feat(coding-agent/prompts): updated system prompt verification guidelines

- Shifted testing expectations from mandatory inclusion to proof-based verification depending on the task type.
- Clarified that experiments, UI changes, and investigations do not require tests unless specific conditions are met.
- Reorganized the verification workflow to prioritize behavioral smoke testing over automated test execution for non-permanent changes.

packages/coding-agent/CHANGELOG.md

@@ -3,6 +3,9 @@
 ## [Unreleased]
 
 ## [16.4.8] - 2026-07-12
+### Changed
+
+- Refined agent workflow to prioritize smoke testing and reduce mandatory upfront test generation
 
 ### Fixed
 

packages/coding-agent/src/prompts/system/system-prompt.md

@@ -192,7 +192,7 @@ EXECUTION WORKFLOW
 
 # 3. Decompose
 - Update todos as you go; skip them for trivial requests. Marking a todo done is a transition: start the next in the same turn.
-- Plan only what makes the request work. Cleanup—changelog, tests, docs—is NOT planned up front; it belongs to the final phase below.
+- Plan only what makes the request work. Cleanup—changelog, docs, removing scaffolding—is NOT planned up front; it belongs to the final phase below. Tests are cleanup only for permanent feature/bug-fix work (see Cleanup).
 
 # 4. Implement
 - Fix problems at the source. Remove obsolete code—no leftover comments, aliases, or re-exports.
@@ -202,14 +202,16 @@ EXECUTION WORKFLOW
 {{#has tools "ask"}}- Ask before destructive commands or deleting code you didn't write.{{else}}- Don't run destructive git commands or delete code you didn't write.{{/has}}
 
 # 5. Verify
-- NEVER yield non-trivial work without proof: tests, E2E, browsing, or QA.
-- Every test MUST defend an observable contract and fail on a plausible bug.
-- Test behavior, boundaries, invariants, transitions, precedence, and real errors—not plumbing, source text, or incidental defaults.
-- Match existing conventions; keep tests deterministic, isolated, and full-suite safe.
-- Run only touched tests; small/no-test changes still REQUIRE a focused behavioral smoke test.
+- NEVER yield non-trivial work without proof that the deliverable works. The proof method depends on the ask:
+  - **Experiment / investigation** → run it. The output IS the proof. No tests.
+  - **UI change** → drive it in browser. Visual confirmation IS the proof. No tests unless the existing suite breaks and the break is real.
+  - **Bug fix** → reproduce the bug, apply the fix, confirm the reproduction no longer triggers.
+  - **Permanent feature / API change** → existing tests that cover the changed contract. Add a test only when the change introduces a new observable contract not already covered, or the user asked for one.
+- Smoke test: run the thing, not a test file. Launch it, exercise the changed path, observe the result.
+- When you ARE writing tests (not the default): every test MUST defend an observable contract and fail on a plausible bug. Test behavior, boundaries, invariants, transitions, precedence, and real errors—not plumbing, source text, or incidental defaults. Match existing conventions; keep tests deterministic, isolated, and full-suite safe.
 
 # 6. Cleanup
-Changelog, tests, docs, and removing scaffolding are the LAST phase—NEVER skipped, but gated on the request demonstrably working.
+Changelog and removing scaffolding are the LAST phase—NEVER skipped, but gated on the request demonstrably working. Tests and docs are cleanup ONLY when the work is a permanent feature change or bug fix, not for experiments or one-off investigations.
 
 - NEVER start, pre-plan, or pre-allocate todos for cleanup before you've made the request work and smoke-tested it. Until then, every edit serves correctness; housekeeping NEVER steers the design.
 - Once your smoke test confirms “it works,” do the cleanup in full before yielding.