Rework Research Mode consent tiers and collected fields

docs/research-mode.md

@@ -8,24 +8,25 @@ Consent is **per repository**, not machine-wide — agreeing to share one projec
 
 > Help improve Tracybot: share this repository's Tasklet history for a study on AI-assisted coding behavior?
 
-Agreeing shows a Tier picker (Tier 1, the most conservative, is the default if dismissed) and generates a random, per-machine `participant_id` that is never derived from git identity (`user.name`/`user.email`) — the participant identity is shared across repos even though the enable/tier decision isn't. The decision (`enabled` + tier, or `declined`) is stored in that repo's `.git/tracybot/research-consent.json` — inside `.git` so it's never itself tracked or pushed by that repo's own history — and can be changed anytime from the Research Mode status bar item ("Disable for This Repo").
+Agreeing shows a Tier picker (Tier 1, the most conservative option, is the default if dismissed) and generates a random, per-machine `participant_id` that is never derived from git identity (`user.name`/`user.email`) — the participant identity is shared across repos even though the enable/tier decision isn't. The decision (`enabled` + tier, or `declined`) is stored in that repo's `.git/tracybot/research-consent.json` — inside `.git` so it's never itself tracked or pushed by that repo's own history — and can be changed anytime from the Research Mode status bar item ("Disable for This Repo").
 
 ### Consent tiers
 
 Tiers are additive — each includes everything in the tier below it.
 
 | Tier | Adds |
 |---|---|
-| **1** (default) | Model, timestamps, file extensions touched, line-change counts, ownership-flip/BLEU stats. No prompt text, no code. |
-| **2** | Plan/build prompt and response text (fenced code blocks in responses are redacted before leaving the machine). |
-| **3** | The diff hunks touched by each Tasklet (`added_lines`/`removed_lines`), plus the BLEU-significance result per hunk. Never a full file or repo snapshot. |
+| **1** (default) | Model, timestamps, file extensions touched, line-change counts, ownership-flip/BLEU stats, the taskletIds of prior Tasklets that previously owned any line this one currently owns (`history_tasklet_ids`), plus plan/build prompt and response text (fenced code blocks in responses are redacted before leaving the machine). |
+| **2** | The diff hunks touched by each Tasklet (`added_lines`/`removed_lines`), plus the BLEU-significance result per hunk. Never a full file or repo snapshot. |
 
 The developer's own (non-AI) code is never collected, regardless of tier.
 
 ## What gets collected
 
 One payload per Tasklet, built by `vscode-extension/src/research/buildResearchPayloads.ts` from `buildHistory()`'s output. See `vscode-extension/src/research/types.ts` for the exact field list per tier.
 
+`repo_url` is read live from the repo's `origin` remote (`vscode-extension/src/research/gitRemote.ts`) at submission time — it isn't something the participant sets, and isn't stored in the consent file. There's no separate consent gate for it: for an open-source repo the URL doesn't tell us anything not already public, and for a private one the URL alone doesn't grant access either way.
+
 ## Architecture
 
 ```
@@ -62,8 +63,7 @@ Stored per-repo in `.git/tracybot/research-consent.json` (see `vscode-extension/
 | Field | Purpose |
 |---|---|
 | `decision` | `"enabled"` or `"declined"` — absent entirely means undecided (prompt shows next time the repo is opened) |
-| `consentTier` | `1`, `2`, or `3` — see tiers above; only present when `decision` is `"enabled"` |
-| `repoUrl` | Optional, not currently set through any UI — lets researchers later check if a repo is open source, if manually added to the file |
+| `consentTier` | `1` or `2` — see tiers above; only present when `decision` is `"enabled"` |
 
 ## Local development
 

research-collector-worker/src/schema.test.ts

@@ -21,7 +21,13 @@ function makeTier1Payload(overrides: Record<string, unknown> = {}) {
     ownership_flip: false,
     bleu_score: null,
     review_latency_sec: null,
+    history_tasklet_ids: [],
     consent_level: 1,
+    plan_prompts: ["Plan this"],
+    plan_responses: ["Here's the plan"],
+    build_prompt: "Build it",
+    build_response: "Done",
+    questions_answers: [],
     ...overrides,
   };
 }
@@ -37,10 +43,16 @@ describe("submitRequestSchema", () => {
     assert.equal(result.success, false);
   });
 
-  test("rejects a Tier 2 payload missing the Tier 2-only fields", () => {
-    const result = submitRequestSchema.safeParse({
-      payloads: [makeTier1Payload({ consent_level: 2 })],
-    });
+  test("rejects a Tier 1 payload missing the Tier 1-only fields", () => {
+    const {
+      plan_prompts,
+      plan_responses,
+      build_prompt,
+      build_response,
+      questions_answers,
+      ...baseOnly
+    } = makeTier1Payload();
+    const result = submitRequestSchema.safeParse({ payloads: [baseOnly] });
     assert.equal(result.success, false);
   });
 

research-collector-worker/src/schema.ts

@@ -27,19 +27,19 @@ const basePayload = z.object({
   ownership_flip: z.boolean(),
   bleu_score: z.number().nullable(),
   review_latency_sec: z.number().nullable(),
-});
 
-const tier1Payload = basePayload.extend({ consent_level: z.literal(1) });
+  history_tasklet_ids: z.array(z.string()),
+});
 
-const tier2Fields = {
+const tier1Fields = {
   plan_prompts: z.array(z.string()),
   plan_responses: z.array(z.string()),
   build_prompt: z.string(),
   build_response: z.string(),
   questions_answers: z.array(z.object({ question: z.string(), answer: z.array(z.string()) })),
 };
 
-const tier2Payload = basePayload.extend({ consent_level: z.literal(2), ...tier2Fields });
+const tier1Payload = basePayload.extend({ consent_level: z.literal(1), ...tier1Fields });
 
 const diffHunk = z.object({
   file: z.string(),
@@ -51,17 +51,16 @@ const diffHunk = z.object({
   removed_lines: z.array(z.string()),
 });
 
-const tier3Payload = basePayload.extend({
-  consent_level: z.literal(3),
-  ...tier2Fields,
+const tier2Payload = basePayload.extend({
+  consent_level: z.literal(2),
+  ...tier1Fields,
   diff_hunks: z.array(diffHunk),
   hunk_significance: z.array(z.boolean()),
 });
 
 export const taskletResearchPayloadSchema = z.discriminatedUnion("consent_level", [
   tier1Payload,
   tier2Payload,
-  tier3Payload,
 ]);
 
 export type TaskletResearchPayload = z.infer<typeof taskletResearchPayloadSchema>;

vscode-extension/src/extension.ts

@@ -8,7 +8,7 @@ import { checkOpencode } from './pluginCheck';
 import { checkHookBasedAgents } from './hookAgentPluginCheck';
 import { checkTracyInit } from './tracyInitCheck';
 import { checkResearchModeConsent, enableResearchModeForRepo, pickResearchModeTier } from './research/researchModeCheck';
-import { getConsentTier, getParticipantContext, isResearchModeEnabled } from './research/consent';
+import { getConsentTier, getOrCreateParticipantId, getParticipantContext, isResearchModeEnabled } from './research/consent';
 import { readRepoConsent, writeRepoConsent } from './research/repoConsent';
 import { clearPendingPayloads, getPendingPayloads, getTodaysSentCount, queueTaskletForSubmission } from './research/queue';
 import { buildTaskletResearchPayloads } from './research/buildResearchPayloads';
@@ -142,7 +142,7 @@ async function updateResearchStatusBar(ctx: vscode.ExtensionContext): Promise<vo
 async function processNewTaskletsForResearch(ctx: vscode.ExtensionContext, h: History, repoPath: string): Promise<void> {
   if (!isResearchModeEnabled(repoPath)) { return; }
 
-  const participant = getParticipantContext(ctx, repoPath);
+  const participant = await getParticipantContext(ctx, repoPath);
   const payloads = buildTaskletResearchPayloads(h, getConsentTier(repoPath), participant);
 
   for (const payload of payloads) {
@@ -277,17 +277,25 @@ export async function activate(context: vscode.ExtensionContext) {
       const action = await vscode.window.showInformationMessage(
         `Tracybot Research Mode: sent ${count} tasklet${count === 1 ? '' : 's'} today. ` +
         `${pending.length} total pending.`,
-        'View Pending Data',
+        'View Pending',
+        'Copy ID',
         'Change Tier',
-        'Disable for This Repo'
+        'Disable'
       );
 
-      if (action === 'View Pending Data') {
+      if (action === 'View Pending') {
         const doc = await vscode.workspace.openTextDocument({
           content: JSON.stringify(pending, null, 2),
           language: 'json',
         });
         await vscode.window.showTextDocument(doc);
+      } else if (action === 'Copy ID') {
+        // Only reachable from this already-opted-in menu — nothing shows this
+        // to a participant who hasn't enabled Research Mode. Useful for e.g. a
+        // classroom study where students self-report this id through a
+        // separate, out-of-band roster rather than the tool ever identifying them.
+        await vscode.env.clipboard.writeText(getOrCreateParticipantId(context));
+        vscode.window.showInformationMessage('Participant ID copied to clipboard.');
       } else if (action === 'Change Tier') {
         const tier = await pickResearchModeTier();
         // Dismissed: leave the existing tier untouched — this is a change,
@@ -296,7 +304,7 @@ export async function activate(context: vscode.ExtensionContext) {
           writeRepoConsent(repoPath, { ...consent, consentTier: tier });
           vscode.window.showInformationMessage(`Research Mode tier changed to Tier ${tier} for this repository.`);
         }
-      } else if (action === 'Disable for This Repo') {
+      } else if (action === 'Disable') {
         writeRepoConsent(repoPath, { decision: 'declined' });
         vscode.window.showInformationMessage('Tracybot Research Mode disabled for this repository.');
         await updateResearchStatusBar(context);

vscode-extension/src/research/buildResearchPayloads.test.ts

@@ -2,7 +2,7 @@ import { test, describe } from "node:test";
 import assert from "node:assert/strict";
 import { History, TaskletMessage } from "../history/types";
 import { buildTaskletResearchPayloads } from "./buildResearchPayloads";
-import { ParticipantContext, Tier2Payload, Tier3Payload } from "./types";
+import { ParticipantContext, Tier1Payload, Tier2Payload } from "./types";
 
 const PARTICIPANT: ParticipantContext = {
   participantId: "p_test",
@@ -65,9 +65,9 @@ describe("buildTaskletResearchPayloads", () => {
     assert.equal(p.files_touched_count, 1);
     assert.equal(p.lines_changed_total, 2);
     assert.equal(p.ownership_flip, false);
+    assert.deepEqual(p.history_tasklet_ids, []);
 
-    // Tier 1 must not leak Tier 2/3 fields
-    assert.equal("plan_prompts" in p, false);
+    // Tier 1 must not leak Tier 2-only fields
     assert.equal("diff_hunks" in p, false);
   });
 
@@ -251,7 +251,7 @@ describe("buildTaskletResearchPayloads", () => {
     });
   });
 
-  describe("Tier 2 fields", () => {
+  describe("Tier 1 fields", () => {
     test("redacts fenced code blocks in plan/build responses", () => {
       const messages: TaskletMessage[] = [
         { stage: "plan", type: "prompt", model: "anthropic/claude-sonnet-4-6", message: "Plan this" },
@@ -266,7 +266,7 @@ describe("buildTaskletResearchPayloads", () => {
         },
       ];
       const history = makeHistory([{ path: "src/app.ts", tasklets: [makeTasklet({ messages })] }]);
-      const payloads = buildTaskletResearchPayloads(history, 2, PARTICIPANT, SUBMITTED_AT) as Tier2Payload[];
+      const payloads = buildTaskletResearchPayloads(history, 1, PARTICIPANT, SUBMITTED_AT) as Tier1Payload[];
 
       assert.equal(payloads[0].plan_responses[0], "Here's the plan.\n\n[code omitted]\n\nDone.");
       assert.equal(payloads[0].build_response, "Done.\n\n[code omitted]");
@@ -286,7 +286,7 @@ describe("buildTaskletResearchPayloads", () => {
         },
       ];
       const history = makeHistory([{ path: "src/app.ts", tasklets: [makeTasklet({ messages })] }]);
-      const payloads = buildTaskletResearchPayloads(history, 2, PARTICIPANT, SUBMITTED_AT) as Tier2Payload[];
+      const payloads = buildTaskletResearchPayloads(history, 1, PARTICIPANT, SUBMITTED_AT) as Tier1Payload[];
 
       assert.ok(!payloads[0].build_response.includes("esme"), "username should not leak");
       assert.ok(!payloads[0].build_response.includes("secret-client"), "local project name should not leak");
@@ -308,7 +308,7 @@ describe("buildTaskletResearchPayloads", () => {
         },
       ];
       const history = makeHistory([{ path: "src/app.ts", tasklets: [makeTasklet({ messages })] }]);
-      const payloads = buildTaskletResearchPayloads(history, 2, PARTICIPANT, SUBMITTED_AT) as Tier2Payload[];
+      const payloads = buildTaskletResearchPayloads(history, 1, PARTICIPANT, SUBMITTED_AT) as Tier1Payload[];
 
       assert.equal(
         payloads[0].build_response,
@@ -335,18 +335,18 @@ describe("buildTaskletResearchPayloads", () => {
           ],
         },
       ]);
-      const payloads = buildTaskletResearchPayloads(history, 2, PARTICIPANT, SUBMITTED_AT) as Tier2Payload[];
+      const payloads = buildTaskletResearchPayloads(history, 1, PARTICIPANT, SUBMITTED_AT) as Tier1Payload[];
       assert.deepEqual(payloads[0].questions_answers, [{ question: "Which log level?", answer: ["DEBUG"] }]);
     });
 
-    test("Tier 2 payload does not include Tier 3 diff_hunks", () => {
+    test("Tier 1 payload does not include Tier 2 diff_hunks", () => {
       const history = makeHistory([{ path: "src/app.ts", tasklets: [makeTasklet()] }]);
-      const payloads = buildTaskletResearchPayloads(history, 2, PARTICIPANT, SUBMITTED_AT);
+      const payloads = buildTaskletResearchPayloads(history, 1, PARTICIPANT, SUBMITTED_AT);
       assert.equal("diff_hunks" in payloads[0], false);
     });
   });
 
-  describe("Tier 3 fields", () => {
+  describe("Tier 2 fields", () => {
     test("flattens diff_hunks across files with correct file tagging and field mapping", () => {
       const history = makeHistory([
         {
@@ -378,7 +378,7 @@ describe("buildTaskletResearchPayloads", () => {
           ],
         },
       ]);
-      const payloads = buildTaskletResearchPayloads(history, 3, PARTICIPANT, SUBMITTED_AT) as Tier3Payload[];
+      const payloads = buildTaskletResearchPayloads(history, 2, PARTICIPANT, SUBMITTED_AT) as Tier2Payload[];
       const p = payloads[0];
 
       assert.equal(p.diff_hunks.length, 2);
@@ -414,20 +414,91 @@ describe("buildTaskletResearchPayloads", () => {
           ],
         },
       ]);
-      const payloads = buildTaskletResearchPayloads(history, 3, PARTICIPANT, SUBMITTED_AT) as Tier3Payload[];
+      const payloads = buildTaskletResearchPayloads(history, 2, PARTICIPANT, SUBMITTED_AT) as Tier2Payload[];
       assert.deepEqual(payloads[0].diff_hunks[0].added_lines, []);
       assert.deepEqual(payloads[0].diff_hunks[0].removed_lines, []);
       assert.equal(payloads[0].hunk_significance[0], false);
     });
 
-    test("Tier 3 still includes Tier 2 fields", () => {
+    test("Tier 2 still includes Tier 1 fields", () => {
       const history = makeHistory([{ path: "src/app.ts", tasklets: [makeTasklet()] }]);
-      const payloads = buildTaskletResearchPayloads(history, 3, PARTICIPANT, SUBMITTED_AT) as Tier3Payload[];
+      const payloads = buildTaskletResearchPayloads(history, 2, PARTICIPANT, SUBMITTED_AT) as Tier2Payload[];
       assert.ok(Array.isArray(payloads[0].plan_prompts));
       assert.ok(Array.isArray(payloads[0].questions_answers));
     });
   });
 
+  describe("history_tasklet_ids", () => {
+    test("lists the Tasklet that previously owned a now-taken-over line", () => {
+      const history = makeHistory([
+        {
+          path: "src/app.ts",
+          tasklets: [
+            // Originally wrote lines 1-3; line 2 was later taken over by tasklet-b.
+            makeTasklet({ taskletId: "tasklet-a", sessionId: "session-a", lines: [1, 3], ghostLines: [2] }),
+            // Now owns line 2.
+            makeTasklet({ taskletId: "tasklet-b", sessionId: "session-b", lines: [2], ghostLines: [] }),
+          ],
+        },
+      ]);
+      const payloads = buildTaskletResearchPayloads(history, 1, PARTICIPANT, SUBMITTED_AT);
+
+      const a = payloads.find(p => p.tasklet_id === "tasklet-a")!;
+      const b = payloads.find(p => p.tasklet_id === "tasklet-b")!;
+      // a's currently-live lines (1, 3) were never written by anyone else first.
+      assert.deepEqual(a.history_tasklet_ids, []);
+      // b's currently-live line (2) was previously written by a.
+      assert.deepEqual(b.history_tasklet_ids, ["tasklet-a"]);
+    });
+
+    test("dedupes repeated predecessors across multiple lines", () => {
+      const history = makeHistory([
+        {
+          path: "src/app.ts",
+          tasklets: [
+            makeTasklet({ taskletId: "tasklet-a", sessionId: "session-a", lines: [], ghostLines: [1, 2] }),
+            makeTasklet({ taskletId: "tasklet-b", sessionId: "session-b", lines: [1, 2], ghostLines: [] }),
+          ],
+        },
+      ]);
+      const payloads = buildTaskletResearchPayloads(history, 1, PARTICIPANT, SUBMITTED_AT);
+
+      const b = payloads.find(p => p.tasklet_id === "tasklet-b")!;
+      assert.deepEqual(b.history_tasklet_ids, ["tasklet-a"]);
+    });
+
+    test("aggregates history across every file the Tasklet touched", () => {
+      const history = makeHistory([
+        {
+          path: "src/app.ts",
+          tasklets: [
+            makeTasklet({ taskletId: "tasklet-a", sessionId: "session-a", lines: [], ghostLines: [1] }),
+            makeTasklet({ taskletId: "tasklet-c", sessionId: "session-c", lines: [1], ghostLines: [] }),
+          ],
+        },
+        {
+          path: "src/other.ts",
+          tasklets: [
+            makeTasklet({ taskletId: "tasklet-b", sessionId: "session-b", lines: [], ghostLines: [5] }),
+            { ...makeTasklet({ taskletId: "tasklet-c", sessionId: "session-c", lines: [5], ghostLines: [] }), id: "snapshot-hash-2" },
+          ],
+        },
+      ]);
+      const payloads = buildTaskletResearchPayloads(history, 1, PARTICIPANT, SUBMITTED_AT);
+
+      const c = payloads.find(p => p.tasklet_id === "tasklet-c")!;
+      assert.deepEqual([...c.history_tasklet_ids].sort(), ["tasklet-a", "tasklet-b"]);
+    });
+
+    test("does not include a Tasklet's own id even if it still ghost-owns a line elsewhere", () => {
+      const history = makeHistory([
+        { path: "src/app.ts", tasklets: [makeTasklet({ lines: [1], ghostLines: [2] })] },
+      ]);
+      const payloads = buildTaskletResearchPayloads(history, 1, PARTICIPANT, SUBMITTED_AT);
+      assert.deepEqual(payloads[0].history_tasklet_ids, []);
+    });
+  });
+
   test("model_provider/model_id split on the build-stage message's model field", () => {
     const messages: TaskletMessage[] = [
       { stage: "build", type: "prompt", model: "openai/gpt-5", message: "Build it" },