing import Any, get_args, get_origin
 
 from prisma.enums import ContentType
 
-from backend.blocks import get_blocks
 from backend.blocks.llm import LlmModel
 from backend.data.db import query_raw_with_schema
-from backend.util.text import split_camelcase
-
-if TYPE_CHECKING:
-    from backend.blocks._base import AnyBlockSchema
 
 logger = logging.getLogger(__name__)
 
@@ -164,28 +154,6 @@ class StoreAgentHandler(ContentHandler):
         }
 
 
-@functools.lru_cache(maxsize=1)
-def _get_enabled_blocks() -> dict[str, AnyBlockSchema]:
-    """Return ``{block_id: block_instance}`` for all enabled, instantiable blocks.
-
-    Disabled blocks and blocks that fail to instantiate are silently skipped
-    (with a warning log), so callers never need their own try/except loop.
-
-    Results are cached for the process lifetime via ``lru_cache`` because
-    blocks are registered at import time and never change while running.
-    """
-    enabled: dict[str, AnyBlockSchema] = {}
-    for block_id, block_cls in get_blocks().items():
-        try:
-            instance = block_cls()
-        except Exception as e:
-            logger.warning(f"Skipping block {block_id}: init failed: {e}")
-            continue
-        if not instance.disabled:
-            enabled[block_id] = instance
-    return enabled
-
-
 class BlockHandler(ContentHandler):
     """Handler for block definitions (Python classes)."""
 
@@ -195,14 +163,16 @@ class BlockHandler(ContentHandler):
 
     async def get_missing_items(self, batch_size: int) -> list[ContentItem]:
         """Fetch blocks without embeddings."""
-        # to_thread keeps the first (heavy) call off the event loop.  On
-        # subsequent calls the lru_cache makes this a dict lookup, so the
-        # thread-pool overhead is negligible compared to the DB queries below.
-        enabled = await asyncio.to_thread(_get_enabled_blocks)
-        if not enabled:
+        from backend.blocks import get_blocks
+
+        # Get all available blocks
+        all_blocks = get_blocks()
+
+        # Check which ones have embeddings
+        if not all_blocks:
             return []
 
-        block_ids = list(enabled.keys())
+        block_ids = list(all_blocks.keys())
 
         # Query for existing embeddings
         placeholders = ",".join([f"${i+1}" for i in range(len(block_ids))])
@@ -217,42 +187,52 @@ class BlockHandler(ContentHandler):
         )
 
         existing_ids = {row["contentId"] for row in existing_result}
+        missing_blocks = [
+            (block_id, block_cls)
+            for block_id, block_cls in all_blocks.items()
+            if block_id not in existing_ids
+        ]
 
-        # Convert to ContentItem — disabled filtering already done by
-        # _get_enabled_blocks so batch_size won't be exhausted by disabled blocks.
-        missing = ((bid, b) for bid, b in enabled.items() if bid not in existing_ids)
+        # Convert to ContentItem
         items = []
-        for block_id, block in itertools.islice(missing, batch_size):
+        for block_id, block_cls in missing_blocks[:batch_size]:
             try:
+                block_instance = block_cls()
+
+                if block_instance.disabled:
+                    continue
+
                 # Build searchable text from block metadata
-                if not block.name:
-                    logger.warning(
-                        f"Block {block_id} has no name — using block_id as fallback"
-                    )
-                display_name = split_camelcase(block.name) if block.name else ""
                 parts = []
-                if display_name:
-                    parts.append(display_name)
-                if block.description:
-                    parts.append(block.description)
-                if block.categories:
-                    parts.append(" ".join(str(cat.value) for cat in block.categories))
+                if block_instance.name:
+                    parts.append(block_instance.name)
+                if block_instance.description:
+                    parts.append(block_instance.description)
+                if block_instance.categories:
+                    parts.append(
+                        " ".join(str(cat.value) for cat in block_instance.categories)
+                    )
 
                 # Add input schema field descriptions
+                block_input_fields = block_instance.input_schema.model_fields
                 parts += [
                     f"{field_name}: {field_info.description}"
-                    for field_name, field_info in block.input_schema.model_fields.items()
+                    for field_name, field_info in block_input_fields.items()
                     if field_info.description
                 ]
 
                 searchable_text = " ".join(parts)
 
                 categories_list = (
-                    [cat.value for cat in block.categories] if block.categories else []
+                    [cat.value for cat in block_instance.categories]
+                    if block_instance.categories
+                    else []
                 )
 
                 # Extract provider names from credentials fields
-                credentials_info = block.input_schema.get_credentials_fields_info()
+                credentials_info = (
+                    block_instance.input_schema.get_credentials_fields_info()
+                )
                 is_integration = len(credentials_info) > 0
                 provider_names = [
                     provider.value.lower()
@@ -263,7 +243,7 @@ class BlockHandler(ContentHandler):
                 # Check if block has LlmModel field in input schema
                 has_llm_model_field = any(
                     _contains_type(field.annotation, LlmModel)
-                    for field in block.input_schema.model_fields.values()
+                    for field in block_instance.input_schema.model_fields.values()
                 )
 
                 items.append(
@@ -272,13 +252,13 @@ class BlockHandler(ContentHandler):
                         content_type=ContentType.BLOCK,
                         searchable_text=searchable_text,
                         metadata={
-                            "name": display_name or block.name or block_id,
+                            "name": block_instance.name,
                             "categories": categories_list,
                             "providers": provider_names,
                             "has_llm_model_field": has_llm_model_field,
                             "is_integration": is_integration,
                         },
-                        user_id=None,
+                        user_id=None,  # Blocks are public
                     )
                 )
             except Exception as e:
@@ -289,13 +269,22 @@ class BlockHandler(ContentHandler):
 
     async def get_stats(self) -> dict[str, int]:
         """Get statistics about block embedding coverage."""
-        enabled = await asyncio.to_thread(_get_enabled_blocks)
-        total_blocks = len(enabled)
+        from backend.blocks import get_blocks
+
+        all_blocks = get_blocks()
+
+        # Filter out disabled blocks - they're not indexed
+        enabled_block_ids = [
+            block_id
+            for block_id, block_cls in all_blocks.items()
+            if not block_cls().disabled
+        ]
+        total_blocks = len(enabled_block_ids)
 
         if total_blocks == 0:
             return {"total": 0, "with_embeddings": 0, "without_embeddings": 0}
 
-        block_ids = list(enabled.keys())
+        block_ids = enabled_block_ids
         placeholders = ",".join([f"${i+1}" for i in range(len(block_ids))])
 
         embedded_result = await query_raw_with_schema(

autogpt_platform/backend/backend/api/features/store/content_handlers_test.py

@@ -1,5 +1,7 @@
 """
-Tests for content handlers (blocks, store agents, documentation).
+E2E tests for content handlers (blocks, store agents, documentation).
+
+Tests the full flow: discovering content → generating embeddings → storing.
 """
 
 from pathlib import Path
@@ -13,103 +15,15 @@ from backend.api.features.store.content_handlers import (
     BlockHandler,
     DocumentationHandler,
     StoreAgentHandler,
-    _get_enabled_blocks,
 )
 
 
-@pytest.fixture(autouse=True)
-def _clear_block_cache():
-    """Clear the lru_cache on _get_enabled_blocks before each test."""
-    _get_enabled_blocks.cache_clear()
-    yield
-    _get_enabled_blocks.cache_clear()
-
-
-# ---------------------------------------------------------------------------
-# Helper to build a mock block class that returns a pre-configured instance
-# ---------------------------------------------------------------------------
-
-
-def _make_block_class(
-    *,
-    name: str = "Block",
-    description: str = "",
-    disabled: bool = False,
-    categories: list[MagicMock] | None = None,
-    fields: dict[str, str] | None = None,
-    raise_on_init: Exception | None = None,
-) -> MagicMock:
-    cls = MagicMock()
-    if raise_on_init is not None:
-        cls.side_effect = raise_on_init
-        return cls
-    inst = MagicMock()
-    inst.name = name
-    inst.disabled = disabled
-    inst.description = description
-    inst.categories = categories or []
-    field_mocks = {
-        fname: MagicMock(description=fdesc) for fname, fdesc in (fields or {}).items()
-    }
-    inst.input_schema.model_fields = field_mocks
-    inst.input_schema.get_credentials_fields_info.return_value = {}
-    cls.return_value = inst
-    return cls
-
-
-# ---------------------------------------------------------------------------
-# _get_enabled_blocks
-# ---------------------------------------------------------------------------
-
-
-def test_get_enabled_blocks_filters_disabled():
-    """Disabled blocks are excluded."""
-    blocks = {
-        "enabled": _make_block_class(name="E", disabled=False),
-        "disabled": _make_block_class(name="D", disabled=True),
-    }
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        result = _get_enabled_blocks()
-    assert list(result.keys()) == ["enabled"]
-
-
-def test_get_enabled_blocks_skips_broken():
-    """Blocks that raise on init are skipped without crashing."""
-    blocks = {
-        "good": _make_block_class(name="Good"),
-        "bad": _make_block_class(raise_on_init=RuntimeError("boom")),
-    }
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        result = _get_enabled_blocks()
-    assert list(result.keys()) == ["good"]
-
-
-def test_get_enabled_blocks_cached():
-    """_get_enabled_blocks() calls get_blocks() only once across multiple calls."""
-    blocks = {"b1": _make_block_class(name="B1")}
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ) as mock_get_blocks:
-        result1 = _get_enabled_blocks()
-        result2 = _get_enabled_blocks()
-    assert result1 is result2
-    mock_get_blocks.assert_called_once()
-
-
-# ---------------------------------------------------------------------------
-# StoreAgentHandler
-# ---------------------------------------------------------------------------
-
-
 @pytest.mark.asyncio(loop_scope="session")
 async def test_store_agent_handler_get_missing_items(mocker):
     """Test StoreAgentHandler fetches approved agents without embeddings."""
     handler = StoreAgentHandler()
 
+    # Mock database query
     mock_missing = [
         {
             "id": "agent-1",
@@ -140,7 +54,9 @@ async def test_store_agent_handler_get_stats(mocker):
     """Test StoreAgentHandler returns correct stats."""
     handler = StoreAgentHandler()
 
+    # Mock approved count query
     mock_approved = [{"count": 50}]
+    # Mock embedded count query
     mock_embedded = [{"count": 30}]
 
     with patch(
@@ -154,130 +70,74 @@ async def test_store_agent_handler_get_stats(mocker):
         assert stats["without_embeddings"] == 20
 
 
-# ---------------------------------------------------------------------------
-# BlockHandler
-# ---------------------------------------------------------------------------
-
-
 @pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_missing_items():
+async def test_block_handler_get_missing_items(mocker):
     """Test BlockHandler discovers blocks without embeddings."""
     handler = BlockHandler()
 
-    blocks = {
-        "block-uuid-1": _make_block_class(
-            name="CalculatorBlock",
-            description="Performs calculations",
-            categories=[MagicMock(value="MATH")],
-            fields={"expression": "Math expression to evaluate"},
-        ),
-    }
+    # Mock get_blocks to return test blocks
+    mock_block_class = MagicMock()
+    mock_block_instance = MagicMock()
+    mock_block_instance.name = "Calculator Block"
+    mock_block_instance.description = "Performs calculations"
+    mock_block_instance.categories = [MagicMock(value="MATH")]
+    mock_block_instance.disabled = False
+    mock_field = MagicMock()
+    mock_field.description = "Math expression to evaluate"
+    mock_block_instance.input_schema.model_fields = {"expression": mock_field}
+    mock_block_instance.input_schema.get_credentials_fields_info.return_value = {}
+    mock_block_class.return_value = mock_block_instance
+
+    mock_blocks = {"block-uuid-1": mock_block_class}
+
+    # Mock existing embeddings query (no embeddings exist)
+    mock_existing = []
 
     with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
+        "backend.blocks.get_blocks",
+        return_value=mock_blocks,
     ):
         with patch(
             "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
+            return_value=mock_existing,
         ):
             items = await handler.get_missing_items(batch_size=10)
 
             assert len(items) == 1
             assert items[0].content_id == "block-uuid-1"
             assert items[0].content_type == ContentType.BLOCK
-            # CamelCase should be split in searchable text and metadata name
             assert "Calculator Block" in items[0].searchable_text
             assert "Performs calculations" in items[0].searchable_text
             assert "MATH" in items[0].searchable_text
             assert "expression: Math expression" in items[0].searchable_text
-            assert items[0].metadata["name"] == "Calculator Block"
             assert items[0].user_id is None
 
 
 @pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_missing_items_splits_camelcase():
-    """CamelCase block names are split for better search indexing."""
-    handler = BlockHandler()
-
-    blocks = {
-        "ai-block": _make_block_class(name="AITextGeneratorBlock"),
-    }
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            assert "AI Text Generator Block" in items[0].searchable_text
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_missing_items_batch_size_zero():
-    """batch_size=0 returns an empty list; the DB is still queried to find missing IDs."""
-    handler = BlockHandler()
-
-    blocks = {"b1": _make_block_class(name="B1")}
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ) as mock_query:
-            items = await handler.get_missing_items(batch_size=0)
-            assert items == []
-            # DB query is still issued to learn which blocks lack embeddings;
-            # the empty result comes from itertools.islice limiting to 0 items.
-            mock_query.assert_called_once()
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_disabled_dont_exhaust_batch():
-    """Disabled blocks don't consume batch budget, so enabled blocks get indexed."""
-    handler = BlockHandler()
-
-    # 5 disabled + 3 enabled, batch_size=2
-    blocks = {
-        **{
-            f"dis-{i}": _make_block_class(name=f"D{i}", disabled=True) for i in range(5)
-        },
-        **{f"en-{i}": _make_block_class(name=f"E{i}") for i in range(3)},
-    }
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=2)
-
-            assert len(items) == 2
-            assert all(item.content_id.startswith("en-") for item in items)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_stats():
+async def test_block_handler_get_stats(mocker):
     """Test BlockHandler returns correct stats."""
     handler = BlockHandler()
 
-    blocks = {
-        "block-1": _make_block_class(name="B1"),
-        "block-2": _make_block_class(name="B2"),
-        "block-3": _make_block_class(name="B3"),
+    # Mock get_blocks - each block class returns an instance with disabled=False
+    def make_mock_block_class():
+        mock_class = MagicMock()
+        mock_instance = MagicMock()
+        mock_instance.disabled = False
+        mock_class.return_value = mock_instance
+        return mock_class
+
+    mock_blocks = {
+        "block-1": make_mock_block_class(),
+        "block-2": make_mock_block_class(),
+        "block-3": make_mock_block_class(),
     }
 
+    # Mock embedded count query (2 blocks have embeddings)
     mock_embedded = [{"count": 2}]
 
     with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
+        "backend.blocks.get_blocks",
+        return_value=mock_blocks,
     ):
         with patch(
             "backend.api.features.store.content_handlers.query_raw_with_schema",
@@ -290,123 +150,21 @@ async def test_block_handler_get_stats():
             assert stats["without_embeddings"] == 1
 
 
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_stats_skips_broken():
-    """get_stats skips broken blocks instead of crashing."""
-    handler = BlockHandler()
-
-    blocks = {
-        "good": _make_block_class(name="Good"),
-        "bad": _make_block_class(raise_on_init=RuntimeError("boom")),
-    }
-
-    mock_embedded = [{"count": 1}]
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=mock_embedded,
-        ):
-            stats = await handler.get_stats()
-
-            assert stats["total"] == 1  # only the good block
-            assert stats["with_embeddings"] == 1
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_handles_none_name():
-    """When block.name is None the fallback display name logic is used."""
-    handler = BlockHandler()
-
-    blocks = {
-        "none-name-block": _make_block_class(
-            name="placeholder",  # will be overridden to None below
-            description="A block with no name",
-        ),
-    }
-    # Override the name to None after construction so _make_block_class
-    # doesn't interfere with the mock wiring.
-    blocks["none-name-block"].return_value.name = None
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            # display_name should be "" because block.name is None
-            # searchable_text should still contain the description
-            assert "A block with no name" in items[0].searchable_text
-            # metadata["name"] falls back to block_id when both display_name
-            # and block.name are falsy, ensuring it is always a non-empty string.
-            assert items[0].metadata["name"] == "none-name-block"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_handles_empty_attributes():
-    """Test BlockHandler handles blocks with empty/falsy attribute values."""
-    handler = BlockHandler()
-
-    blocks = {"block-minimal": _make_block_class(name="Minimal Block")}
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            assert items[0].searchable_text == "Minimal Block"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_skips_failed_blocks():
-    """Test BlockHandler skips blocks that fail to instantiate."""
-    handler = BlockHandler()
-
-    blocks = {
-        "good-block": _make_block_class(name="Good Block", description="Works fine"),
-        "bad-block": _make_block_class(raise_on_init=Exception("Instantiation failed")),
-    }
-
-    with patch(
-        "backend.api.features.store.content_handlers.get_blocks", return_value=blocks
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            assert items[0].content_id == "good-block"
-
-
-# ---------------------------------------------------------------------------
-# DocumentationHandler
-# ---------------------------------------------------------------------------
-
-
 @pytest.mark.asyncio(loop_scope="session")
 async def test_documentation_handler_get_missing_items(tmp_path, mocker):
     """Test DocumentationHandler discovers docs without embeddings."""
     handler = DocumentationHandler()
 
+    # Create temporary docs directory with test files
     docs_root = tmp_path / "docs"
     docs_root.mkdir()
+
     (docs_root / "guide.md").write_text("# Getting Started\n\nThis is a guide.")
     (docs_root / "api.mdx").write_text("# API Reference\n\nAPI documentation.")
 
+    # Mock _get_docs_root to return temp dir
     with patch.object(handler, "_get_docs_root", return_value=docs_root):
+        # Mock existing embeddings query (no embeddings exist)
         with patch(
             "backend.api.features.store.content_handlers.query_raw_with_schema",
             return_value=[],
@@ -415,6 +173,7 @@ async def test_documentation_handler_get_missing_items(tmp_path, mocker):
 
             assert len(items) == 2
 
+            # Check guide.md (content_id format: doc_path::section_index)
             guide_item = next(
                 (item for item in items if item.content_id == "guide.md::0"), None
             )
@@ -425,6 +184,7 @@ async def test_documentation_handler_get_missing_items(tmp_path, mocker):
             assert guide_item.metadata["doc_title"] == "Getting Started"
             assert guide_item.user_id is None
 
+            # Check api.mdx (content_id format: doc_path::section_index)
             api_item = next(
                 (item for item in items if item.content_id == "api.mdx::0"), None
             )
@@ -437,12 +197,14 @@ async def test_documentation_handler_get_stats(tmp_path, mocker):
     """Test DocumentationHandler returns correct stats."""
     handler = DocumentationHandler()
 
+    # Create temporary docs directory
     docs_root = tmp_path / "docs"
     docs_root.mkdir()
     (docs_root / "doc1.md").write_text("# Doc 1")
     (docs_root / "doc2.md").write_text("# Doc 2")
     (docs_root / "doc3.mdx").write_text("# Doc 3")
 
+    # Mock embedded count query (1 doc has embedding)
     mock_embedded = [{"count": 1}]
 
     with patch.object(handler, "_get_docs_root", return_value=docs_root):
@@ -462,11 +224,13 @@ async def test_documentation_handler_title_extraction(tmp_path):
     """Test DocumentationHandler extracts title from markdown heading."""
     handler = DocumentationHandler()
 
+    # Test with heading
     doc_with_heading = tmp_path / "with_heading.md"
     doc_with_heading.write_text("# My Title\n\nContent here")
     title = handler._extract_doc_title(doc_with_heading)
     assert title == "My Title"
 
+    # Test without heading
     doc_without_heading = tmp_path / "no-heading.md"
     doc_without_heading.write_text("Just content, no heading")
     title = handler._extract_doc_title(doc_without_heading)
@@ -478,6 +242,7 @@ async def test_documentation_handler_markdown_chunking(tmp_path):
     """Test DocumentationHandler chunks markdown by headings."""
     handler = DocumentationHandler()
 
+    # Test document with multiple sections
     doc_with_sections = tmp_path / "sections.md"
     doc_with_sections.write_text(
         "# Document Title\n\n"
@@ -489,6 +254,7 @@ async def test_documentation_handler_markdown_chunking(tmp_path):
     )
     sections = handler._chunk_markdown_by_headings(doc_with_sections)
 
+    # Should have 3 sections: intro (with doc title), section one, section two
     assert len(sections) == 3
     assert sections[0].title == "Document Title"
     assert sections[0].index == 0
@@ -502,6 +268,7 @@ async def test_documentation_handler_markdown_chunking(tmp_path):
     assert sections[2].index == 2
     assert "Content for section two" in sections[2].content
 
+    # Test document without headings
     doc_no_sections = tmp_path / "no-sections.md"
     doc_no_sections.write_text("Just plain content without any headings.")
     sections = handler._chunk_markdown_by_headings(doc_no_sections)
@@ -515,39 +282,21 @@ async def test_documentation_handler_section_content_ids():
     """Test DocumentationHandler creates and parses section content IDs."""
     handler = DocumentationHandler()
 
+    # Test making content ID
     content_id = handler._make_section_content_id("docs/guide.md", 2)
     assert content_id == "docs/guide.md::2"
 
+    # Test parsing content ID
     doc_path, section_index = handler._parse_section_content_id("docs/guide.md::2")
     assert doc_path == "docs/guide.md"
     assert section_index == 2
 
+    # Test parsing legacy format (no section index)
     doc_path, section_index = handler._parse_section_content_id("docs/old-format.md")
     assert doc_path == "docs/old-format.md"
     assert section_index == 0
 
 
-@pytest.mark.asyncio(loop_scope="session")
-async def test_documentation_handler_missing_docs_directory():
-    """Test DocumentationHandler handles missing docs directory gracefully."""
-    handler = DocumentationHandler()
-
-    fake_path = Path("/nonexistent/docs")
-    with patch.object(handler, "_get_docs_root", return_value=fake_path):
-        items = await handler.get_missing_items(batch_size=10)
-        assert items == []
-
-        stats = await handler.get_stats()
-        assert stats["total"] == 0
-        assert stats["with_embeddings"] == 0
-        assert stats["without_embeddings"] == 0
-
-
-# ---------------------------------------------------------------------------
-# Registry
-# ---------------------------------------------------------------------------
-
-
 @pytest.mark.asyncio(loop_scope="session")
 async def test_content_handlers_registry():
     """Test all content types are registered."""
@@ -558,3 +307,88 @@ async def test_content_handlers_registry():
     assert isinstance(CONTENT_HANDLERS[ContentType.STORE_AGENT], StoreAgentHandler)
     assert isinstance(CONTENT_HANDLERS[ContentType.BLOCK], BlockHandler)
     assert isinstance(CONTENT_HANDLERS[ContentType.DOCUMENTATION], DocumentationHandler)
+
+
+@pytest.mark.asyncio(loop_scope="session")
+async def test_block_handler_handles_empty_attributes():
+    """Test BlockHandler handles blocks with empty/falsy attribute values."""
+    handler = BlockHandler()
+
+    # Mock block with empty values (all attributes exist but are falsy)
+    mock_block_class = MagicMock()
+    mock_block_instance = MagicMock()
+    mock_block_instance.name = "Minimal Block"
+    mock_block_instance.disabled = False
+    mock_block_instance.description = ""
+    mock_block_instance.categories = set()
+    mock_block_instance.input_schema.model_fields = {}
+    mock_block_instance.input_schema.get_credentials_fields_info.return_value = {}
+    mock_block_class.return_value = mock_block_instance
+
+    mock_blocks = {"block-minimal": mock_block_class}
+
+    with patch(
+        "backend.blocks.get_blocks",
+        return_value=mock_blocks,
+    ):
+        with patch(
+            "backend.api.features.store.content_handlers.query_raw_with_schema",
+            return_value=[],
+        ):
+            items = await handler.get_missing_items(batch_size=10)
+
+            assert len(items) == 1
+            assert items[0].searchable_text == "Minimal Block"
+
+
+@pytest.mark.asyncio(loop_scope="session")
+async def test_block_handler_skips_failed_blocks():
+    """Test BlockHandler skips blocks that fail to instantiate."""
+    handler = BlockHandler()
+
+    # Mock one good block and one bad block
+    good_block = MagicMock()
+    good_instance = MagicMock()
+    good_instance.name = "Good Block"
+    good_instance.description = "Works fine"
+    good_instance.categories = []
+    good_instance.disabled = False
+    good_instance.input_schema.model_fields = {}
+    good_instance.input_schema.get_credentials_fields_info.return_value = {}
+    good_block.return_value = good_instance
+
+    bad_block = MagicMock()
+    bad_block.side_effect = Exception("Instantiation failed")
+
+    mock_blocks = {"good-block": good_block, "bad-block": bad_block}
+
+    with patch(
+        "backend.blocks.get_blocks",
+        return_value=mock_blocks,
+    ):
+        with patch(
+            "backend.api.features.store.content_handlers.query_raw_with_schema",
+            return_value=[],
+        ):
+            items = await handler.get_missing_items(batch_size=10)
+
+            # Should only get the good block
+            assert len(items) == 1
+            assert items[0].content_id == "good-block"
+
+
+@pytest.mark.asyncio(loop_scope="session")
+async def test_documentation_handler_missing_docs_directory():
+    """Test DocumentationHandler handles missing docs directory gracefully."""
+    handler = DocumentationHandler()
+
+    # Mock _get_docs_root to return non-existent path
+    fake_path = Path("/nonexistent/docs")
+    with patch.object(handler, "_get_docs_root", return_value=fake_path):
+        items = await handler.get_missing_items(batch_size=10)
+        assert items == []
+
+        stats = await handler.get_stats()
+        assert stats["total"] == 0
+        assert stats["with_embeddings"] == 0
+        assert stats["without_embeddings"] == 0

autogpt_platform/backend/backend/api/features/store/embeddings.py

@@ -15,7 +15,6 @@ from prisma.enums import ContentType
 from tiktoken import encoding_for_model
 
 from backend.api.features.store.content_handlers import CONTENT_HANDLERS
-from backend.blocks import get_blocks
 from backend.data.db import execute_raw_with_schema, query_raw_with_schema
 from backend.util.clients import get_openai_client
 from backend.util.json import dumps
@@ -663,6 +662,8 @@ async def cleanup_orphaned_embeddings() -> dict[str, Any]:
                 )
                 current_ids = {row["id"] for row in valid_agents}
             elif content_type == ContentType.BLOCK:
+                from backend.blocks import get_blocks
+
                 current_ids = set(get_blocks().keys())
             elif content_type == ContentType.DOCUMENTATION:
                 # Use DocumentationHandler to get section-based content IDs

autogpt_platform/backend/backend/api/features/store/hybrid_search.py

@@ -31,10 +31,12 @@ logger = logging.getLogger(__name__)
 
 
 def tokenize(text: str) -> list[str]:
-    """Tokenize text for BM25."""
+    """Simple tokenizer for BM25 - lowercase and split on non-alphanumeric."""
     if not text:
         return []
-    return re.findall(r"\b\w+\b", text.lower())
+    # Lowercase and split on non-alphanumeric characters
+    tokens = re.findall(r"\b\w+\b", text.lower())
+    return tokens
 
 
 def bm25_rerank(

autogpt_platform/backend/backend/api/features/store/hybrid_search_test.py

@@ -14,27 +14,9 @@ from backend.api.features.store.hybrid_search import (
     HybridSearchWeights,
     UnifiedSearchWeights,
     hybrid_search,
-    tokenize,
     unified_hybrid_search,
 )
 
-# ---------------------------------------------------------------------------
-# tokenize (BM25)
-# ---------------------------------------------------------------------------
-
-
-@pytest.mark.parametrize(
-    "input_text, expected",
-    [
-        ("AITextGeneratorBlock", ["aitextgeneratorblock"]),
-        ("hello world", ["hello", "world"]),
-        ("", []),
-        ("HTTPRequest", ["httprequest"]),
-    ],
-)
-def test_tokenize(input_text: str, expected: list[str]):
-    assert tokenize(input_text) == expected
-
 
 @pytest.mark.asyncio(loop_scope="session")
 @pytest.mark.integration

autogpt_platform/backend/backend/api/features/store/text_utils.py

@@ -1,5 +0,0 @@
-"""Backward-compatibility shim — ``split_camelcase`` now lives in backend.util.text."""
-
-from backend.util.text import split_camelcase  # noqa: F401
-
-__all__ = ["split_camelcase"]

autogpt_platform/backend/backend/api/features/store/text_utils_test.py

@@ -1,49 +0,0 @@
-"""Tests for split_camelcase (now in backend.util.text)."""
-
-import pytest
-
-from backend.util.text import split_camelcase
-
-# ---------------------------------------------------------------------------
-# split_camelcase
-# ---------------------------------------------------------------------------
-
-
-@pytest.mark.parametrize(
-    "input_text, expected",
-    [
-        ("AITextGeneratorBlock", "AI Text Generator Block"),
-        ("HTTPRequestBlock", "HTTP Request Block"),
-        ("simpleWord", "simple Word"),
-        ("already spaced", "already spaced"),
-        ("XMLParser", "XML Parser"),
-        ("getHTTPResponse", "get HTTP Response"),
-        ("Block", "Block"),
-        ("", ""),
-        ("OAuth2Block", "OAuth2 Block"),
-        ("IOError", "IO Error"),
-        ("getHTTPSResponse", "get HTTPS Response"),
-        # Known limitation: single-letter uppercase prefixes are NOT split.
-        # "ABlock" stays "ABlock" because the algorithm requires the left
-        # part of an uppercase run to retain at least 2 uppercase chars.
-        ("ABlock", "ABlock"),
-        # Digit-to-uppercase transitions
-        ("Base64Encoder", "Base64 Encoder"),
-        ("UTF8Decoder", "UTF8 Decoder"),
-        # Pure digits — no camelCase boundaries to split
-        ("123", "123"),
-        # Known limitation: single-letter uppercase segments after digits
-        # are not split from the following word.  "3D" is only 1 uppercase
-        # char so the uppercase-run rule cannot fire, producing "3 DRenderer"
-        # rather than the ideal "3D Renderer".
-        ("3DRenderer", "3 DRenderer"),
-        # Exception list — compound terms that should stay together
-        ("YouTubeBlock", "YouTube Block"),
-        ("OpenAIBlock", "OpenAI Block"),
-        ("AutoGPTAgent", "AutoGPT Agent"),
-        ("GitHubIntegration", "GitHub Integration"),
-        ("LinkedInBlock", "LinkedIn Block"),
-    ],
-)
-def test_split_camelcase(input_text: str, expected: str):
-    assert split_camelcase(input_text) == expected

autogpt_platform/backend/backend/copilot/config.py

@@ -115,7 +115,7 @@ class ChatConfig(BaseSettings):
         description="E2B sandbox template to use for copilot sessions.",
     )
     e2b_sandbox_timeout: int = Field(
-        default=300,  # 5 min safety net — explicit per-turn pause is the primary mechanism
+        default=420,  # 7 min safety net — allows headroom for compaction retries
         description="E2B sandbox running-time timeout (seconds). "
         "E2B timeout is wall-clock (not idle). Explicit per-turn pause is the primary "
         "mechanism; this is the safety net.",

autogpt_platform/backend/backend/copilot/response_model.py

@@ -43,6 +43,7 @@ class ResponseType(str, Enum):
     ERROR = "error"
     USAGE = "usage"
     HEARTBEAT = "heartbeat"
+    STATUS = "status"
 
 
 class StreamBaseResponse(BaseModel):
@@ -232,3 +233,26 @@ class StreamHeartbeat(StreamBaseResponse):
     def to_sse(self) -> str:
         """Convert to SSE comment format to keep connection alive."""
         return ": heartbeat\n\n"
+
+
+class StreamStatus(StreamBaseResponse):
+    """Transient status notification shown to the user during long operations.
+
+    Used to provide feedback when the backend performs behind-the-scenes work
+    (e.g., compacting conversation context on a retry) that would otherwise
+    leave the user staring at an unexplained pause.
+    """
+
+    type: ResponseType = ResponseType.STATUS
+    message: str = Field(..., description="Human-readable status message")
+
+    def to_sse(self) -> str:
+        """Encode as an SSE comment so the AI SDK stream parser ignores it.
+
+        The frontend AI SDK validates every ``data:`` line against a strict
+        Zod union of known chunk types.  ``"status"`` is not in that union,
+        so sending it as ``data:`` would cause a schema-validation error that
+        breaks the entire stream.  Using an SSE comment (``:``) keeps the
+        connection alive and is silently discarded by ``EventSource`` parsers.
+        """
+        return f": status {self.message}\n\n"

autogpt_platform/backend/backend/copilot/sdk/compaction.py

@@ -12,6 +12,7 @@ import asyncio
 import logging
 import uuid
 from dataclasses import dataclass, field
+from typing import Any
 
 from ..constants import COMPACTION_DONE_MSG, COMPACTION_TOOL_NAME
 from ..model import ChatMessage, ChatSession
@@ -119,14 +120,12 @@ def filter_compaction_messages(
     filtered: list[ChatMessage] = []
     for msg in messages:
         if msg.role == "assistant" and msg.tool_calls:
+            real_calls: list[dict[str, Any]] = []
             for tc in msg.tool_calls:
                 if tc.get("function", {}).get("name") == COMPACTION_TOOL_NAME:
                     compaction_ids.add(tc.get("id", ""))
-            real_calls = [
-                tc
-                for tc in msg.tool_calls
-                if tc.get("function", {}).get("name") != COMPACTION_TOOL_NAME
-            ]
+                else:
+                    real_calls.append(tc)
             if not real_calls and not msg.content:
                 continue
         if msg.role == "tool" and msg.tool_call_id in compaction_ids:
@@ -222,6 +221,7 @@ class CompactionTracker:
 
     def reset_for_query(self) -> None:
         """Reset per-query state before a new SDK query."""
+        self._compact_start.clear()
         self._done = False
         self._start_emitted = False
         self._tool_call_id = ""

autogpt_platform/backend/backend/copilot/sdk/conftest.py

@@ -0,0 +1,41 @@
+"""Shared test fixtures for copilot SDK tests."""
+
+from __future__ import annotations
+
+from uuid import uuid4
+
+from backend.util import json
+
+
+def build_test_transcript(pairs: list[tuple[str, str]]) -> str:
+    """Build a minimal valid JSONL transcript from (role, content) pairs.
+
+    Use this helper in any copilot SDK test that needs a well-formed
+    transcript without hitting the real storage layer.
+    """
+    lines: list[str] = []
+    last_uuid: str | None = None
+    for role, content in pairs:
+        uid = str(uuid4())
+        entry_type = "assistant" if role == "assistant" else "user"
+        msg: dict = {"role": role, "content": content}
+        if role == "assistant":
+            msg.update(
+                {
+                    "model": "",
+                    "id": f"msg_{uid[:8]}",
+                    "type": "message",
+                    "content": [{"type": "text", "text": content}],
+                    "stop_reason": "end_turn",
+                    "stop_sequence": None,
+                }
+            )
+        entry = {
+            "type": entry_type,
+            "uuid": uid,
+            "parentUuid": last_uuid,
+            "message": msg,
+        }
+        lines.append(json.dumps(entry, separators=(",", ":")))
+        last_uuid = uid
+    return "\n".join(lines) + "\n"

autogpt_platform/backend/backend/copilot/sdk/prompt_too_long_test.py

@@ -0,0 +1,552 @@
+"""Tests for retry logic and transcript compaction helpers."""
+
+from __future__ import annotations
+
+from unittest.mock import AsyncMock, patch
+from uuid import uuid4
+
+import pytest
+
+from backend.util import json
+
+from .conftest import build_test_transcript as _build_transcript
+from .service import _is_prompt_too_long
+from .transcript import (
+    _flatten_assistant_content,
+    _flatten_tool_result_content,
+    _messages_to_transcript,
+    _transcript_to_messages,
+    compact_transcript,
+    validate_transcript,
+)
+
+# ---------------------------------------------------------------------------
+# _flatten_assistant_content
+# ---------------------------------------------------------------------------
+
+
+class TestFlattenAssistantContent:
+    def test_text_blocks(self):
+        blocks = [
+            {"type": "text", "text": "Hello"},
+            {"type": "text", "text": "World"},
+        ]
+        assert _flatten_assistant_content(blocks) == "Hello\nWorld"
+
+    def test_tool_use_blocks(self):
+        blocks = [{"type": "tool_use", "name": "read_file", "input": {}}]
+        assert _flatten_assistant_content(blocks) == "[tool_use: read_file]"
+
+    def test_mixed_blocks(self):
+        blocks = [
+            {"type": "text", "text": "Let me read that."},
+            {"type": "tool_use", "name": "Read", "input": {"path": "/foo"}},
+        ]
+        result = _flatten_assistant_content(blocks)
+        assert "Let me read that." in result
+        assert "[tool_use: Read]" in result
+
+    def test_raw_strings(self):
+        assert _flatten_assistant_content(["hello", "world"]) == "hello\nworld"
+
+    def test_unknown_block_type_preserved_as_placeholder(self):
+        blocks = [
+            {"type": "text", "text": "See this image:"},
+            {"type": "image", "source": {"type": "base64", "data": "..."}},
+        ]
+        result = _flatten_assistant_content(blocks)
+        assert "See this image:" in result
+        assert "[__image__]" in result
+
+    def test_empty(self):
+        assert _flatten_assistant_content([]) == ""
+
+
+# ---------------------------------------------------------------------------
+# _flatten_tool_result_content
+# ---------------------------------------------------------------------------
+
+
+class TestFlattenToolResultContent:
+    def test_tool_result_with_text(self):
+        blocks = [
+            {
+                "type": "tool_result",
+                "tool_use_id": "123",
+                "content": [{"type": "text", "text": "file contents here"}],
+            }
+        ]
+        assert _flatten_tool_result_content(blocks) == "file contents here"
+
+    def test_tool_result_with_string_content(self):
+        blocks = [{"type": "tool_result", "tool_use_id": "123", "content": "ok"}]
+        assert _flatten_tool_result_content(blocks) == "ok"
+
+    def test_text_block(self):
+        blocks = [{"type": "text", "text": "plain text"}]
+        assert _flatten_tool_result_content(blocks) == "plain text"
+
+    def test_raw_string(self):
+        assert _flatten_tool_result_content(["raw"]) == "raw"
+
+    def test_tool_result_with_none_content(self):
+        """tool_result with content=None should produce empty string."""
+        blocks = [{"type": "tool_result", "tool_use_id": "x", "content": None}]
+        assert _flatten_tool_result_content(blocks) == ""
+
+    def test_tool_result_with_empty_list_content(self):
+        """tool_result with content=[] should produce empty string."""
+        blocks = [{"type": "tool_result", "tool_use_id": "x", "content": []}]
+        assert _flatten_tool_result_content(blocks) == ""
+
+    def test_empty(self):
+        assert _flatten_tool_result_content([]) == ""
+
+    def test_nested_dict_without_text(self):
+        """Dict blocks without text key use json.dumps fallback."""
+        blocks = [
+            {
+                "type": "tool_result",
+                "tool_use_id": "x",
+                "content": [{"type": "image", "source": "data:..."}],
+            }
+        ]
+        result = _flatten_tool_result_content(blocks)
+        assert "image" in result  # json.dumps fallback
+
+    def test_unknown_block_type_preserved_as_placeholder(self):
+        blocks = [{"type": "image", "source": {"type": "base64", "data": "..."}}]
+        result = _flatten_tool_result_content(blocks)
+        assert "[__image__]" in result
+
+
+# ---------------------------------------------------------------------------
+# _transcript_to_messages
+# ---------------------------------------------------------------------------
+
+
+def _make_entry(entry_type: str, role: str, content: str | list, **kwargs) -> str:
+    """Build a JSONL line for testing."""
+    uid = str(uuid4())
+    msg: dict = {"role": role, "content": content}
+    msg.update(kwargs)
+    entry = {
+        "type": entry_type,
+        "uuid": uid,
+        "parentUuid": None,
+        "message": msg,
+    }
+    return json.dumps(entry, separators=(",", ":"))
+
+
+class TestTranscriptToMessages:
+    def test_basic_roundtrip(self):
+        lines = [
+            _make_entry("user", "user", "Hello"),
+            _make_entry("assistant", "assistant", [{"type": "text", "text": "Hi"}]),
+        ]
+        content = "\n".join(lines) + "\n"
+        messages = _transcript_to_messages(content)
+        assert len(messages) == 2
+        assert messages[0] == {"role": "user", "content": "Hello"}
+        assert messages[1] == {"role": "assistant", "content": "Hi"}
+
+    def test_skips_strippable_types(self):
+        """Progress and metadata entries are excluded."""
+        lines = [
+            _make_entry("user", "user", "Hello"),
+            json.dumps(
+                {
+                    "type": "progress",
+                    "uuid": str(uuid4()),
+                    "parentUuid": None,
+                    "message": {"role": "assistant", "content": "..."},
+                }
+            ),
+            _make_entry("assistant", "assistant", [{"type": "text", "text": "Hi"}]),
+        ]
+        content = "\n".join(lines) + "\n"
+        messages = _transcript_to_messages(content)
+        assert len(messages) == 2
+
+    def test_empty_content(self):
+        assert _transcript_to_messages("") == []
+
+    def test_tool_result_content(self):
+        """User entries with tool_result content blocks are flattened."""
+        lines = [
+            _make_entry(
+                "user",
+                "user",
+                [
+                    {
+                        "type": "tool_result",
+                        "tool_use_id": "123",
+                        "content": "tool output",
+                    }
+                ],
+            ),
+        ]
+        content = "\n".join(lines) + "\n"
+        messages = _transcript_to_messages(content)
+        assert len(messages) == 1
+        assert messages[0]["content"] == "tool output"
+
+    def test_malformed_json_lines_skipped(self):
+        """Malformed JSON lines in transcript are silently skipped."""
+        lines = [
+            _make_entry("user", "user", "Hello"),
+            "this is not valid json",
+            _make_entry("assistant", "assistant", [{"type": "text", "text": "Hi"}]),
+        ]
+        content = "\n".join(lines) + "\n"
+        messages = _transcript_to_messages(content)
+        assert len(messages) == 2
+
+    def test_empty_lines_skipped(self):
+        """Empty lines and whitespace-only lines are skipped."""
+        lines = [
+            _make_entry("user", "user", "Hello"),
+            "",
+            "   ",
+            _make_entry("assistant", "assistant", [{"type": "text", "text": "Hi"}]),
+        ]
+        content = "\n".join(lines) + "\n"
+        messages = _transcript_to_messages(content)
+        assert len(messages) == 2
+
+    def test_unicode_content_preserved(self):
+        """Unicode characters survive transcript roundtrip."""
+        lines = [
+            _make_entry("user", "user", "Hello 你好 🌍"),
+            _make_entry(
+                "assistant",
+                "assistant",
+                [{"type": "text", "text": "Bonjour 日本語 émojis 🎉"}],
+            ),
+        ]
+        content = "\n".join(lines) + "\n"
+        messages = _transcript_to_messages(content)
+        assert messages[0]["content"] == "Hello 你好 🌍"
+        assert messages[1]["content"] == "Bonjour 日本語 émojis 🎉"
+
+    def test_entry_without_role_skipped(self):
+        """Entries with missing role in message are skipped."""
+        entry_no_role = json.dumps(
+            {
+                "type": "user",
+                "uuid": str(uuid4()),
+                "parentUuid": None,
+                "message": {"content": "no role here"},
+            }
+        )
+        lines = [
+            entry_no_role,
+            _make_entry("user", "user", "Hello"),
+        ]
+        content = "\n".join(lines) + "\n"
+        messages = _transcript_to_messages(content)
+        assert len(messages) == 1
+        assert messages[0]["content"] == "Hello"
+
+    def test_tool_use_and_result_pairs(self):
+        """Tool use + tool result pairs are properly flattened."""
+        lines = [
+            _make_entry(
+                "assistant",
+                "assistant",
+                [
+                    {"type": "text", "text": "Let me check."},
+                    {"type": "tool_use", "name": "read_file", "input": {"path": "/x"}},
+                ],
+            ),
+            _make_entry(
+                "user",
+                "user",
+                [
+                    {
+                        "type": "tool_result",
+                        "tool_use_id": "abc",
+                        "content": [{"type": "text", "text": "file contents"}],
+                    }
+                ],
+            ),
+        ]
+        content = "\n".join(lines) + "\n"
+        messages = _transcript_to_messages(content)
+        assert len(messages) == 2
+        assert "Let me check." in messages[0]["content"]
+        assert "[tool_use: read_file]" in messages[0]["content"]
+        assert messages[1]["content"] == "file contents"
+
+
+# ---------------------------------------------------------------------------
+# _messages_to_transcript
+# ---------------------------------------------------------------------------
+
+
+class TestMessagesToTranscript:
+    def test_produces_valid_jsonl(self):
+        messages = [
+            {"role": "user", "content": "Hello"},
+            {"role": "assistant", "content": "Hi there"},
+        ]
+        result = _messages_to_transcript(messages)
+        lines = result.strip().split("\n")
+        assert len(lines) == 2
+        for line in lines:
+            parsed = json.loads(line)
+            assert "type" in parsed
+            assert "uuid" in parsed
+            assert "message" in parsed
+
+    def test_assistant_has_proper_structure(self):
+        messages = [{"role": "assistant", "content": "Hello"}]
+        result = _messages_to_transcript(messages)
+        entry = json.loads(result.strip())
+        assert entry["type"] == "assistant"
+        msg = entry["message"]
+        assert msg["role"] == "assistant"
+        assert msg["type"] == "message"
+        assert msg["stop_reason"] == "end_turn"
+        assert isinstance(msg["content"], list)
+        assert msg["content"][0]["type"] == "text"
+
+    def test_user_has_plain_content(self):
+        messages = [{"role": "user", "content": "Hi"}]
+        result = _messages_to_transcript(messages)
+        entry = json.loads(result.strip())
+        assert entry["type"] == "user"
+        assert entry["message"]["content"] == "Hi"
+
+    def test_parent_uuid_chain(self):
+        messages = [
+            {"role": "user", "content": "A"},
+            {"role": "assistant", "content": "B"},
+            {"role": "user", "content": "C"},
+        ]
+        result = _messages_to_transcript(messages)
+        lines = result.strip().split("\n")
+        entries = [json.loads(line) for line in lines]
+        assert entries[0]["parentUuid"] == ""
+        assert entries[1]["parentUuid"] == entries[0]["uuid"]
+        assert entries[2]["parentUuid"] == entries[1]["uuid"]
+
+    def test_empty_messages(self):
+        assert _messages_to_transcript([]) == ""
+
+    def test_output_is_valid_transcript(self):
+        """Output should pass validate_transcript if it has assistant entries."""
+        messages = [
+            {"role": "user", "content": "Hello"},
+            {"role": "assistant", "content": "Hi"},
+        ]
+        result = _messages_to_transcript(messages)
+        assert validate_transcript(result)
+
+    def test_roundtrip_to_messages(self):
+        """Messages → transcript → messages preserves structure."""
+        original = [
+            {"role": "user", "content": "Hello"},
+            {"role": "assistant", "content": "Hi there"},
+            {"role": "user", "content": "How are you?"},
+        ]
+        transcript = _messages_to_transcript(original)
+        restored = _transcript_to_messages(transcript)
+        assert len(restored) == len(original)
+        for orig, rest in zip(original, restored):
+            assert orig["role"] == rest["role"]
+            assert orig["content"] == rest["content"]
+
+
+# ---------------------------------------------------------------------------
+# compact_transcript
+# ---------------------------------------------------------------------------
+
+
+class TestCompactTranscript:
+    @pytest.mark.asyncio
+    async def test_too_few_messages_returns_none(self):
+        """compact_transcript returns None when transcript has < 2 messages."""
+        transcript = _build_transcript([("user", "Hello")])
+        with patch(
+            "backend.copilot.config.ChatConfig",
+            return_value=type(
+                "Cfg", (), {"model": "m", "api_key": "k", "base_url": "u"}
+            )(),
+        ):
+            result = await compact_transcript(transcript, model="test-model")
+        assert result is None
+
+    @pytest.mark.asyncio
+    async def test_returns_none_when_not_compacted(self):
+        """When compress_context says no compaction needed, returns None.
+        The compressor couldn't reduce it, so retrying with the same
+        content would fail identically."""
+        transcript = _build_transcript(
+            [
+                ("user", "Hello"),
+                ("assistant", "Hi there"),
+            ]
+        )
+        mock_result = type(
+            "CompressResult",
+            (),
+            {
+                "was_compacted": False,
+                "messages": [],
+                "original_token_count": 100,
+                "token_count": 100,
+                "messages_summarized": 0,
+                "messages_dropped": 0,
+            },
+        )()
+        with (
+            patch(
+                "backend.copilot.config.ChatConfig",
+                return_value=type(
+                    "Cfg", (), {"model": "m", "api_key": "k", "base_url": "u"}
+                )(),
+            ),
+            patch(
+                "backend.copilot.sdk.transcript._run_compression",
+                new_callable=AsyncMock,
+                return_value=mock_result,
+            ),
+        ):
+            result = await compact_transcript(transcript, model="test-model")
+        assert result is None
+
+    @pytest.mark.asyncio
+    async def test_returns_compacted_transcript(self):
+        """When compaction succeeds, returns a valid compacted transcript."""
+        transcript = _build_transcript(
+            [
+                ("user", "Hello"),
+                ("assistant", "Hi"),
+                ("user", "More"),
+                ("assistant", "Details"),
+            ]
+        )
+        compacted_msgs = [
+            {"role": "user", "content": "[summary]"},
+            {"role": "assistant", "content": "Summarized response"},
+        ]
+        mock_result = type(
+            "CompressResult",
+            (),
+            {
+                "was_compacted": True,
+                "messages": compacted_msgs,
+                "original_token_count": 500,
+                "token_count": 100,
+                "messages_summarized": 2,
+                "messages_dropped": 0,
+            },
+        )()
+        with (
+            patch(
+                "backend.copilot.config.ChatConfig",
+                return_value=type(
+                    "Cfg", (), {"model": "m", "api_key": "k", "base_url": "u"}
+                )(),
+            ),
+            patch(
+                "backend.copilot.sdk.transcript._run_compression",
+                new_callable=AsyncMock,
+                return_value=mock_result,
+            ),
+        ):
+            result = await compact_transcript(transcript, model="test-model")
+        assert result is not None
+        assert validate_transcript(result)
+        msgs = _transcript_to_messages(result)
+        assert len(msgs) == 2
+        assert msgs[1]["content"] == "Summarized response"
+
+    @pytest.mark.asyncio
+    async def test_returns_none_on_compression_failure(self):
+        """When _run_compression raises, returns None."""
+        transcript = _build_transcript(
+            [
+                ("user", "Hello"),
+                ("assistant", "Hi"),
+            ]
+        )
+        with (
+            patch(
+                "backend.copilot.config.ChatConfig",
+                return_value=type(
+                    "Cfg", (), {"model": "m", "api_key": "k", "base_url": "u"}
+                )(),
+            ),
+            patch(
+                "backend.copilot.sdk.transcript._run_compression",
+                new_callable=AsyncMock,
+                side_effect=RuntimeError("LLM unavailable"),
+            ),
+        ):
+            result = await compact_transcript(transcript, model="test-model")
+        assert result is None
+
+
+# ---------------------------------------------------------------------------
+# _is_prompt_too_long
+# ---------------------------------------------------------------------------
+
+
+class TestIsPromptTooLong:
+    """Unit tests for _is_prompt_too_long pattern matching."""
+
+    def test_prompt_is_too_long(self):
+        err = RuntimeError("prompt is too long for model context")
+        assert _is_prompt_too_long(err) is True
+
+    def test_request_too_large(self):
+        err = Exception("request too large: 250000 tokens")
+        assert _is_prompt_too_long(err) is True
+
+    def test_maximum_context_length(self):
+        err = ValueError("maximum context length exceeded")
+        assert _is_prompt_too_long(err) is True
+
+    def test_context_length_exceeded(self):
+        err = Exception("context_length_exceeded")
+        assert _is_prompt_too_long(err) is True
+
+    def test_input_tokens_exceed(self):
+        err = Exception("input tokens exceed the max_tokens limit")
+        assert _is_prompt_too_long(err) is True
+
+    def test_input_is_too_long(self):
+        err = Exception("input is too long for the model")
+        assert _is_prompt_too_long(err) is True
+
+    def test_content_length_exceeds(self):
+        err = Exception("content length exceeds maximum")
+        assert _is_prompt_too_long(err) is True
+
+    def test_unrelated_error_returns_false(self):
+        err = RuntimeError("network timeout")
+        assert _is_prompt_too_long(err) is False
+
+    def test_auth_error_returns_false(self):
+        err = Exception("authentication failed: invalid API key")
+        assert _is_prompt_too_long(err) is False
+
+    def test_chained_exception_detected(self):
+        """Prompt-too-long error wrapped in another exception is detected."""
+        inner = RuntimeError("prompt is too long")
+        outer = Exception("SDK error")
+        outer.__cause__ = inner
+        assert _is_prompt_too_long(outer) is True
+
+    def test_case_insensitive(self):
+        err = Exception("PROMPT IS TOO LONG")
+        assert _is_prompt_too_long(err) is True
+
+    def test_old_max_tokens_exceeded_not_matched(self):
+        """The old broad 'max_tokens_exceeded' pattern was removed.
+        Only 'input tokens exceed' should match now."""
+        err = Exception("max_tokens_exceeded")
+        assert _is_prompt_too_long(err) is False

autogpt_platform/backend/backend/copilot/sdk/response_adapter.py

@@ -226,7 +226,7 @@ class SDKResponseAdapter:
                 responses.append(StreamFinish())
 
         else:
-            logger.debug(f"Unhandled SDK message type: {type(sdk_message).__name__}")
+            logger.debug("Unhandled SDK message type: %s", type(sdk_message).__name__)
 
         return responses
 

autogpt_platform/backend/backend/copilot/sdk/security_hooks.py

@@ -52,7 +52,7 @@ def _validate_workspace_path(
     if is_allowed_local_path(path, sdk_cwd):
         return {}
 
-    logger.warning(f"Blocked {tool_name} outside workspace: {path}")
+    logger.warning("Blocked %s outside workspace: %s", tool_name, path)
     workspace_hint = f" Allowed workspace: {sdk_cwd}" if sdk_cwd else ""
     return _deny(
         f"[SECURITY] Tool '{tool_name}' can only access files within the workspace "
@@ -71,7 +71,7 @@ def _validate_tool_access(
     """
     # Block forbidden tools
     if tool_name in BLOCKED_TOOLS:
-        logger.warning(f"Blocked tool access attempt: {tool_name}")
+        logger.warning("Blocked tool access attempt: %s", tool_name)
         return _deny(
             f"[SECURITY] Tool '{tool_name}' is blocked for security. "
             "This is enforced by the platform and cannot be bypassed. "
@@ -89,7 +89,9 @@ def _validate_tool_access(
     for pattern in DANGEROUS_PATTERNS:
         if re.search(pattern, input_str, re.IGNORECASE):
             logger.warning(
-                f"Blocked dangerous pattern in tool input: {pattern} in {tool_name}"
+                "Blocked dangerous pattern in tool input: %s in %s",
+                pattern,
+                tool_name,
             )
             return _deny(
                 "[SECURITY] Input contains a blocked pattern. "
@@ -111,7 +113,9 @@ def _validate_user_isolation(
         # the tool itself via _validate_ephemeral_path.
         path = tool_input.get("path", "") or tool_input.get("file_path", "")
         if path and ".." in path:
-            logger.warning(f"Blocked path traversal attempt: {path} by user {user_id}")
+            logger.warning(
+                "Blocked path traversal attempt: %s by user %s", path, user_id
+            )
             return {
                 "hookSpecificOutput": {
                     "hookEventName": "PreToolUse",
@@ -170,7 +174,7 @@ def create_security_hooks(
                 # Block background task execution first — denied calls
                 # should not consume a subtask slot.
                 if tool_input.get("run_in_background"):
-                    logger.info(f"[SDK] Blocked background Task, user={user_id}")
+                    logger.info("[SDK] Blocked background Task, user=%s", user_id)
                     return cast(
                         SyncHookJSONOutput,
                         _deny(
@@ -181,7 +185,9 @@ def create_security_hooks(
                     )
                 if len(task_tool_use_ids) >= max_subtasks:
                     logger.warning(
-                        f"[SDK] Task limit reached ({max_subtasks}), user={user_id}"
+                        "[SDK] Task limit reached (%d), user=%s",
+                        max_subtasks,
+                        user_id,
                     )
                     return cast(
                         SyncHookJSONOutput,
@@ -212,7 +218,7 @@ def create_security_hooks(
             if tool_name == "Task" and tool_use_id is not None:
                 task_tool_use_ids.add(tool_use_id)
 
-            logger.debug(f"[SDK] Tool start: {tool_name}, user={user_id}")
+            logger.debug("[SDK] Tool start: %s, user=%s", tool_name, user_id)
             return cast(SyncHookJSONOutput, {})
 
         def _release_task_slot(tool_name: str, tool_use_id: str | None) -> None:
@@ -282,8 +288,11 @@ def create_security_hooks(
             tool_name = cast(str, input_data.get("tool_name", ""))
             error = input_data.get("error", "Unknown error")
             logger.warning(
-                f"[SDK] Tool failed: {tool_name}, error={error}, "
-                f"user={user_id}, tool_use_id={tool_use_id}"
+                "[SDK] Tool failed: %s, error=%s, user=%s, tool_use_id=%s",
+                tool_name,
+                str(error).replace("\n", "").replace("\r", ""),
+                user_id,
+                tool_use_id,
             )
 
             _release_task_slot(tool_name, tool_use_id)
@@ -301,16 +310,19 @@ def create_security_hooks(
             This hook provides visibility into when compaction happens.
             """
             _ = context, tool_use_id
-            trigger = input_data.get("trigger", "auto")
             # Sanitize untrusted input before logging to prevent log injection
+            trigger = (
+                str(input_data.get("trigger", "auto"))
+                .replace("\n", "")
+                .replace("\r", "")
+            )
             transcript_path = (
                 str(input_data.get("transcript_path", ""))
                 .replace("\n", "")
                 .replace("\r", "")
             )
             logger.info(
-                "[SDK] Context compaction triggered: %s, user=%s, "
-                "transcript_path=%s",
+                "[SDK] Context compaction triggered: %s, user=%s, transcript_path=%s",
                 trigger,
                 user_id,
                 transcript_path,

autogpt_platform/backend/backend/copilot/sdk/service_helpers_test.py

@@ -0,0 +1,283 @@
+"""Unit tests for extracted service helpers.
+
+Covers ``_is_prompt_too_long``, ``_reduce_context``, ``_iter_sdk_messages``,
+and the ``ReducedContext`` named tuple.
+"""
+
+from __future__ import annotations
+
+import asyncio
+from collections.abc import AsyncGenerator
+from unittest.mock import AsyncMock, patch
+
+import pytest
+
+from .conftest import build_test_transcript as _build_transcript
+from .service import (
+    ReducedContext,
+    _is_prompt_too_long,
+    _iter_sdk_messages,
+    _reduce_context,
+)
+
+# ---------------------------------------------------------------------------
+# _is_prompt_too_long
+# ---------------------------------------------------------------------------
+
+
+class TestIsPromptTooLong:
+    def test_direct_match(self) -> None:
+        assert _is_prompt_too_long(Exception("prompt is too long")) is True
+
+    def test_case_insensitive(self) -> None:
+        assert _is_prompt_too_long(Exception("PROMPT IS TOO LONG")) is True
+
+    def test_no_match(self) -> None:
+        assert _is_prompt_too_long(Exception("network timeout")) is False
+
+    def test_request_too_large(self) -> None:
+        assert _is_prompt_too_long(Exception("request too large for model")) is True
+
+    def test_context_length_exceeded(self) -> None:
+        assert _is_prompt_too_long(Exception("context_length_exceeded")) is True
+
+    def test_max_tokens_exceeded_not_matched(self) -> None:
+        """'max_tokens_exceeded' is intentionally excluded (too broad)."""
+        assert _is_prompt_too_long(Exception("max_tokens_exceeded")) is False
+
+    def test_max_tokens_config_error_no_match(self) -> None:
+        """'max_tokens must be at least 1' should NOT match."""
+        assert _is_prompt_too_long(Exception("max_tokens must be at least 1")) is False
+
+    def test_chained_cause(self) -> None:
+        inner = Exception("prompt is too long")
+        outer = RuntimeError("SDK error")
+        outer.__cause__ = inner
+        assert _is_prompt_too_long(outer) is True
+
+    def test_chained_context(self) -> None:
+        inner = Exception("request too large")
+        outer = RuntimeError("wrapped")
+        outer.__context__ = inner
+        assert _is_prompt_too_long(outer) is True
+
+    def test_deep_chain(self) -> None:
+        bottom = Exception("maximum context length")
+        middle = RuntimeError("middle")
+        middle.__cause__ = bottom
+        top = ValueError("top")
+        top.__cause__ = middle
+        assert _is_prompt_too_long(top) is True
+
+    def test_chain_no_match(self) -> None:
+        inner = Exception("rate limit exceeded")
+        outer = RuntimeError("wrapped")
+        outer.__cause__ = inner
+        assert _is_prompt_too_long(outer) is False
+
+    def test_cycle_detection(self) -> None:
+        """Exception chain with a cycle should not infinite-loop."""
+        a = Exception("error a")
+        b = Exception("error b")
+        a.__cause__ = b
+        b.__cause__ = a  # cycle
+        assert _is_prompt_too_long(a) is False
+
+    def test_all_patterns(self) -> None:
+        patterns = [
+            "prompt is too long",
+            "request too large",
+            "maximum context length",
+            "context_length_exceeded",
+            "input tokens exceed",
+            "input is too long",
+            "content length exceeds",
+        ]
+        for pattern in patterns:
+            assert _is_prompt_too_long(Exception(pattern)) is True, pattern
+
+
+# ---------------------------------------------------------------------------
+# _reduce_context
+# ---------------------------------------------------------------------------
+
+
+class TestReduceContext:
+    @pytest.mark.asyncio
+    async def test_first_retry_compaction_success(self) -> None:
+        transcript = _build_transcript([("user", "hi"), ("assistant", "hello")])
+        compacted = _build_transcript([("user", "hi"), ("assistant", "[summary]")])
+
+        with (
+            patch(
+                "backend.copilot.sdk.service.compact_transcript",
+                new_callable=AsyncMock,
+                return_value=compacted,
+            ),
+            patch(
+                "backend.copilot.sdk.service.validate_transcript",
+                return_value=True,
+            ),
+            patch(
+                "backend.copilot.sdk.service.write_transcript_to_tempfile",
+                return_value="/tmp/resume.jsonl",
+            ),
+        ):
+            ctx = await _reduce_context(
+                transcript, False, "sess-123", "/tmp/cwd", "[test]"
+            )
+
+        assert isinstance(ctx, ReducedContext)
+        assert ctx.use_resume is True
+        assert ctx.resume_file == "/tmp/resume.jsonl"
+        assert ctx.transcript_lost is False
+        assert ctx.tried_compaction is True
+
+    @pytest.mark.asyncio
+    async def test_compaction_fails_drops_transcript(self) -> None:
+        transcript = _build_transcript([("user", "hi"), ("assistant", "hello")])
+
+        with patch(
+            "backend.copilot.sdk.service.compact_transcript",
+            new_callable=AsyncMock,
+            return_value=None,
+        ):
+            ctx = await _reduce_context(
+                transcript, False, "sess-123", "/tmp/cwd", "[test]"
+            )
+
+        assert ctx.use_resume is False
+        assert ctx.resume_file is None
+        assert ctx.transcript_lost is True
+        assert ctx.tried_compaction is True
+
+    @pytest.mark.asyncio
+    async def test_already_tried_compaction_skips(self) -> None:
+        transcript = _build_transcript([("user", "hi"), ("assistant", "hello")])
+
+        ctx = await _reduce_context(transcript, True, "sess-123", "/tmp/cwd", "[test]")
+
+        assert ctx.use_resume is False
+        assert ctx.transcript_lost is True
+        assert ctx.tried_compaction is True
+
+    @pytest.mark.asyncio
+    async def test_empty_transcript_drops(self) -> None:
+        ctx = await _reduce_context("", False, "sess-123", "/tmp/cwd", "[test]")
+
+        assert ctx.use_resume is False
+        assert ctx.transcript_lost is True
+
+    @pytest.mark.asyncio
+    async def test_compaction_returns_same_content_drops(self) -> None:
+        transcript = _build_transcript([("user", "hi"), ("assistant", "hello")])
+
+        with patch(
+            "backend.copilot.sdk.service.compact_transcript",
+            new_callable=AsyncMock,
+            return_value=transcript,  # same content
+        ):
+            ctx = await _reduce_context(
+                transcript, False, "sess-123", "/tmp/cwd", "[test]"
+            )
+
+        assert ctx.transcript_lost is True
+
+    @pytest.mark.asyncio
+    async def test_write_tempfile_fails_drops(self) -> None:
+        transcript = _build_transcript([("user", "hi"), ("assistant", "hello")])
+        compacted = _build_transcript([("user", "hi"), ("assistant", "[summary]")])
+
+        with (
+            patch(
+                "backend.copilot.sdk.service.compact_transcript",
+                new_callable=AsyncMock,
+                return_value=compacted,
+            ),
+            patch(
+                "backend.copilot.sdk.service.validate_transcript",
+                return_value=True,
+            ),
+            patch(
+                "backend.copilot.sdk.service.write_transcript_to_tempfile",
+                return_value=None,
+            ),
+        ):
+            ctx = await _reduce_context(
+                transcript, False, "sess-123", "/tmp/cwd", "[test]"
+            )
+
+        assert ctx.transcript_lost is True
+
+
+# ---------------------------------------------------------------------------
+# _iter_sdk_messages
+# ---------------------------------------------------------------------------
+
+
+class TestIterSdkMessages:
+    @pytest.mark.asyncio
+    async def test_yields_messages(self) -> None:
+        messages = ["msg1", "msg2", "msg3"]
+        client = AsyncMock()
+
+        async def _fake_receive() -> AsyncGenerator[str]:
+            for m in messages:
+                yield m
+
+        client.receive_response = _fake_receive
+        result = [msg async for msg in _iter_sdk_messages(client)]
+        assert result == messages
+
+    @pytest.mark.asyncio
+    async def test_heartbeat_on_timeout(self) -> None:
+        """Yields None when asyncio.wait times out."""
+        client = AsyncMock()
+        received: list = []
+
+        async def _slow_receive() -> AsyncGenerator[str]:
+            await asyncio.sleep(100)  # never completes
+            yield "never"  # pragma: no cover — unreachable, yield makes this an async generator
+
+        client.receive_response = _slow_receive
+
+        with patch("backend.copilot.sdk.service._HEARTBEAT_INTERVAL", 0.01):
+            count = 0
+            async for msg in _iter_sdk_messages(client):
+                received.append(msg)
+                count += 1
+                if count >= 3:
+                    break
+
+        assert all(m is None for m in received)
+
+    @pytest.mark.asyncio
+    async def test_exception_propagates(self) -> None:
+        client = AsyncMock()
+
+        async def _error_receive() -> AsyncGenerator[str]:
+            raise RuntimeError("SDK crash")
+            yield  # pragma: no cover — unreachable, yield makes this an async generator
+
+        client.receive_response = _error_receive
+
+        with pytest.raises(RuntimeError, match="SDK crash"):
+            async for _ in _iter_sdk_messages(client):
+                pass
+
+    @pytest.mark.asyncio
+    async def test_task_cleanup_on_break(self) -> None:
+        """Pending task is cancelled when generator is closed."""
+        client = AsyncMock()
+
+        async def _slow_receive() -> AsyncGenerator[str]:
+            yield "first"
+            await asyncio.sleep(100)
+            yield "second"
+
+        client.receive_response = _slow_receive
+
+        gen = _iter_sdk_messages(client)
+        first = await gen.__anext__()
+        assert first == "first"
+        await gen.aclose()  # should cancel pending task cleanly

autogpt_platform/backend/backend/copilot/sdk/tool_adapter.py

@@ -234,7 +234,9 @@ def create_tool_handler(base_tool: BaseTool):
         try:
             return await _execute_tool_sync(base_tool, user_id, session, args)
         except Exception as e:
-            logger.error(f"Error executing tool {base_tool.name}: {e}", exc_info=True)
+            logger.error(
+                "Error executing tool %s: %s", base_tool.name, e, exc_info=True
+            )
             return _mcp_error(f"Failed to execute {base_tool.name}: {e}")
 
     return tool_handler

autogpt_platform/backend/backend/copilot/sdk/transcript.py

@@ -10,6 +10,9 @@ Storage is handled via ``WorkspaceStorageBackend`` (GCS in prod, local
 filesystem for self-hosted) — no DB column needed.
 """
 
+from __future__ import annotations
+
+import asyncio
 import logging
 import os
 import re
@@ -17,8 +20,12 @@ import shutil
 import time
 from dataclasses import dataclass
 from pathlib import Path
+from uuid import uuid4
 
 from backend.util import json
+from backend.util.clients import get_openai_client
+from backend.util.prompt import CompressResult, compress_context
+from backend.util.workspace_storage import GCSWorkspaceStorage, get_workspace_storage
 
 logger = logging.getLogger(__name__)
 
@@ -99,7 +106,14 @@ def strip_progress_entries(content: str) -> str:
             continue
         parent = entry.get("parentUuid", "")
         original_parent = parent
-        while parent in stripped_uuids:
+        # seen_parents is local per-entry (not shared across iterations) so
+        # it can only detect cycles within a single ancestry walk, not across
+        # entries.  This is intentional: each entry's parent chain is
+        # independent, and reusing a global set would incorrectly short-circuit
+        # valid re-use of the same UUID as a parent in different subtrees.
+        seen_parents: set[str] = set()
+        while parent in stripped_uuids and parent not in seen_parents:
+            seen_parents.add(parent)
             parent = uuid_to_parent.get(parent, "")
         if parent != original_parent:
             entry["parentUuid"] = parent
@@ -327,7 +341,7 @@ def write_transcript_to_tempfile(
     # Validate cwd is under the expected sandbox prefix (CodeQL sanitizer).
     real_cwd = os.path.realpath(cwd)
     if not real_cwd.startswith(_SAFE_CWD_PREFIX):
-        logger.warning(f"[Transcript] cwd outside sandbox: {cwd}")
+        logger.warning("[Transcript] cwd outside sandbox: %s", cwd)
         return None
 
     try:
@@ -337,17 +351,17 @@ def write_transcript_to_tempfile(
             os.path.join(real_cwd, f"transcript-{safe_id}.jsonl")
         )
         if not jsonl_path.startswith(real_cwd):
-            logger.warning(f"[Transcript] Path escaped cwd: {jsonl_path}")
+            logger.warning("[Transcript] Path escaped cwd: %s", jsonl_path)
             return None
 
         with open(jsonl_path, "w") as f:
             f.write(transcript_content)
 
-        logger.info(f"[Transcript] Wrote resume file: {jsonl_path}")
+        logger.info("[Transcript] Wrote resume file: %s", jsonl_path)
         return jsonl_path
 
     except OSError as e:
-        logger.warning(f"[Transcript] Failed to write resume file: {e}")
+        logger.warning("[Transcript] Failed to write resume file: %s", e)
         return None
 
 
@@ -408,8 +422,6 @@ def _meta_storage_path_parts(user_id: str, session_id: str) -> tuple[str, str, s
 
 def _build_path_from_parts(parts: tuple[str, str, str], backend: object) -> str:
     """Build a full storage path from (workspace_id, file_id, filename) parts."""
-    from backend.util.workspace_storage import GCSWorkspaceStorage
-
     wid, fid, fname = parts
     if isinstance(backend, GCSWorkspaceStorage):
         blob = f"workspaces/{wid}/{fid}/{fname}"
@@ -448,17 +460,15 @@ async def upload_transcript(
         content: Complete JSONL transcript (from TranscriptBuilder).
         message_count: ``len(session.messages)`` at upload time.
     """
-    from backend.util.workspace_storage import get_workspace_storage
-
     # Strip metadata entries (progress, file-history-snapshot, etc.)
     # Note: SDK-built transcripts shouldn't have these, but strip for safety
     stripped = strip_progress_entries(content)
     if not validate_transcript(stripped):
         # Log entry types for debugging — helps identify why validation failed
-        entry_types: list[str] = []
-        for line in stripped.strip().split("\n"):
-            entry = json.loads(line, fallback={"type": "INVALID_JSON"})
-            entry_types.append(entry.get("type", "?"))
+        entry_types = [
+            json.loads(line, fallback={"type": "INVALID_JSON"}).get("type", "?")
+            for line in stripped.strip().split("\n")
+        ]
         logger.warning(
             "%s Skipping upload — stripped content not valid "
             "(types=%s, stripped_len=%d, raw_len=%d)",
@@ -494,11 +504,14 @@ async def upload_transcript(
             content=json.dumps(meta).encode("utf-8"),
         )
     except Exception as e:
-        logger.warning(f"{log_prefix} Failed to write metadata: {e}")
+        logger.warning("%s Failed to write metadata: %s", log_prefix, e)
 
     logger.info(
-        f"{log_prefix} Uploaded {len(encoded)}B "
-        f"(stripped from {len(content)}B, msg_count={message_count})"
+        "%s Uploaded %dB (stripped from %dB, msg_count=%d)",
+        log_prefix,
+        len(encoded),
+        len(content),
+        message_count,
     )
 
 
@@ -512,8 +525,6 @@ async def download_transcript(
     Returns a ``TranscriptDownload`` with the JSONL content and the
     ``message_count`` watermark from the upload, or ``None`` if not found.
     """
-    from backend.util.workspace_storage import get_workspace_storage
-
     storage = await get_workspace_storage()
     path = _build_storage_path(user_id, session_id, storage)
 
@@ -521,10 +532,10 @@ async def download_transcript(
         data = await storage.retrieve(path)
         content = data.decode("utf-8")
     except FileNotFoundError:
-        logger.debug(f"{log_prefix} No transcript in storage")
+        logger.debug("%s No transcript in storage", log_prefix)
         return None
     except Exception as e:
-        logger.warning(f"{log_prefix} Failed to download transcript: {e}")
+        logger.warning("%s Failed to download transcript: %s", log_prefix, e)
         return None
 
     # Try to load metadata (best-effort — old transcripts won't have it)
@@ -536,10 +547,14 @@ async def download_transcript(
         meta = json.loads(meta_data.decode("utf-8"), fallback={})
         message_count = meta.get("message_count", 0)
         uploaded_at = meta.get("uploaded_at", 0.0)
-    except (FileNotFoundError, Exception):
+    except FileNotFoundError:
         pass  # No metadata — treat as unknown (msg_count=0 → always fill gap)
+    except Exception as e:
+        logger.debug("%s Failed to load transcript metadata: %s", log_prefix, e)
 
-    logger.info(f"{log_prefix} Downloaded {len(content)}B (msg_count={message_count})")
+    logger.info(
+        "%s Downloaded %dB (msg_count=%d)", log_prefix, len(content), message_count
+    )
     return TranscriptDownload(
         content=content,
         message_count=message_count,
@@ -553,8 +568,6 @@ async def delete_transcript(user_id: str, session_id: str) -> None:
     Removes both the ``.jsonl`` transcript and the companion ``.meta.json``
     so stale ``message_count`` watermarks cannot corrupt gap-fill logic.
     """
-    from backend.util.workspace_storage import get_workspace_storage
-
     storage = await get_workspace_storage()
     path = _build_storage_path(user_id, session_id, storage)
 
@@ -571,3 +584,280 @@ async def delete_transcript(user_id: str, session_id: str) -> None:
         logger.info("[Transcript] Deleted metadata for session %s", session_id)
     except Exception as e:
         logger.warning("[Transcript] Failed to delete metadata: %s", e)
+
+
+# ---------------------------------------------------------------------------
+# Transcript compaction — LLM summarization for prompt-too-long recovery
+# ---------------------------------------------------------------------------
+
+# JSONL protocol values used in transcript serialization.
+STOP_REASON_END_TURN = "end_turn"
+COMPACT_MSG_ID_PREFIX = "msg_compact_"
+ENTRY_TYPE_MESSAGE = "message"
+
+
+def _flatten_assistant_content(blocks: list) -> str:
+    """Flatten assistant content blocks into a single plain-text string.
+
+    Structured ``tool_use`` blocks are converted to ``[tool_use: name]``
+    placeholders.  This is intentional: ``compress_context`` requires plain
+    text for token counting and LLM summarization.  The structural loss is
+    acceptable because compaction only runs when the original transcript was
+    already too large for the model — a summarized plain-text version is
+    better than no context at all.
+    """
+    parts: list[str] = []
+    for block in blocks:
+        if isinstance(block, dict):
+            btype = block.get("type", "")
+            if btype == "text":
+                parts.append(block.get("text", ""))
+            elif btype == "tool_use":
+                parts.append(f"[tool_use: {block.get('name', '?')}]")
+            else:
+                # Preserve non-text blocks (e.g. image) as placeholders.
+                # Use __prefix__ to distinguish from literal user text.
+                parts.append(f"[__{btype}__]")
+        elif isinstance(block, str):
+            parts.append(block)
+    return "\n".join(parts) if parts else ""
+
+
+def _flatten_tool_result_content(blocks: list) -> str:
+    """Flatten tool_result and other content blocks into plain text.
+
+    Handles nested tool_result structures, text blocks, and raw strings.
+    Uses ``json.dumps`` as fallback for dict blocks without a ``text`` key
+    or where ``text`` is ``None``.
+
+    Like ``_flatten_assistant_content``, structured blocks (images, nested
+    tool results) are reduced to text representations for compression.
+    """
+    str_parts: list[str] = []
+    for block in blocks:
+        if isinstance(block, dict) and block.get("type") == "tool_result":
+            inner = block.get("content") or ""
+            if isinstance(inner, list):
+                for sub in inner:
+                    if isinstance(sub, dict):
+                        sub_type = sub.get("type")
+                        if sub_type in ("image", "document"):
+                            # Avoid serializing base64 binary data into
+                            # the compaction input — use a placeholder.
+                            str_parts.append(f"[__{sub_type}__]")
+                        elif sub_type == "text" or sub.get("text") is not None:
+                            str_parts.append(str(sub.get("text", "")))
+                        else:
+                            str_parts.append(json.dumps(sub))
+                    else:
+                        str_parts.append(str(sub))
+            else:
+                str_parts.append(str(inner))
+        elif isinstance(block, dict) and block.get("type") == "text":
+            str_parts.append(str(block.get("text", "")))
+        elif isinstance(block, dict):
+            # Preserve non-text/non-tool_result blocks (e.g. image) as placeholders.
+            # Use __prefix__ to distinguish from literal user text.
+            btype = block.get("type", "unknown")
+            str_parts.append(f"[__{btype}__]")
+        elif isinstance(block, str):
+            str_parts.append(block)
+    return "\n".join(str_parts) if str_parts else ""
+
+
+def _transcript_to_messages(content: str) -> list[dict]:
+    """Convert JSONL transcript entries to plain message dicts for compression.
+
+    Parses each line of the JSONL *content*, skips strippable metadata entries
+    (progress, file-history-snapshot, etc.), and extracts the ``role`` and
+    flattened ``content`` from the ``message`` field of each remaining entry.
+
+    Structured content blocks (``tool_use``, ``tool_result``, images) are
+    flattened to plain text via ``_flatten_assistant_content`` and
+    ``_flatten_tool_result_content`` so that ``compress_context`` can
+    perform token counting and LLM summarization on uniform strings.
+
+    Returns:
+        A list of ``{"role": str, "content": str}`` dicts suitable for
+        ``compress_context``.
+    """
+    messages: list[dict] = []
+    for line in content.strip().split("\n"):
+        if not line.strip():
+            continue
+        entry = json.loads(line, fallback=None)
+        if not isinstance(entry, dict):
+            continue
+        if entry.get("type", "") in STRIPPABLE_TYPES and not entry.get(
+            "isCompactSummary"
+        ):
+            continue
+        msg = entry.get("message", {})
+        role = msg.get("role", "")
+        if not role:
+            continue
+        msg_dict: dict = {"role": role}
+        raw_content = msg.get("content")
+        if role == "assistant" and isinstance(raw_content, list):
+            msg_dict["content"] = _flatten_assistant_content(raw_content)
+        elif isinstance(raw_content, list):
+            msg_dict["content"] = _flatten_tool_result_content(raw_content)
+        else:
+            msg_dict["content"] = raw_content or ""
+        messages.append(msg_dict)
+    return messages
+
+
+def _messages_to_transcript(messages: list[dict]) -> str:
+    """Convert compressed message dicts back to JSONL transcript format.
+
+    Rebuilds a minimal JSONL transcript from the ``{"role", "content"}``
+    dicts returned by ``compress_context``.  Each message becomes one JSONL
+    line with a fresh ``uuid`` / ``parentUuid`` chain so the CLI's
+    ``--resume`` flag can reconstruct a valid conversation tree.
+
+    Assistant messages are wrapped in the full ``message`` envelope
+    (``id``, ``model``, ``stop_reason``, structured ``content`` blocks)
+    that the CLI expects.  User messages use the simpler ``{role, content}``
+    form.
+
+    Returns:
+        A newline-terminated JSONL string, or an empty string if *messages*
+        is empty.
+    """
+    lines: list[str] = []
+    last_uuid: str = ""  # root entry uses empty string, not null
+    for msg in messages:
+        role = msg.get("role", "user")
+        entry_type = "assistant" if role == "assistant" else "user"
+        uid = str(uuid4())
+        content = msg.get("content", "")
+        if role == "assistant":
+            message: dict = {
+                "role": "assistant",
+                "model": "",
+                "id": f"{COMPACT_MSG_ID_PREFIX}{uuid4().hex[:24]}",
+                "type": ENTRY_TYPE_MESSAGE,
+                "content": [{"type": "text", "text": content}] if content else [],
+                "stop_reason": STOP_REASON_END_TURN,
+                "stop_sequence": None,
+            }
+        else:
+            message = {"role": role, "content": content}
+        entry = {
+            "type": entry_type,
+            "uuid": uid,
+            "parentUuid": last_uuid,
+            "message": message,
+        }
+        lines.append(json.dumps(entry, separators=(",", ":")))
+        last_uuid = uid
+    return "\n".join(lines) + "\n" if lines else ""
+
+
+_COMPACTION_TIMEOUT_SECONDS = 60
+_TRUNCATION_TIMEOUT_SECONDS = 30
+
+
+async def _run_compression(
+    messages: list[dict],
+    model: str,
+    log_prefix: str,
+) -> CompressResult:
+    """Run LLM-based compression with truncation fallback.
+
+    Uses the shared OpenAI client from ``get_openai_client()``.
+    If no client is configured or the LLM call fails, falls back to
+    truncation-based compression which drops older messages without
+    summarization.
+
+    A 60-second timeout prevents a hung LLM call from blocking the
+    retry path indefinitely.  The truncation fallback also has a
+    30-second timeout to guard against slow tokenization on very large
+    transcripts.
+    """
+    client = get_openai_client()
+    if client is None:
+        logger.warning("%s No OpenAI client configured, using truncation", log_prefix)
+        return await asyncio.wait_for(
+            compress_context(messages=messages, model=model, client=None),
+            timeout=_TRUNCATION_TIMEOUT_SECONDS,
+        )
+    try:
+        return await asyncio.wait_for(
+            compress_context(messages=messages, model=model, client=client),
+            timeout=_COMPACTION_TIMEOUT_SECONDS,
+        )
+    except Exception as e:
+        logger.warning("%s LLM compaction failed, using truncation: %s", log_prefix, e)
+        return await asyncio.wait_for(
+            compress_context(messages=messages, model=model, client=None),
+            timeout=_TRUNCATION_TIMEOUT_SECONDS,
+        )
+
+
+async def compact_transcript(
+    content: str,
+    *,
+    model: str,
+    log_prefix: str = "[Transcript]",
+) -> str | None:
+    """Compact an oversized JSONL transcript using LLM summarization.
+
+    Converts transcript entries to plain messages, runs ``compress_context``
+    (the same compressor used for pre-query history), and rebuilds JSONL.
+
+    Structured content (``tool_use`` blocks, ``tool_result`` nesting, images)
+    is flattened to plain text for compression.  This matches the fidelity of
+    the Plan C (DB compression) fallback path, where
+    ``_format_conversation_context`` similarly renders tool calls as
+    ``You called tool: name(args)`` and results as ``Tool result: ...``.
+    Neither path preserves structured API content blocks — the compacted
+    context serves as text history for the LLM, which creates proper
+    structured tool calls going forward.
+
+    Images are per-turn attachments loaded from workspace storage by file ID
+    (via ``_prepare_file_attachments``), not part of the conversation history.
+    They are re-attached each turn and are unaffected by compaction.
+
+    Returns the compacted JSONL string, or ``None`` on failure.
+
+    See also:
+        ``_compress_messages`` in ``service.py`` — compresses ``ChatMessage``
+        lists for pre-query DB history.  Both share ``compress_context()``
+        but operate on different input formats (JSONL transcript entries
+        here vs. ChatMessage dicts there).
+    """
+    messages = _transcript_to_messages(content)
+    if len(messages) < 2:
+        logger.warning("%s Too few messages to compact (%d)", log_prefix, len(messages))
+        return None
+    try:
+        result = await _run_compression(messages, model, log_prefix)
+        if not result.was_compacted:
+            # Compressor says it's within budget, but the SDK rejected it.
+            # Return None so the caller falls through to DB fallback.
+            logger.warning(
+                "%s Compressor reports within budget but SDK rejected — "
+                "signalling failure",
+                log_prefix,
+            )
+            return None
+        logger.info(
+            "%s Compacted transcript: %d->%d tokens (%d summarized, %d dropped)",
+            log_prefix,
+            result.original_token_count,
+            result.token_count,
+            result.messages_summarized,
+            result.messages_dropped,
+        )
+        compacted = _messages_to_transcript(result.messages)
+        if not validate_transcript(compacted):
+            logger.warning("%s Compacted transcript failed validation", log_prefix)
+            return None
+        return compacted
+    except Exception as e:
+        logger.error(
+            "%s Transcript compaction failed: %s", log_prefix, e, exc_info=True
+        )
+        return None

autogpt_platform/backend/backend/copilot/sdk/transcript_builder.py

@@ -68,7 +68,7 @@ class TranscriptBuilder:
             type=entry_type,
             uuid=data.get("uuid") or str(uuid4()),
             parentUuid=data.get("parentUuid"),
-            isCompactSummary=data.get("isCompactSummary") or None,
+            isCompactSummary=data.get("isCompactSummary"),
             message=data.get("message", {}),
         )
 

autogpt_platform/backend/backend/copilot/sdk/transcript_test.py

@@ -1,7 +1,7 @@
 """Unit tests for JSONL transcript management utilities."""
 
 import os
-from unittest.mock import AsyncMock, patch
+from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
@@ -382,7 +382,7 @@ class TestDeleteTranscript:
         mock_storage.delete = AsyncMock()
 
         with patch(
-            "backend.util.workspace_storage.get_workspace_storage",
+            "backend.copilot.sdk.transcript.get_workspace_storage",
             new_callable=AsyncMock,
             return_value=mock_storage,
         ):
@@ -402,7 +402,7 @@ class TestDeleteTranscript:
         )
 
         with patch(
-            "backend.util.workspace_storage.get_workspace_storage",
+            "backend.copilot.sdk.transcript.get_workspace_storage",
             new_callable=AsyncMock,
             return_value=mock_storage,
         ):
@@ -420,7 +420,7 @@ class TestDeleteTranscript:
         )
 
         with patch(
-            "backend.util.workspace_storage.get_workspace_storage",
+            "backend.copilot.sdk.transcript.get_workspace_storage",
             new_callable=AsyncMock,
             return_value=mock_storage,
         ):
@@ -897,3 +897,134 @@ class TestCompactionFlowIntegration:
         output2 = builder2.to_jsonl()
         lines2 = [json.loads(line) for line in output2.strip().split("\n")]
         assert lines2[-1]["parentUuid"] == "a2"
+
+
+# ---------------------------------------------------------------------------
+# _run_compression (direct tests for the 3 code paths)
+# ---------------------------------------------------------------------------
+
+
+class TestRunCompression:
+    """Direct tests for ``_run_compression`` covering all 3 code paths.
+
+    Paths:
+    (a) No OpenAI client configured → truncation fallback immediately.
+    (b) LLM success → returns LLM-compressed result.
+    (c) LLM call raises → truncation fallback.
+    """
+
+    def _make_compress_result(self, was_compacted: bool, msgs=None):
+        """Build a minimal CompressResult-like object."""
+        from types import SimpleNamespace
+
+        return SimpleNamespace(
+            was_compacted=was_compacted,
+            messages=msgs or [{"role": "user", "content": "summary"}],
+            original_token_count=500,
+            token_count=100 if was_compacted else 500,
+            messages_summarized=2 if was_compacted else 0,
+            messages_dropped=0,
+        )
+
+    @pytest.mark.asyncio
+    async def test_no_client_uses_truncation(self):
+        """Path (a): ``get_openai_client()`` returns None → truncation only."""
+        from .transcript import _run_compression
+
+        truncation_result = self._make_compress_result(
+            True, [{"role": "user", "content": "truncated"}]
+        )
+
+        with (
+            patch(
+                "backend.copilot.sdk.transcript.get_openai_client",
+                return_value=None,
+            ),
+            patch(
+                "backend.copilot.sdk.transcript.compress_context",
+                new_callable=AsyncMock,
+                return_value=truncation_result,
+            ) as mock_compress,
+        ):
+            result = await _run_compression(
+                [{"role": "user", "content": "hello"}],
+                model="test-model",
+                log_prefix="[test]",
+            )
+
+        # compress_context called with client=None (truncation mode)
+        call_kwargs = mock_compress.call_args
+        assert (
+            call_kwargs.kwargs.get("client") is None
+            or (call_kwargs.args and call_kwargs.args[2] is None)
+            or mock_compress.call_args[1].get("client") is None
+        )
+        assert result is truncation_result
+
+    @pytest.mark.asyncio
+    async def test_llm_success_returns_llm_result(self):
+        """Path (b): ``get_openai_client()`` returns a client → LLM compresses."""
+        from .transcript import _run_compression
+
+        llm_result = self._make_compress_result(
+            True, [{"role": "user", "content": "LLM summary"}]
+        )
+        mock_client = MagicMock()
+
+        with (
+            patch(
+                "backend.copilot.sdk.transcript.get_openai_client",
+                return_value=mock_client,
+            ),
+            patch(
+                "backend.copilot.sdk.transcript.compress_context",
+                new_callable=AsyncMock,
+                return_value=llm_result,
+            ) as mock_compress,
+        ):
+            result = await _run_compression(
+                [{"role": "user", "content": "long conversation"}],
+                model="test-model",
+                log_prefix="[test]",
+            )
+
+        # compress_context called with the real client
+        assert mock_compress.called
+        assert result is llm_result
+
+    @pytest.mark.asyncio
+    async def test_llm_failure_falls_back_to_truncation(self):
+        """Path (c): LLM call raises → truncation fallback used instead."""
+        from .transcript import _run_compression
+
+        truncation_result = self._make_compress_result(
+            True, [{"role": "user", "content": "truncated fallback"}]
+        )
+        mock_client = MagicMock()
+        call_count = [0]
+
+        async def _compress_side_effect(**kwargs):
+            call_count[0] += 1
+            if kwargs.get("client") is not None:
+                raise RuntimeError("LLM timeout")
+            return truncation_result
+
+        with (
+            patch(
+                "backend.copilot.sdk.transcript.get_openai_client",
+                return_value=mock_client,
+            ),
+            patch(
+                "backend.copilot.sdk.transcript.compress_context",
+                side_effect=_compress_side_effect,
+            ),
+        ):
+            result = await _run_compression(
+                [{"role": "user", "content": "long conversation"}],
+                model="test-model",
+                log_prefix="[test]",
+            )
+
+        # compress_context called twice: once for LLM (raises), once for truncation
+        assert call_count[0] == 2
+        assert result is truncation_result

autogpt_platform/backend/backend/copilot/tools/e2b_sandbox.py

@@ -41,8 +41,7 @@ import contextlib
 import logging
 from typing import Any, Awaitable, Callable, Literal
 
-from e2b import AsyncSandbox
-from e2b.sandbox.sandbox_api import SandboxLifecycle
+from e2b import AsyncSandbox, SandboxLifecycle
 
 from backend.data.redis_client import get_redis_async
 

autogpt_platform/backend/backend/util/prompt.py

@@ -70,6 +70,10 @@ def _msg_tokens(msg: dict, enc) -> int:
                 # Count tool result tokens
                 tool_call_tokens += _tok_len(item.get("tool_use_id", ""), enc)
                 tool_call_tokens += _tok_len(item.get("content", ""), enc)
+            elif isinstance(item, dict) and item.get("type") == "text":
+                # Count text block tokens (standard: "text" key, fallback: "content")
+                text_val = item.get("text") or item.get("content", "")
+                tool_call_tokens += _tok_len(text_val, enc)
             elif isinstance(item, dict) and "content" in item:
                 # Other content types with content field
                 tool_call_tokens += _tok_len(item.get("content", ""), enc)
@@ -145,10 +149,16 @@ def _truncate_middle_tokens(text: str, enc, max_tok: int) -> str:
     if len(ids) <= max_tok:
         return text  # nothing to do
 
+    # Need at least 3 tokens (head + ellipsis + tail) for meaningful truncation
+    if max_tok < 1:
+        return ""
+    mid = enc.encode(" … ")
+    if max_tok < 3:
+        return enc.decode(ids[:max_tok])
+
     # Split the allowance between the two ends:
     head = max_tok // 2 - 1  # -1 for the ellipsis
     tail = max_tok - head - 1
-    mid = enc.encode(" … ")
     return enc.decode(ids[:head] + mid + ids[-tail:])
 
 
@@ -545,6 +555,14 @@ async def _summarize_messages_llm(
                     "- Actions taken and key decisions made\n"
                     "- Technical specifics (file names, tool outputs, function signatures)\n"
                     "- Errors encountered and resolutions applied\n\n"
+                    "IMPORTANT: Preserve all concrete references verbatim — these are small but "
+                    "critical for continuing the conversation:\n"
+                    "- File paths and directory paths (e.g. /src/app/page.tsx, ./output/result.csv)\n"
+                    "- Image/media file paths from tool outputs\n"
+                    "- URLs, API endpoints, and webhook addresses\n"
+                    "- Resource IDs, session IDs, and identifiers\n"
+                    "- Tool names that were called and their key parameters\n"
+                    "- Environment variables, config keys, and credentials names (not values)\n\n"
                     "Include ONLY the sections below that have relevant content "
                     "(skip sections with nothing to report):\n\n"
                     "## 1. Primary Request and Intent\n"
@@ -552,7 +570,8 @@ async def _summarize_messages_llm(
                     "## 2. Key Technical Concepts\n"
                     "Technologies, frameworks, tools, and patterns being used or discussed.\n\n"
                     "## 3. Files and Resources Involved\n"
-                    "Specific files examined or modified, with relevant snippets and identifiers.\n\n"
+                    "Specific files examined or modified, with relevant snippets and identifiers. "
+                    "Include exact file paths, image paths from tool outputs, and resource URLs.\n\n"
                     "## 4. Errors and Fixes\n"
                     "Problems encountered, error messages, and their resolutions.\n\n"
                     "## 5. All User Messages\n"
@@ -566,7 +585,7 @@ async def _summarize_messages_llm(
             },
             {"role": "user", "content": f"Summarize:\n\n{conversation_text}"},
         ],
-        max_tokens=1500,
+        max_tokens=2000,
         temperature=0.3,
     )
 
@@ -686,11 +705,15 @@ async def compress_context(
                     msgs = [summary_msg] + recent_msgs
 
                 logger.info(
-                    f"Context summarized: {original_count} -> {total_tokens()} tokens, "
-                    f"summarized {messages_summarized} messages"
+                    "Context summarized: %d -> %d tokens, summarized %d messages",
+                    original_count,
+                    total_tokens(),
+                    messages_summarized,
                 )
             except Exception as e:
-                logger.warning(f"Summarization failed, continuing with truncation: {e}")
+                logger.warning(
+                    "Summarization failed, continuing with truncation: %s", e
+                )
                 # Fall through to content truncation
 
     # ---- STEP 2: Normalize content ----------------------------------------

autogpt_platform/backend/backend/util/text.py

@@ -1,5 +1,4 @@
 import logging
-import re
 
 import bleach
 from bleach.css_sanitizer import CSSSanitizer
@@ -155,76 +154,3 @@ class TextFormatter:
         )
 
         return rendered_subject_template, rendered_base_template
-
-
-# ---------------------------------------------------------------------------
-# CamelCase splitting
-# ---------------------------------------------------------------------------
-
-# Map of split forms back to their canonical compound terms.
-# Mirrors the frontend exception list in frontend/src/lib/utils.ts.
-_CAMELCASE_EXCEPTIONS: dict[str, str] = {
-    "Auto GPT": "AutoGPT",
-    "Open AI": "OpenAI",
-    "You Tube": "YouTube",
-    "Git Hub": "GitHub",
-    "Linked In": "LinkedIn",
-}
-
-_CAMELCASE_EXCEPTION_RE = re.compile(
-    "|".join(re.escape(k) for k in _CAMELCASE_EXCEPTIONS),
-)
-
-
-def split_camelcase(text: str) -> str:
-    """Split CamelCase into separate words.
-
-    Uses a single-pass character-by-character algorithm to avoid any
-    regex backtracking concerns (guaranteed O(n) time).
-
-    After splitting, known compound terms are restored via an exception
-    list (e.g. ``"YouTube"`` stays ``"YouTube"`` instead of becoming
-    ``"You Tube"``).  The list mirrors the frontend mapping in
-    ``frontend/src/lib/utils.ts``.
-
-    Examples::
-
-        >>> split_camelcase("AITextGeneratorBlock")
-        'AI Text Generator Block'
-        >>> split_camelcase("OAuth2Block")
-        'OAuth2 Block'
-        >>> split_camelcase("YouTubeBlock")
-        'YouTube Block'
-    """
-    if len(text) <= 1:
-        return text
-
-    parts: list[str] = []
-    prev = 0
-    for i in range(1, len(text)):
-        # Insert split between lowercase/digit and uppercase: "camelCase" -> "camel|Case"
-        if (text[i - 1].islower() or text[i - 1].isdigit()) and text[i].isupper():
-            parts.append(text[prev:i])
-            prev = i
-        # Insert split between uppercase run (2+ chars) and uppercase+lowercase:
-        # "AIText" -> "AI|Text".  Requires at least 3 consecutive uppercase chars
-        # before the lowercase so that the left part keeps 2+ uppercase chars
-        # (mirrors the original regex r"([A-Z]{2,})([A-Z][a-z])").
-        elif (
-            i >= 2
-            and text[i - 2].isupper()
-            and text[i - 1].isupper()
-            and text[i].islower()
-            and (i - 1 - prev) >= 2  # left part must retain at least 2 upper chars
-        ):
-            parts.append(text[prev : i - 1])
-            prev = i - 1
-
-    parts.append(text[prev:])
-    result = " ".join(parts)
-
-    # Restore known compound terms that should not be split.
-    result = _CAMELCASE_EXCEPTION_RE.sub(
-        lambda m: _CAMELCASE_EXCEPTIONS[m.group()], result
-    )
-    return result