diff --git a/backend/pipeline/stages.py b/backend/pipeline/stages.py
index 1532c9f..740c179 100644
--- a/backend/pipeline/stages.py
+++ b/backend/pipeline/stages.py
@@ -1049,19 +1049,47 @@ def stage5_synthesis(self, video_id: str, run_id: str | None = None) -> str:
             for _, cls_info in moment_group:
                 all_tags.update(cls_info.get("topic_tags", []))
 
-            # ── Chunked synthesis ────────────────────────────────────
+            # ── Chunked synthesis with truncation recovery ─────────
             if len(moment_group) <= chunk_size:
-                # Small group — single LLM call (original behavior)
-                result = _synthesize_chunk(
-                    moment_group, category, creator_name,
-                    system_prompt, llm, model_override, modality, hard_limit,
-                    video_id, run_id, f"category:{category}",
-                )
-                synthesized_pages = list(result.pages)
-                logger.info(
-                    "Stage 5: category '%s' — %d moments, %d page(s) from single call",
-                    category, len(moment_group), len(synthesized_pages),
-                )
+                # Small group — try single LLM call first
+                try:
+                    result = _synthesize_chunk(
+                        moment_group, category, creator_name,
+                        system_prompt, llm, model_override, modality, hard_limit,
+                        video_id, run_id, f"category:{category}",
+                    )
+                    synthesized_pages = list(result.pages)
+                    logger.info(
+                        "Stage 5: category '%s' — %d moments, %d page(s) from single call",
+                        category, len(moment_group), len(synthesized_pages),
+                    )
+                except LLMTruncationError:
+                    # Output too large for model context — split in half and retry
+                    logger.warning(
+                        "Stage 5: category '%s' truncated with %d moments. "
+                        "Splitting into smaller chunks and retrying.",
+                        category, len(moment_group),
+                    )
+                    half = max(1, len(moment_group) // 2)
+                    chunk_pages = []
+                    for sub_start in range(0, len(moment_group), half):
+                        sub_chunk = moment_group[sub_start:sub_start + half]
+                        sub_label = f"category:{category} recovery-chunk:{sub_start // half + 1}"
+                        sub_result = _synthesize_chunk(
+                            sub_chunk, category, creator_name,
+                            system_prompt, llm, model_override, modality, hard_limit,
+                            video_id, run_id, sub_label,
+                        )
+                        # Reindex moment_indices to global offsets
+                        for p in sub_result.pages:
+                            if p.moment_indices:
+                                p.moment_indices = [idx + sub_start for idx in p.moment_indices]
+                        chunk_pages.extend(sub_result.pages)
+                    synthesized_pages = chunk_pages
+                    logger.info(
+                        "Stage 5: category '%s' — %d page(s) from recovery split",
+                        category, len(synthesized_pages),
+                    )
             else:
                 # Large group — split into chunks, synthesize each, then merge
                 num_chunks = (len(moment_group) + chunk_size - 1) // chunk_size
@@ -1108,6 +1136,7 @@ def stage5_synthesis(self, video_id: str, run_id: str | None = None) -> str:
             prior_page_ids = _load_prior_pages(video_id)
 
             for page_data in synthesized_pages:
+                page_moment_indices = getattr(page_data, "moment_indices", None) or []
                 existing = None
 
                 # First: check by slug (most specific match)
@@ -1202,7 +1231,6 @@ def stage5_synthesis(self, video_id: str, run_id: str | None = None) -> str:
                 pages_created += 1
 
                 # Link moments to the technique page using moment_indices
-                page_moment_indices = getattr(page_data, "moment_indices", None) or []
 
                 if page_moment_indices:
                     # LLM specified which moments belong to this page