Ground supervisor judgments in sourced evidence and competing explanations

src/supervisor-session.ts

@@ -79,6 +79,10 @@ Keep authorized work moving. Resolve technical choices within the agreed scope y
 
 At each review, give a brief visible recap of how work is tracking against the goal: what the evidence shows and your judgment about the next step. Add perspective rather than repeating status. Distinguish observations from guesses. Keep routine recaps short, but do not suppress useful explanation or thinking. Do not edit files or execute the worker's work.
 
+Ground consequential judgments in verbatim evidence with a source path or link and enough surrounding context to check the interpretation. Keep the observation separate from your inference. A worker summary is a claim, not an independent observation; repeated summaries of one result are not independent evidence. Say what evidence would change your mind. Missing evidence stays unknown until you inspect where it should be.
+
+For a surprising result or stalled investigation, compare plausible explanations, including an implementation or evaluation bug and a confound. Choose a cheap check whose outcomes distinguish them, and state the predictions before requesting it. For ML results, inspect actual inputs and full outputs alongside metrics and relevant baselines or controls; a passing smoke test does not establish scientific validity. One failed implementation does not refute the idea. Ask the worker to improve checks in the real pipeline rather than build a separate diagnostic implementation. Use ml-debug and varglight for deeper investigation when available; routine reviews need only the decisive evidence and next action.
+
 Before approving a goal, inspect its exact plan block, repository state, cited evidence, and a saved nonempty verification-output file. Challenge success claims as carefully as blocker claims: check that the artifact demonstrates the discriminator rather than merely existing or repeating a claimed pass. A stopped view means Pi is idle, not that background jobs have finished. Inspect saved job status when work was delegated or launched in the background; withhold approval if its state is unknown. When the discriminator is positively satisfied and no work is active, call ApproveGoal with that repository-relative path. Then call SteerWorker and tell the worker to call CompleteGoal with the exact goal text. When every goal is completed or cancelled, give a short final assessment and stop issuing instructions. -- Pi/OpenAI`;
 }
 

test/supervisor-session.test.ts

@@ -132,6 +132,10 @@ describe("visible supervisor session", () => {
 			expect(systemPrompt).toContain("what event will resume progress and how it will be observed");
 			expect(systemPrompt).toContain("after checking what is already authorized");
 			expect(systemPrompt).toContain("Challenge success claims as carefully as blocker claims");
+			expect(systemPrompt).toContain("verbatim evidence with a source path or link");
+			expect(systemPrompt).toContain("not independent evidence");
+			expect(systemPrompt).toContain("outcomes distinguish them");
+			expect(systemPrompt).toContain("One failed implementation does not refute the idea");
 			expect(systemPrompt).toContain("do not invent work");
 			expect(systemPrompt).toContain("stop issuing instructions");
 		} finally { rmSync(cwd, { recursive: true, force: true }); }