IB-WP-0019-T01: plan snapshot persistence

Every generate plan invocation now appends its compact summary to
output/budget/plans.yaml with a deterministic 12-char snapshot_id
hashed over the selection filters and the estimated call/token/cost
totals. Identical-fingerprint plans refresh the most recent entry's
recorded_at instead of stacking duplicates. Retention defaults to the
last 50 snapshots; older entries are pruned and counted on a top-level
pruned_count field.

The summary now echoes its input filters (chapter_filter, chunk_filter,
from_chapter, to_chapter) so reviewers can read the snapshot without
cross-referencing the CLI invocation.

New module src/infospace_bench/budget.py owns layer 1 (per-infospace
recording) of the IB-WP-0019 three-layer design; layer 2 still belongs
in llm-connect LLM-WP-0004 and layer 3 in state-hub.

99 tests pass.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/infospace_bench/generator.py

@@ -15,6 +15,7 @@ from .evaluation_io import read_entity_evaluations
 from .history import get_history, read_metrics_file, record_check_results
 from .lifecycle import create_infospace, load_infospace, register_artifact
 from .openrouter import OpenRouterAssistedGenerationAdapter
+from .budget import record_plan_snapshot
 from .source_intake import SourceChunk, normalize_source
 from .workflow import (
     AssistedGenerationAdapter,
@@ -113,6 +114,7 @@ def plan_generation(
     words_per_token: float = WORDS_PER_TOKEN_DEFAULT,
     entities_per_chunk: int = ENTITIES_PER_CHUNK_ESTIMATE,
     full: bool = False,
+    persist: bool = True,
 ) -> dict[str, Any]:
     root_path = Path(root)
     status = status_generation(root_path)
@@ -129,9 +131,15 @@ def plan_generation(
         words_per_token=words_per_token,
         entities_per_chunk=entities_per_chunk,
     )
+    summary["chapter_filter"] = list(chapter_filter) if chapter_filter else None
+    summary["chunk_filter"] = list(chunk_filter) if chunk_filter else None
+    summary["from_chapter"] = from_chapter
+    summary["to_chapter"] = to_chapter
     summary["root"] = str(root_path)
     summary["stale"] = status["stale"]
     summary["status"] = "planned"
+    if persist:
+        summary["snapshot_id"] = record_plan_snapshot(root_path, summary)
     if not full:
         return summary
     workflow_ids = _workflow_ids_for_stage(stage)