Repo Intelligence: agent-managed per-repo learnings with revision history (#487)

* add repo learnings feature with edit history

introduces a new "Learnings" section in the repo console where agents can
persist operational knowledge (setup steps, test commands, conventions) at
the end of runs via an MCP tool. users can also edit learnings manually.

- add `learnings` field to Repo model and `LearningsRevision` audit table
- add `update_learnings` MCP tool for agents to persist repo knowledge
- integrate learnings into prompt assembly as REPO LEARNINGS section
- add learnings step to mode guidance (Build, AddressReviews, Plan, Fix, Task)
- add PATCH /api/repo/[owner]/[repo]/learnings endpoint (JWT auth)
- add GET /api/repo/[owner]/[repo]/learnings/history endpoint (Clerk auth)
- add LearningsSection component with textarea, save-on-blur, and history modal
- record revision history with actor tracking (agent vs user) and pruning (50 max)
- gate UI behind owner === "pullfrog" for internal dogfooding

Made-with: Cursor

* fix prisma enum import path for LearningsActor

Made-with: Cursor

* simplify learnings schema: remove LearningsActor enum, store model name directly

the actor/actorName split was unnecessary — learnings are only written by
agents so the revision table just needs a model column. removes all user
editing concepts from schema, API, and frontend.

Made-with: Cursor

* fix migration: add separate migration instead of rewriting existing one

restores original learnings_revisions migration and adds a new migration
that drops actor/actorName columns, backfills model from actorName, and
drops the LearningsActor enum.

Made-with: Cursor

* polish learnings feature: rename to Repo Intelligence, fix atomicity, fix review skip

- rename user-facing "learnings" to "Repo Intelligence" (UI, prompt section, wiki, sidebar)
- simplify description to "Automatically discovered by the agent across runs."
- wrap repo.update + revision create in $transaction for atomicity
- refactor recordLearningsRevision to pruneLearningsRevisions (prune-only)
- fix empty review skip: don't block APPROVE reviews with no body
- fix broken docs anchor: #free-options → #free-models
- update agent guidance to require flat bullet list format with pruning
- add accessibility: aria-expanded, sr-only loading, output element
- add chevron rotation, stale data clear on modal close, max-h scroll
- trim + length-limit model field, remove type cast, restore pre-existing comment
- update wiki prompt examples with actual bullet-formatted content
- update model test snapshot

Made-with: Cursor

* fix stale free model name in docs, rename utility file to match export

- docs/keys.mdx: MiMo V2 Flash → MiMo V2 Pro (matches model code change)
- rename recordLearningsRevision.ts → pruneLearningsRevisions.ts

Made-with: Cursor

* Add skill, .neon

* polish learnings UI and remove verbose log

- learnings code block: read-only appearance with muted text, copy button, rounded corners
- history modal: full-width rows with cursor-pointer, chevron moved to right, no preview text
- drop noisy update_learnings log line

Made-with: Cursor

* inject learningsStep into all modes, drop seed script, soften revision styling

Made-with: Cursor

* Drop seed

---------

Co-authored-by: Colin McDonnell <colinmcd94@gmail.com>

mcp/selectMode.ts

@@ -19,6 +19,10 @@ function resolveMode(modes: Mode[], modeName: string): Mode | null {
   return modes.find((m) => m.name.toLowerCase() === modeName.toLowerCase()) ?? null;
 }
 
+function learningsStep(n: number): string {
+  return `${n}. **learnings** (only if high confidence): if you discovered something about repo setup, test commands, conventions, or patterns that you are confident is correct and would reliably help future runs, call \`${ghPullfrogMcpName}/update_learnings\` to persist it. skip this step if you are unsure or the finding is speculative/one-off. format as a flat bullet list (\`- \` per line, one fact per bullet). merge with existing learnings from the prompt — pass the FULL merged list. deduplicate, and drop bullets that are clearly wrong or no longer relevant to the current codebase.`;
+}
+
 const modeGuidance: Record<string, string> = {
   Build: `### Checklist
 
@@ -40,6 +44,8 @@ const modeGuidance: Record<string, string> = {
    - create a PR via \`${ghPullfrogMcpName}/create_pull_request\`
    - call \`${ghPullfrogMcpName}/report_progress\` with the final summary including PR link
 
+${learningsStep(5)}
+
 ### Notes
 
 For simple, well-defined tasks, skip the plan phase and go straight to build.`,
@@ -86,7 +92,9 @@ For simple, well-defined tasks, skip the plan phase and go straight to build.`,
    - push changes via \`${ghPullfrogMcpName}/push_branch\`
    - reply to each comment using \`${ghPullfrogMcpName}/reply_to_review_comment\`
    - resolve addressed threads via \`${ghPullfrogMcpName}/resolve_review_thread\`
-   - call \`${ghPullfrogMcpName}/report_progress\` with a brief summary`,
+   - call \`${ghPullfrogMcpName}/report_progress\` with a brief summary
+
+${learningsStep(6)}`,
 
   Review: `### Checklist
 
@@ -139,7 +147,9 @@ For simple, well-defined tasks, skip the plan phase and go straight to build.`,
 
 2. Produce a structured, actionable plan with clear milestones.
 
-3. Call \`${ghPullfrogMcpName}/report_progress\` with the plan.`,
+3. Call \`${ghPullfrogMcpName}/report_progress\` with the plan.
+
+${learningsStep(4)}`,
 
   PlanEdit: `### Checklist (editing existing plan)
 
@@ -170,7 +180,9 @@ An existing plan comment was found for this issue. Update that comment with the
 
 5. Finalize:
    - push changes via \`${ghPullfrogMcpName}/push_branch\`
-   - call \`${ghPullfrogMcpName}/report_progress\` with the diagnosis and fix summary`,
+   - call \`${ghPullfrogMcpName}/report_progress\` with the diagnosis and fix summary
+
+${learningsStep(6)}`,
 
   Task: `### Checklist
 
@@ -185,7 +197,9 @@ An existing plan comment was found for this issue. Update that comment with the
 3. Finalize:
    - call \`${ghPullfrogMcpName}/report_progress\` with results
    - if the task involved code changes, push via \`${ghPullfrogMcpName}/push_branch\` and create a PR via \`${ghPullfrogMcpName}/create_pull_request\`
-   - if the task involved labeling, commenting, or other GitHub operations, perform those directly`,
+   - if the task involved labeling, commenting, or other GitHub operations, perform those directly
+
+${learningsStep(4)}`,
 
   Summarize: `### Checklist