fix(copilot): improve summarization prompt to retain file paths and references

- Add explicit instructions to preserve file paths, image paths, URLs,
  resource IDs, tool names, and config keys during LLM summarization
- Bump max_tokens from 1500 to 2000 for more detailed summaries
- Document compaction fidelity equivalence between Plan B and Plan C
- Add docstrings explaining tool_use structure flattening trade-off
- Fix remaining f-string logging in transcript.py to %s-style

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

@@ -759,6 +759,19 @@ async def compact_transcript(
     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.
     """
     cfg = ChatConfig()

autogpt_platform/backend/backend/util/prompt.py

@@ -545,6 +545,14 @@ 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 +560,8 @@ 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 +575,7 @@ async def _summarize_messages_llm(
             },
             {"role": "user", "content": f"Summarize:\n\n{conversation_text}"},
         ],
-        max_tokens=1500,
+        max_tokens=2000,
         temperature=0.3,
     )