Refine caption display and final prompt experiments

prompt_experiments.py

@@ -44,6 +44,7 @@ def reconstruct_samples(path):
     samples = []
     rows = parse_distribute_debug_log(path)
     previous_llm = ""
+    previous_llm_history = []
     pending_bridges = []
     recent_raw_windows = []
 
@@ -60,6 +61,7 @@ def reconstruct_samples(path):
         samples.append(
             {
                 "previous_refined": previous_llm,
+                "previous_refined_history": list(previous_llm_history),
                 "previous_raw": prev_raw,
                 "new_raw": new_raw,
                 "observed_output": llm_output,
@@ -67,6 +69,7 @@ def reconstruct_samples(path):
         )
 
         previous_llm = llm_output
+        previous_llm_history.append(llm_output)
         recent_raw_windows.append(new_raw)
         pending_bridges = []
 
@@ -107,6 +110,7 @@ def maybe_augment_samples(samples, mode):
 
 def build_variants(sample, variant_filter=None):
     prev_refined = sample["previous_refined"]
+    prev_refined_history = sample.get("previous_refined_history", [])
     prev_raw = sample["previous_raw"]
     new_raw = sample["new_raw"]
 
@@ -354,6 +358,79 @@ Decision rules:
 """
     variants.append(("grounded_new_dominant_dedupe", system_f, user_f))
 
+    for window_size in [2, 4, 6, 8, 10]:
+        context_window = "\n\n".join(prev_refined_history[-window_size:]).strip()
+        system_ctx = """You are a careful live transcript editor working from noisy translated source text.
+
+Goal:
+Produce the most faithful readable English update.
+
+Decision rules:
+1. NEW SOURCE TEXT is the primary evidence and should dominate the output.
+2. Use PREVIOUS REFINED CONTEXT and PREVIOUS SOURCE TEXT only when they clearly help resolve or continue the new material.
+3. The final answer must be English only.
+4. Never copy non-English words into the output unless they are proper names.
+5. If a non-English fragment appears as an isolated clause, trailing fragment, or side comment without a clear English anchor, drop it.
+6. Only translate a non-English fragment when it is clearly central to the same idea and its meaning is reasonably obvious from context.
+7. If the new material starts a fresh thought, output only the new material.
+8. Remove exact or near-exact repetition unless the repetition is clearly intentional rhetoric.
+9. Do not add explanations, disclaimers, or meta commentary.
+10. Prefer conservative wording over guessed meaning.
+11. Return only the revised transcript text."""
+        user_ctx = f"""Edit this transcript update.
+
+[PREVIOUS REFINED CONTEXT WINDOW]
+{context_window}
+
+[PREVIOUS SOURCE TEXT]
+"{prev_raw}"
+
+[NEW SOURCE TEXT]
+"{new_raw}"
+        """
+        variants.append((f"grounded_ctx{window_size}", system_ctx, user_ctx))
+
+        if window_size in (2, 4):
+            user_ctx_no_prev_source = f"""Edit this transcript update.
+
+[PREVIOUS REFINED CONTEXT WINDOW]
+{context_window}
+
+[NEW SOURCE TEXT]
+"{new_raw}"
+"""
+            variants.append((f"grounded_ctx{window_size}_no_prev_source", system_ctx, user_ctx_no_prev_source))
+
+        system_ctx_repair = """You are a careful live transcript editor working from noisy translated source text.
+
+Goal:
+Produce the most faithful readable English update.
+
+Decision rules:
+1. NEW SOURCE TEXT is the primary evidence and should dominate the output.
+2. Use PREVIOUS REFINED CONTEXT and PREVIOUS SOURCE TEXT only when they clearly help resolve or continue the new material.
+3. The final answer must be English only.
+4. Never copy non-English words into the output unless they are proper names.
+5. If a non-English fragment appears as an isolated clause, trailing fragment, or side comment without a clear English anchor, drop it.
+6. Correct likely caption-word mistakes only when the surrounding context makes the intended English wording reasonably clear.
+7. If a word or phrase is unclear, keep it conservative instead of guessing.
+8. If the new material starts a fresh thought, output only the new material.
+9. Remove exact or near-exact repetition unless the repetition is clearly intentional rhetoric.
+10. Do not add explanations, disclaimers, or meta commentary.
+11. Return only the revised transcript text."""
+        user_ctx_repair = f"""Edit this transcript update.
+
+[PREVIOUS REFINED CONTEXT WINDOW]
+{context_window}
+
+[PREVIOUS SOURCE TEXT]
+"{prev_raw}"
+
+[NEW SOURCE TEXT]
+"{new_raw}"
+"""
+        variants.append((f"grounded_repair_ctx{window_size}", system_ctx_repair, user_ctx_repair))
+
     if variant_filter:
         allowed = set(x.strip() for x in variant_filter.split(",") if x.strip())
         variants = [variant for variant in variants if variant[0] in allowed]
@@ -468,6 +545,8 @@ def build_param_sets(args):
 def run_experiments(args):
     samples = reconstruct_samples(args.log_file)
     samples = maybe_augment_samples(samples, args.sample_mode)
+    if args.start_index:
+        samples = samples[args.start_index:]
     if args.limit:
         samples = samples[: args.limit]
 
@@ -554,6 +633,7 @@ def main():
     parser.add_argument("--timeout", type=float, default=40.0)
     parser.add_argument("--keep-alive", type=str, default="30m")
     parser.add_argument("--limit", type=int, default=0)
+    parser.add_argument("--start-index", type=int, default=0)
     parser.add_argument("--output-file", type=str, default="logs/prompt_experiment_results.json")
     parser.add_argument("--variant-filter", type=str, default="", help="Comma-separated subset of variants to run.")
     parser.add_argument("--temperature-grid", type=str, default="", help="Comma-separated temperatures to test.")