Add shared read-only Git and database research tools

docs/investigation-loop-v1.md

@@ -96,8 +96,9 @@ contract rather than granting a model extra allocations through this schema.
 All source, database, human feedback and prior model notes are untrusted data.
 Symbol occurrences and partial/empty queries retain their existing scope warnings.
 No conclusions about current live server behavior are inferred from old snapshots.
-The context includes current-revision evidence rather than silently dropping
-history. If the configured byte bound is exceeded, dispatch rejects explicitly;
+The durable context includes current-revision evidence. The opt-in project-research
+prompt uses a compact view documented in [project-research-v1.md](project-research-v1.md).
+If the configured byte bound is exceeded, dispatch rejects explicitly;
 operators must align context, gateway request and artifact limits.
 
 ## Budget and stopping
@@ -119,16 +120,16 @@ Logical defaults, frozen per analysis revision:
 | Config | Default | Meaning |
 | --- | --- | --- |
 | `max_iterations_per_hypothesis` | 50 | Maximum research-producing model iterations; one final assessment/closure is permitted |
-| `max_invalid_responses` | 3 | Consecutive rejected replies before abandoning that hypothesis's controller attempt |
+| `max_invalid_responses` | 3 | Consecutive rejected replies before blocking the case for technical correction |
 | `max_questions_per_hypothesis` | 30 | Bound on accumulated question records |
 | `test_deadline_seconds` | 21600 | Controller-owned external test deadline |
 | `max_steps_per_dispatch` | 8 | Fair scheduler yield boundary |
 
 An invalid reply changes only retry/audit bookkeeping. A following prompt includes
-its safe rejection code. Repeated invalid replies cause a recorded
-`invalid_responses` disposition, not a factual rejection. If a previous result
-cannot be assessed within that limit, it is deterministically closed with zero
-reward before ending that controller attempt. Existing credit is not refilled.
+its safe rejection code. Repeated invalid replies cause `BLOCKED` with
+`INVALID_LLM_RESPONSES`, requiring explicit operator resume after correction.
+The hypothesis stays active; pending results, reservations and remaining credit
+are preserved. No budget completion or zero-score settlement is fabricated.
 The same initial hypotheses cannot be regenerated to reset their limits.
 
 The iteration cap prevents free model-only research loops even when credit is