refactor(scripts): restructured edit-mode fallbacks to ignore strict mode

- Removed PI_STRICT_EDIT_MODE gating from edit-mode resolution so model fallbacks now always apply.
- Stopped injecting PI_STRICT_EDIT_MODE in edit-benchmark.py and rate-edit-tool.py execution environments.
- Removed PI_STRICT_EDIT_MODE from environment-variable documentation and strict-mode test coverage.

scripts/edit-benchmark.py

@@ -58,7 +58,7 @@ def build_spec(variant: str) -> BenchmarkSpec:
 		description=f"Benchmark edit tool in {variant} mode across models with simple edit tasks.",
 		workspace_prefix=f"{variant}-benchmark",
 		tools=("edit", "read"),
-		env={"PI_EDIT_VARIANT": variant, "PI_STRICT_EDIT_MODE": "1"},
+		env={"PI_EDIT_VARIANT": variant},
 		initial_prompt=prompt,
 		retry_instruction=retry,
 	)

scripts/rate-edit-tool.py

@@ -1632,7 +1632,6 @@ def run_model_sync(
             executable=omp_bin,
             model=model,
             cwd=workspace,
-            env={"PI_STRICT_EDIT_MODE": "1"},
             thinking="high",
             tools=TOOL_WHITELIST,
             no_skills=True,
@@ -1852,7 +1851,6 @@ def run_oracle_review_sync(
         executable=omp_bin,
         model=model,
         cwd=results_dir,
-        env={"PI_STRICT_EDIT_MODE": "1"},
         thinking="high",
         tools=(),
         no_skills=True,