knowledge: agent self-correction with audit + per-persona gate + revert

Bundles three coupled changes so agent-side mutations stay
auditable and reversible:

1. Audit columns on entity_facts —
   `last_modified_by_model` / `last_modified_by_backend` /
   `last_modified_at`. Stamped on every mutation path
   (update_fact, supersede_fact, manual PATCH, manual supersede,
   the new revert). NULL on rows never touched since creation.
   Partial index on `last_modified_at WHERE NOT NULL` keeps the
   "show me recent edits" feed fast without bloating from legacy
   rows.

2. Per-persona gate `personas.allow_agent_corrections` (BOOLEAN,
   default 0). Defense in depth at two layers:
   - build_tool_definitions: when off, `update_fact` and
     `supersede_fact` aren't in the catalog at all, so even a
     hallucinated tool call by the model fails fast.
   - tool_update_fact / tool_supersede_fact: re-checks the persona
     flag at call time and returns an explicit "corrections
     disabled" error if it's somehow off (e.g. flag flipped mid-
     loop).
   ToolGateOpts grows the flag; current_gate_opts splits into
   `current_gate_opts` (no persona context, defaults closed) +
   `current_gate_opts_for_persona` for chat callers that have a
   persona id. Both call sites in insight_chat are updated.

3. Revert action — new DAO method `revert_supersession` +
   `POST /knowledge/facts/{id}/restore`. Flips status back to
   'active', clears `superseded_by`, clears `valid_until` (we
   don't track whether it was hand-set vs auto-stamped, so the
   safe reset is to drop it — user can re-bound after). Stamps
   `last_modified_*` so the revert itself is attributable.

Manual paths (PATCH / supersede via HTTP, plus restore) stamp the
audit columns with `("manual", "manual")`. Agent paths stamp the
loop-time chat model and backend (mirroring the existing
created_by_* convention).

FactDetail in the HTTP response now carries the audit triple
alongside the existing provenance. Apollo wires the new field set
in the matching commit.

PersonaView / UpdatePersonaRequest grow `allowAgentCorrections`;
the PersonaPatch + InsertPersona + bulk_import paths thread it.

317 lib tests pass, including unchanged update_fact / supersede
DAO tests (now passing audit=None — None means "no provenance
context to attribute", legacy semantics).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Cameron Cordes
2026-05-10 20:56:56 -04:00
parent 86c331571d
commit fd4dd89bbb
10 changed files with 515 additions and 7 deletions

View File

@@ -405,7 +405,10 @@ impl InsightChatService {
// and probes the per-table presence flags. Pass `offer_describe_tool`
// directly — the `!is_hybrid && local_first_user_has_image` decision
// is the chat-path's vision predicate.
let gate_opts = self.generator.current_gate_opts(offer_describe_tool);
let gate_opts = self.generator.current_gate_opts_for_persona(
offer_describe_tool,
Some((req.user_id, &active_persona)),
);
let tools = InsightGenerator::build_tool_definitions(gate_opts);
// Image base64 only needed when describe_photo is on the menu. Load
@@ -837,7 +840,10 @@ impl InsightChatService {
.map(|imgs| !imgs.is_empty())
.unwrap_or(false);
let offer_describe_tool = !is_hybrid && local_first_user_has_image;
let gate_opts = self.generator.current_gate_opts(offer_describe_tool);
let gate_opts = self.generator.current_gate_opts_for_persona(
offer_describe_tool,
Some((req.user_id, &active_persona)),
);
let tools = InsightGenerator::build_tool_definitions(gate_opts);
let image_base64: Option<String> = if offer_describe_tool {
@@ -1026,7 +1032,10 @@ impl InsightChatService {
// the chat model can re-look at the photo on demand. Hybrid:
// already inlined, no tool needed.
let offer_describe_tool = !is_hybrid && image_base64.is_some();
let gate_opts = self.generator.current_gate_opts(offer_describe_tool);
let gate_opts = self.generator.current_gate_opts_for_persona(
offer_describe_tool,
Some((req.user_id, &active_persona)),
);
let tools = InsightGenerator::build_tool_definitions(gate_opts);
// System message = persona + photo context block. Photo context