docs(ecosystem): clarify delegated verification rules

docs/ecosystem/ECOSYSTEM_AGENT_OPERATING_MODEL.md

@@ -271,9 +271,14 @@ When implementation lands:
 Do not mark work complete unless:
 
 - code is committed
-- verification evidence exists, or
+- the exact verification command was actually run and its result was reported, or
 - the remaining blocker is explicit and environmental rather than ambiguous
 
+Adding a script, config file, or test file is not enough by itself. A task is not complete until the agent either:
+
+- runs the required verification command successfully and reports it, or
+- reports the exact environmental blocker that prevented the command from running
+
 ---
 
 ## 10. Standard Task Template

docs/ecosystem/ECOSYSTEM_IMPLEMENTATION_TRACKER.md

@@ -118,9 +118,10 @@ Example:
   - `79c85ad`
   - `9ecc7c6`
   - `0f469a9`
+  - `49796b1`
     Status note:
   - artifact flow is implemented end-to-end and downstream event lineage is now hardened with persisted latest-event indexes
-  - MindLyst web Phase 1 memory-import path is verified with focused Vitest (`npm run test:phase1` in `mindlyst-native/web` after `npm install` with `GITEA_NPM_HOST` / token); see `49796b1` in `learning_multimodal_memory_agents`
+  - MindLyst web Phase 1 memory-import path is verified by Codex with focused Vitest using a workspace `vitest` binary; `49796b1` improved the local package path but did not fully close it by itself
   - final end-to-end walkthrough remains open while `learning_ai_notes` still has local dependency gaps in some clones
 - [ ] FlowMonk plan -> ChronoMind routine -> EffoRise habit
       Repos:
@@ -167,6 +168,7 @@ Execution status:
 - LysnrAI also persists the latest transcript event index for downstream causation (`79c85ad`)
 - NoteLett imports the latest transcript artifact into a note, emits `artifact.created` + `artifact.linked`, and now preserves upstream capture event lineage (`9ecc7c6`)
 - MindLyst imports the latest note artifact into a memory proposal, emits `memory.entry.created`, and now preserves upstream note-link lineage (`0f469a9`)
+- MindLyst focused tests were verified by Codex with `/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/node_modules/.bin/vitest run src/lib/ecosystem-phase1.test.ts src/__tests__/api-memory.test.ts`; `49796b1` improved the local script/setup path
 - end-to-end runtime walkthrough is still pending
-- repo-local verification for MindLyst web Phase 1 path is unblocked when private registry env vars are set (`49796b1`)
+- repo-local verification for MindLyst web Phase 1 path is functionally confirmed, but the package-local `npm run test:phase1` path is still not self-sufficient in this clone
 - repo-local verification in `learning_ai_notes` can still be blocked by incomplete local package/tooling setup in some clones

docs/ecosystem/PHASE1_TRANSCRIPT_NOTE_MEMORY_EXECUTION_PLAN.md

@@ -220,10 +220,12 @@ The exact commands may evolve by repo, but the evidence should include at least:
       event causation propagation and persisted latest memory event index; commit `49796b1`
       adds `mindlyst-native/web/.npmrc` (project-local registry), `test:phase1`, and
       fixes the test fixture setup so Vitest can run that path reliably.
-      Verified (2026-04-03):
-      `cd mindlyst-native/web && npm install && npm run test:phase1`
-      (requires `GITEA_NPM_HOST` and `GITEA_NPM_TOKEN` for `@bytelyst/*`)
+      Codex-verified (2026-04-03):
+      `/Users/saravana/BytelystAI/learning_ai/learning_ai_common_plat/node_modules/.bin/vitest run src/lib/ecosystem-phase1.test.ts src/__tests__/api-memory.test.ts`
       Result: 2 files passed, 10 tests passed (`ecosystem-phase1.test.ts`, `api-memory.test.ts`).
+      Remaining local-env gap:
+      `npm run test:phase1` is still not self-sufficient in this clone because
+      `mindlyst-native/web/node_modules/.bin/vitest` is missing.
 
 ### Cross-repo
 

docs/ecosystem/delegation/cursor/MINDLYST_PHASE1_VERIFICATION.md

@@ -49,6 +49,15 @@ If verification changes from blocked to verified, update:
 
 Return the result to Codex for review before claiming completion.
 
+## Completion Rule
+
+Do not report this task as complete only because a test script was added.
+
+Completion requires one of these:
+
+- the exact focused verification command was run successfully and the result was reported
+- the exact verification command failed and the environmental blocker was reported clearly
+
 ## Launch One-Liner
 
 ```bash