📖About

ROOT CAUSE of rubber-stamp pipeline: initiatives are filed with zero success criteria, then dispatched, then the step reviewer has nothing to verify, so PO-S1 self-reports PASS and the step is marked done with no actual work. 7 rubber-stamped executions on 2026-07-01 across INI-1000034 + INI-1000154 — all had step-level criteria=[] and zero Forge/Argus/test runs. The INI-2113 independent-criteria check correctly returned None (nothing to verify) which defaults to pass. FIX: add a mandatory criteria gate in el_initiative_creator_01.create_initiative() before the INSERT. If success_criteria is missing or empty in the POST body, refuse to file with a clear error. Gate applies to ALL modes (planner + bypass) — no initiative enters the system without defined success criteria. The API already accepts success_criteria at creation time (CAROL-INI-417 sends them in the POST body to the plan-step endpoint); the Creator just needs to enforce it.

⚖️Decisions

• Elrond's bypass methodology checklist (a reminder, not a gate -- you've got this): 0. File it requested_mode='bypass' (planner-vs-bypass is a deliberate choice). bypass_start REFUSES a non-bypass initiative (CAROL-INI-1846), and the dispatcher only skips the bypass lane when the mode says bypass -- a 'planner' mistag lets Merlin's pipeline grab the placeholder step and block your finished work. 1. Filed as planned status -- let the bypass claim/activate it; never file active. 2. Open the bypass (bypass_start) with your droid id + the remediation answer (remediates_initiative_id=NNN, or remediates_nothing=True). 3. Work the blocks for your work-type: template -> design -> code -> test -> review. Do the real work; record decisions on the initiative as you make them. 4. Reality is recorded for you at close -- code (files changed), each decision, and the twin-review verdict become real activities tied to this initiative and show in the Activity Tracker like a planner run (CAROL-INI-1840). No dummy rows. 5. Keep the initiative status moving; it parks in 'reviewing' and is tagged uat-pending for you at close (CAROL-INI-1836), so the stuck-watchdog leaves it alone until UAT. 6. Close runs the gates (design/architecture compliance + caller-audit). If a gate flags something pre-existing or unrelated to your change, waive it with a clear written rationale -- audit, don't skip. 7. Bypass skips the planner's auto-orchestration, NOT the standards. Same template checklist, same review, same observability as a planner run. (elrond)
• [status-router] planned -> executing | event=bypass_executing | bypass transition (or-bx-01)
• [status-router] executing -> reviewing | event=bypass_reviewing | bypass transition (or-bx-01)
• Orion remediated: INI-999900446 bypass closed — CAROL-INI-696 close-marker: the Orion bypass INI-999900446 filed against this parent reached terminal state (closed). This row's literal prefix Orion remediated: is the canonical signal the cookbook-155 dispatcher gate looks for. (shared.bypass.bypass_end)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original goal 'mandatory success criteria gate at filing — refuse to create initiative without criteria' is an infinite regress applied to itself. Replacing it with a concrete, bounded deliverable (one gate function, one passing test) allows the initiative to complete and demonstrate the intended behavior, rather than looping forever on a self-contradictory goal. (elrond)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original goal 'mandatory success criteria gate at filing — refuse to create initiative without criteria' is an infinite regress applied to itself. Replacing it with a concrete, bounded deliverable (one gate function, one passing test) allows the initiative to complete and demonstrate the intended behavior, rather than looping forever on a self-contradictory goal. (elrond)
• Elrond re-scoped success criterion 14 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: Original criterion was abstract ('mandatory gate'). Bounded to a concrete, verifiable gate behavior that Forge can implement and the reviewer can test. (elrond)
• Elrond re-scoped success criterion 14 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: Original criterion was abstract ('mandatory gate'). Bounded to a concrete, verifiable gate behavior that Forge can implement and the reviewer can test. (elrond)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The current criterion 'refuse to create initiative without criteria' describes a system behavior, not an executing step deliverable. This initiative was dispatched as a normal executing initiative, which creates an infinite loop: the initiative must run to enforce its rule, but running it requires the rule to already exist. The fix redefines it as a pipeline-mechanism change, aligning with how gat (elrond)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The current criterion 'refuse to create initiative without criteria' describes a system behavior, not an executing step deliverable. This initiative was dispatched as a normal executing initiative, which creates an infinite loop: the initiative must run to enforce its rule, but running it requires the rule to already exist. The fix redefines it as a pipeline-mechanism change, aligning with how gat (elrond)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion 'refuse to create initiative without criteria' describes the GOAL but the actual execution relies on the dispatcher (ds-s1), which is a pipeline component — not a developer step. The criterion must target the correct pipeline gate, not a downstream step that can never fire if criteria are absent. (elrond)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion 'refuse to create initiative without criteria' describes the GOAL but the actual execution relies on the dispatcher (ds-s1), which is a pipeline component — not a developer step. The criterion must target the correct pipeline gate, not a downstream step that can never fire if criteria are absent. (elrond)
• Elrond re-scoped success criterion 999900440 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion 'refuse to create initiative without criteria' is unreachable because the creator itself (not dispatch) would need to enforce this. The corrected criterion bounds the goal to what the pipeline can actually achieve: enforce criteria existence before dispatch progresses. (elrond)
• Elrond re-scoped success criterion 999900440 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion 'refuse to create initiative without criteria' is unreachable because the creator itself (not dispatch) would need to enforce this. The corrected criterion bounds the goal to what the pipeline can actually achieve: enforce criteria existence before dispatch progresses. (elrond)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion demanded 'no execution may ever fail across any run' which is impossible given ~50% pipeline failure rate from dispatch breaker and orphan watchdog. The bounded version tests real gate behavior (API responds correctly to missing criteria) and can be verified in a single execution. (elrond)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion demanded 'no execution may ever fail across any run' which is impossible given ~50% pipeline failure rate from dispatch breaker and orphan watchdog. The bounded version tests real gate behavior (API responds correctly to missing criteria) and can be verified in a single execution. (elrond)
• Elrond re-scoped success criterion 30 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion over-scopes by requiring enforcement across all filing methods (direct DB, API) in a single initiative. This is unachievable in one step. Scoping to the primary path makes the criterion bounded and testable, consistent with P.01.01.00.00 incremental delivery. (elrond)
• Elrond re-scoped success criterion 30 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion over-scopes by requiring enforcement across all filing methods (direct DB, API) in a single initiative. This is unachievable in one step. Scoping to the primary path makes the criterion bounded and testable, consistent with P.01.01.00.00 incremental delivery. (elrond)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original had no success criteria (zero rows in initiative_success_criteria), making the initiative self-referentially impossible to verify. This replacement criterion defines a concrete, testable outcome — the API gate behavior — that can be verified by a step review. (elrond)
• Elrond re-scoped success criterion 1 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original had no success criteria (zero rows in initiative_success_criteria), making the initiative self-referentially impossible to verify. This replacement criterion defines a concrete, testable outcome — the API gate behavior — that can be verified by a step review. (elrond)
• Elrond re-scoped success criterion 999900440 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion was empty/missing — the initiative defined no measurable outcome. The revised criterion describes a concrete, buildable pipeline component (a filing gate) that can be implemented and verified. Without this change the initiative loops forever chasing a gate that doesn't exist. (elrond)
• Elrond re-scoped success criterion 999900440 (replace) on Albus's prescription — Policy P.01.02.04.16 (Elrond edits the initiative definition ONLY on Albus's prescription). Albus diagnosis: The original criterion was empty/missing — the initiative defined no measurable outcome. The revised criterion describes a concrete, buildable pipeline component (a filing gate) that can be implemented and verified. Without this change the initiative loops forever chasing a gate that doesn't exist. (elrond)
• Orion remediated: INI-999900487 bypass closed — CAROL-INI-696 close-marker: the Orion bypass INI-999900487 filed against this parent reached terminal state (closed). This row's literal prefix Orion remediated: is the canonical signal the cookbook-155 dispatcher gate looks for. (shared.bypass.bypass_end)
• [status-router] reviewing -> blocked | event=operator_put | PUT /api/initiatives (operator)
• Orion remediated: Albus RSI group diagnosis (via INI 999900490): [procedural, confidence high] The initiative is blocked because the operator manually put it to blocked after a reviewer reopened it for rework, indicating that the execution artifacts did not satisfy the success criteria. The prior diagnosis for a similar initiative (1000107) highlighted that criteria were meta-checks rather than substantive, and although the current criteria appear improved, the pipeline still lacks proper evidence capture automation, causing the operator to intervene when progress stalls. (orion)
• [status-router] blocked -> closed | event=operator_put | PUT /api/initiatives (operator)
• [rsi-group-cure] Cured by the group diagnosis on INI 999900490 (shared cause operator_put); retriggered as INI 999900923. Root cause: [procedural, confidence high] The initiative is blocked because the operator manually put it to blocked after a reviewer reopened it for rework, indicating that the execution artifacts did not satisfy the success criteria. The prior diagnosis for a similar initiative (1000107) highlighted that criteria were meta-checks rather than substantive, and although the current criteria appear improved, the (elrond.rsi_loop)

✅Success criteria

• el_initiative_creator_01.create_initiative() refuses to file any initiative (planner AND bypass modes) whose POST body lacks a non-empty success_criteria list, returning the INI2199_NO_CRITERIA error before any INSERT. (must_have)
• When success_criteria are supplied at filing time, the Creator persists them into initiative_success_criteria so the step reviewer always has at least one criterion to verify (no more criteria=[] rubber-stamp path). (must_have)