qfai 2.1.1 → 2.2.0

package/assets/init/.qfai/assistant/rule/review-convergence.md

@@ -13,7 +13,10 @@ which owns the delegation rules these sit beside.
   answered, the work proceeds.
 - A finding the author cannot fix is reported in the stage's final report, with
   the finding and why it stays open.
-- A critical decision still goes to the user: one that contradicts a spec, a
+- A critical decision requires actual user authority under
+  `.agents/rules/grilling.md#explicit-delegation-for-a-discussion`.
+  Without an actual answer or recorded applicable authorization, it goes to
+  the user when questions are permitted: one that contradicts a spec, a
   contract or a recorded decision, one whose effect cannot be taken back, or one
   that rests on product intent nothing written states. So does a finding that
   names a concrete security defect, data loss or corruption, or a correctness
@@ -37,7 +40,8 @@ Close a repeat by citing its recorded answer. This bounds what a reviewer may
 require, not what a reviewer may report.
 
 A report of a new defect or evidence that an answer no longer applies must
-state what changed. A critical decision in it still goes to the user.
+state what changed. A critical decision in it still requires actual applicable
+user authority; uncovered authority is never supplied by the review.
 
 ## Discussion review precision
 
@@ -94,7 +98,10 @@ status is not permission to pass those.
 
 A grilling session between agents is a **delegated session**
 (`.agents/rules/grilling.md`): a griller interviews the authors, and the user is
-asked only a critical decision. These rules bound its rounds and say what
+asked only an uncovered critical decision when questions are permitted.
+Actual scoped user delegation may authorize reversible requested judgment
+without an individual option answer; record the agents' adoption and authority
+separately. These rules bound its rounds and say what
 settles each decision when they run out.
 
 **Two rounds.** After the second round **every
@@ -108,8 +115,9 @@ position is recorded beside it with whose it is. The stage reports every adopted
 decision at its end without waiting for an answer. A user who disagrees
 overturns one through a change request or a rerun.
 
-**A critical decision goes to the user at once**, without spending a round.
-Rounds between agents produce agreement, and agreement is not what these lack.
+**A critical decision without an actual answer or recorded applicable user
+authority goes to the user at once when asking is permitted**, without spending
+a round. Agent agreement and round exhaustion supply no authority.
 
 | Critical decision                                                                                                                             | Why it goes to the user                                                     |
 | --------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------- |
@@ -121,15 +129,20 @@ A discussion pack answers product intent for this test. It is non-normative for
 the Drift Protocol, but it is where the user already answered these questions in
 a user session, and asking them again spends that session twice.
 
-Each critical decision goes to the user with every position and a
-recommendation. Escalating is not failure: the work stays where it is and the
+Each uncovered critical decision goes to the user with every position and a
+recommendation when asking is permitted. The work stays where it is while the
 user accepts, decides, or drops the item.
 
 **The budget does not end the session while a critical decision is open.** The
-session ends `adopted` once the user has answered every critical decision.
+session ends `adopted` only with no open node or running lookup, all required
+consumed inputs present, and every critical decision supported by an actual
+user answer or recorded applicable authorization under the master's conditions.
 
-Under a no-question mode the escalation has nobody to reach. A critical decision
-is opened as a question in the register the stage reads, so the stage cannot
-complete over it (`.qfai/assistant/rule/constitution.md` Article X,
+Under a no-question mode no escalation is sent to the user. A critical decision
+without that authority is opened in the register the stage reads, so the stage
+cannot complete over it (`.qfai/assistant/rule/constitution.md` Article X,
 rule 6), and that write ends the session `no-question`. Non-critical decisions
-are adopted as they are in any delegated session.
+are adopted as they are in any delegated session. A qualifying explicitly
+delegated session with every node settled ends `adopted`; no-question mode
+alone does not qualify it. Unknown facts and missing undefaultable consumed
+inputs retain the ordinary open/stop behavior.

package/assets/init/.qfai/assistant/rule/shared-skill-delegation-baseline.md

@@ -1,12 +1,12 @@
 # Shared Skill Delegation Baseline
 
-Use this document to keep SKILL bodies compact. Skill files should reference this baseline and only add role-, stage-, or gate-specific rules.
+Skills cite this baseline and add only role, stage or gate overrides.
 
 ## Sub-agent Delegation (MANDATORY)
 
-This section binds every skill and every step as written. A skill or step
-restates none of it and writes no placeholder stanza for a subsection it does
-not change; it states only an override, under the subsection it overrides.
+This section binds every skill and step. A skill or step repeats none of it
+and adds no placeholder for a subsection it does not change. State only an
+override, under the subsection it overrides.
 
 Delegation is optional. The session agent, called the orchestrator below, may
 author any artifact itself. It uses a sub-agent only for work that runs in
@@ -34,14 +34,22 @@ classified by the taxonomy below before any response.
   `.qfai/assistant/skill/qfai-implement/references/parallelization-policy.md`.
   Where the stage's ledger or a seam makes an ordering mandatory, carrying on
   does not override it.
+- On Codex, read `.qfai/assistant/rule/references/codex-delegation.md` before delegating.
 - A review is done by an agent that did not author what it reviews. The
   orchestrator never reviews its own work and never approves it for
   convenience.
 - A read-only agent never runs `git checkout` or `git switch` in a worktree it
   shares; it reads other revisions with `git show <rev>:<path>`. Each agent
   writes scratch files only under a path of its own.
-- Commit the change, or give each reviewer a fixed commit, before a review
-  starts, and leave the working tree alone until every review returns.
+- Give each reviewer a fixed commit. Leave the checkout alone until reviews
+  return. Only read-only fixed-SHA `git show` reviews permit clean switches.
+  Writers, local gates and reviews using live files or checkout-dependent
+  execution must finish first.
+
+### Worker edit boundary
+
+Before assigning write paths or handling a refused edit, read
+`.qfai/assistant/rule/references/worker-edit-boundary.md`.
 
 ### Capability Probe (MUST)
 
@@ -212,25 +220,8 @@ A blocking review that cannot be delegated because the agent budget is spent is
 
 ## Work order template
 
-```text
-Task title: <short>
-Role: <sub-agent role>
-Review series: <reviewed artifact> + <reviewer role> + <replacement ordinal>   # review work orders only
-Goal: <what to decide/produce>
-Inputs (refs):
-- <file/section>
-- .qfai/assistant/rule/drift-protocol.md#core-rule  <!-- the protected set, in front of the agent -->
-Constraints:
-- must: enforce Drift Protocol
-- must: follow applicable test-layer or validation policy
-- must_not: patch upstream artifacts directly; every upstream change requires
-  STOP + Change Request + owner rerun per .qfai/assistant/rule/drift-protocol.md
-Output format:
-- <headings / bullet schema>
-Time budget: none | <seconds>   # advisory: nothing stops at it. See .qfai/assistant/rule/stage-cost.md
-Elapsed line: end every message with `elapsed <seconds>s / <budget>s`, or `elapsed <seconds>s` when the budget is none
-Acceptance bar: <accept when ...> | <rework when ...>   # never `PASS`/`REVISE`: that is the reviewer's vocabulary and the completion gate matches on it, so a doer told to report in it emits a verdict on its own work
-```
+When preparing a delegation, use the template in
+`.qfai/assistant/rule/references/worker-edit-boundary.md#work-order-template`.
 
 ## Reviewer response template
 

package/assets/init/.qfai/assistant/rule/shared-skill-operating-baseline.md

@@ -43,7 +43,7 @@ asks nothing and records explicit assumptions in its stage report.
   asked for nor a blocker. Neither exhaustion nor a user's `proceed` / `done` answer is `--auto`, so these questions survive both. Under an explicit `--auto` the question is not asked at all — that run stops and names the missing input instead of inventing one. See `.qfai/assistant/rule/constitution.md` Article VI.
 - **Grilling questions are exempt too, and unbounded.** A question asked inside the interview `.agents/rules/grilling.md` defines spends no budget, and a session runs to its own end condition — for a user session an empty frontier and the user's confirmation, which is itself in the exempt class, and for a delegated one no open node and an answer to every critical decision — rather than to a count.
   An exhausted budget does not close one, because its questions never opened it. A
-  session is entered deliberately: an invocation declares one and nothing else starts one, so a question asked outside a declared session is an ordinary clarification and spends a unit, whatever its subject.
+  session is entered deliberately, only as that rule's § Scope says, so a question asked outside a declared session is an ordinary clarification and spends a unit, whatever its subject.
   Under an explicit `--auto` the session asks nothing, a delegated one still adopts every decision that is not critical, and each node it could not settle is opened as a question in the register the stage reads. Each node, not each decision: a fact only
   the user holds cannot be settled from evidence either, and a fact declared undefaultable stops the run rather than taking a value nobody has. Where a document requires the field to hold something, write the defaulted value and label it an assumption beside that open question; what is forbidden is the assumption with no open question against it (Article X, rule 6).
 
@@ -168,8 +168,8 @@ The `common-gate-run` step runs a gate from this section and records it.
 
 ## Policy check (mandatory)
 
-A run starts with the policy check, once, and does not continue affected work
-on stale policy. The contract is
+A run, an exempt route aside, starts with the policy check once and does not
+continue affected work on stale policy. The contract is
 `.qfai/assistant/rule/workflow.md#policy-check-mandatory`.
 The procedure — which files, what counts as incomplete, how a fact is filled
 and where an unverifiable one goes — is the `common-policy-check` step. A
@@ -196,9 +196,9 @@ the policy check. The mode is `workflow.mode` in `qfai.config.yaml`. An absent k
   needs the operator's answer.
 - A QFAI work order binds the stage to its target: one business flow, or one
   new-story slot. The stage works on that target and no other.
-- The stage result names the agent instance that did the work in
-  `actor: { agentInstance }`. The run records that instance as the work's
-  author and never counts it as the work's independent reviewer.
+- The session report names the agent instance that authored the work and
+  each independent reviewer. The author never counts as the work's
+  independent reviewer.
 - These statements add to the constitution. They except no article.
 
 ## Running Steps (Mandatory)
@@ -255,6 +255,11 @@ stage, and no other.
 4. A finding another owner must repair is reported with that owner, not an
    edit made here.
 
+At each existing stage boundary, read
+`.qfai/assistant/skill/qfai-run/references/reached-step-observations.md`
+for the reached-step comparison in the existing stage report. Preserve the
+plan's scope, termination, pass-through and planned review.
+
 ### A pass-through step
 
 A step the plan marks `passThrough` always runs. It first reads what its
@@ -268,12 +273,12 @@ writes nothing and states why; the stage's review reads that statement.
 
 ## Default Autopilot Policy inside a run
 
-Inside a run, each bucket of a skill's Default Autopilot Policy is
-satisfied by one kind of authorization the run records:
+Inside a run, record the authorization for each bucket in the session report:
 
-- An `ask-user` item is satisfied only by a `human_decision` that answers it.
-- A `hard-required` input is satisfied by `request_scope` or by the run's
-  binding.
+- An `ask-user` item is satisfied only by the operator's answer to it.
+  Name that answer and its source; an agent's choice is not an operator answer.
+- A `hard-required` input is satisfied by the operator's request or by the
+  run's binding. Name the request or work order that supplies it.
 - An `auto-decide` item needs no authorization.
 - `--auto` satisfies nothing. It answers no `ask-user` item and supplies no
   `hard-required` input.

package/assets/init/.qfai/assistant/rule/ui-definition-protocol.md

@@ -27,6 +27,8 @@ A downstream skill reads the UI definition in this order.
    - primary tasks
    - states
    - actions
+   - supplements (the text shown beyond title, group headings and labels, each with
+     its reason) and, when written, structure (the groups and headings, in order)
 
 3. **Brand SSOT**
    - root `DESIGN.md` (front-matter + `# Brand Philosophy` body), the only
@@ -36,6 +38,10 @@ A downstream skill reads the UI definition in this order.
    prototyping loop ran): the final prototype, procurement and implementation
    notes
 
+The supplements and structure are required input: implementation adds no text the
+contract does not declare, and surface review compares the rendered text with them.
+A screen that lacks them is returned to `/qfai-sdd`.
+
 The paths that render a user-visible surface are declared by `uiux.surfacePaths`
 in `qfai.config.yaml`, and nowhere else.
 
@@ -51,6 +57,5 @@ in `qfai.config.yaml`, and nowhere else.
 ## Forbidden Fallbacks
 
 - Do not infer downstream UI behavior from discussion-pack sidecars.
-- Do not use retired design contract files.
 - Do not use HTML mock sections as downstream source of truth.
 - Do not treat a competitor reference as a selected design direction.

package/assets/init/.qfai/assistant/rule/workflow.md

@@ -132,7 +132,8 @@ from the skills and baselines that cite it.
 ### Policy check (mandatory)
 
 Once per run, at the start, before the first stage. A stage invoked by name on
-its own is a run of its own.
+its own is a run of its own. The ultra-light routes `answer-in-session` and
+`run-operation`, each one step that changes no tracked file, run without it.
 
 1. Check the current story-tree policy files under `<paths.specsDir>`:
    - `01_policy/objective.md` and `01_policy/initiative.md`

package/assets/init/.qfai/assistant/skill/qfai-configure/SKILL.md

@@ -293,7 +293,7 @@ Fill policy templates with repo evidence.
 - Keep existing content when already accurate.
 - When evidence is missing, write `TBD` and record what is missing.
 - Do not invent facts.
-- Fill `03_contract/tech.md` in its template's shape: a Stack row for the runtime, the platform and each tool detected, each runtime dependency with its reason, and the quality-gate commands under Standard commands, one labelled item each. It holds no rule and no constraint; a constraint goes to `01_policy/constraint.md`.
+- Fill `03_contract/tech.md` in its template's shape: a Stack row for the runtime, the platform and each tool detected, with one row per test layer whose Choice names the tool, the files it was observed in, and why it fits; each runtime dependency with its reason, and the quality-gate commands under Standard commands, one labelled item each. It holds no rule and no constraint; a constraint goes to `01_policy/constraint.md`.
 - Fill `## Architecture` of `03_contract/tech.md` from the codebase: one row per layer the module layout shows, what it is responsible for, and the layers its imports reach, or `-`. Name layers, never paths. Implementation places new code by this table and reviewers judge a change against it, so write the import directions the code has.
   - A layer is a group of modules whose imports point one way: an upper layer uses the layers below it, and a lower layer never imports an upper one.
   - Draw the layers first, as one `mermaid` `flowchart TD` with a node per layer and an `Upper --> Lower` edge per import direction. Then write the table rows from the uppermost layer down, so each Depends on names only rows below it. `npx qfai validate` reports a diagram and a table that disagree.
@@ -304,10 +304,10 @@ Edit:
 
 - `validation.traceability.testFileGlobs`
 - `validation.traceability.testFileExcludeGlobs` (only if needed)
-- `routing` or `reviewProfiles` only when the project needs an override; each matching entry replaces the shipped default as a whole
+- `routing` or `reviewProfiles` only when the user asks to change one; each matching entry replaces the shipped default as a whole
 - `uiux.surfacePaths`: the repository-relative globs of the paths observed to render a user-visible surface, or `[]` when the repository renders none. Keep an existing value unless the user asks to change it. An absent key leaves the UI impact decision unevaluable.
 
-Keep all other config keys unchanged.
+Keep all other config keys unchanged. Add no key the package already defaults, `paths.specsDir` included; a value the project set stays.
 
 ## Step 5 - Evidence sampling
 

package/assets/init/.qfai/assistant/skill/qfai-discussion/SKILL.md

@@ -120,6 +120,12 @@ End the turn with a question listing the next actions, `/qfai-sdd` recommended,
 
 ## Default Autopilot Policy
 
+The entries below govern the default user interview. Only an actual user
+delegation recorded under
+`.agents/rules/grilling.md#explicit-delegation-for-a-discussion` enables the
+delegated `adopted` path. No-question mode alone does not enable it; missing
+inputs and uncovered human decisions retain their ordinary blocking behavior.
+
 - ask-user:
   - every decision the interview puts on the frontier, over every topic in `references/discussion-coverage-checklist.md`. Running the interview is what this skill performs, so these are its own operations
   - the confirmation that closes the session

package/assets/init/.qfai/assistant/skill/qfai-discussion/references/discussion-completion-matrix.md

@@ -22,13 +22,14 @@ Blocking for every pack, UI-bearing or not:
    resolves to a `sources[].id`, and at least one `reflection[]` entry records an apply decision.
    `npx qfai validate --profile discussion --fail-on error` reports `QFAI-RESEARCH-*` until it is.
 2. The stage report's `## Grilling Session` row shows the session ended before authoring began,
-   with `Ended` reading one of the three endings that authorize it:
+   with `Ended` reading an authoring ending and its conditions met:
 
-   | Ended         | Also required                                                                                                  |
-   | ------------- | -------------------------------------------------------------------------------------------------------------- |
-   | `confirmed`   | No node open — the frontier empty **and** no fact lookup still running                                         |
-   | `user-closed` | Lookups finished, and every decision still open recorded as a labelled assumption                              |
-   | `no-question` | Every node still open registered — a decision, and a fact only the user holds — so item 3 below is what blocks |
+   | Ended         | Also required                                                                                                                                                                                        |
+   | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+   | `confirmed`   | No node open — the frontier empty **and** no fact lookup still running                                                                                                                               |
+   | `user-closed` | Lookups finished, and every decision still open recorded as a labelled assumption                                                                                                                    |
+   | `adopted`     | Recorded explicit delegation, actual author rounds, no open node or lookup, all required inputs and applicable human authority; see `.agents/rules/grilling.md#explicit-delegation-for-a-discussion` |
+   | `no-question` | Every node still open registered — a decision, and a fact only the user holds — so item 3 below is what blocks                                                                                       |
 
    `stopped` never completes: the user ended the run, and a pack authored after that is the run
    doing what they told it not to.
@@ -44,6 +45,10 @@ Blocking for every pack, UI-bearing or not:
    covered, every open question registered. What is missing is that someone agreed to what is in
    them, and nothing downstream can tell.
 
+   Delegation is not a human confirmation or a completion receipt. The
+   ordinary research, pack, OQ, UI, schema, validation and independent-review
+   gates remain blocking. No reserved decision or missing fact is forced closed.
+
    The no-question row is the one to read carefully: `--auto` can reach nobody, so waiting for a
    confirmation would stop the run before it could write the open questions that are what block it.
    Item 3 below does that work instead — an open count above zero closes nothing.
@@ -53,7 +58,7 @@ Blocking for every pack, UI-bearing or not:
    Here rather than under one pack shape. It is what a no-question run is blocked by, and a run is
    `--auto` or not independently of whether it has a surface — listed only under `## UI-bearing
 Packs`, it let a non-UI `--auto` pack complete with its decisions still open.
-   Item 7 below does that work instead — an open count above zero closes nothing.
+   All Packs item 3 does that work — an open count above zero closes nothing.
 
 ## UI-bearing Packs
 
@@ -73,13 +78,14 @@ Completion is blocked until all are true:
 5. `01_Context.md#Design Direction` names an adopted theme, what departs from it, and what stays
    ordinary. This is the one visual decision made here, because no later stage asks the user for
    it: `/qfai-sdd`'s `common-design-md` step authors tokens from whatever is recorded. A direction taken without the
-   user carries `chosen_by: assumption` and an open entry in `11_OQ-Register.md`.
-6. No forbidden legacy sidecar exists under `uiux/` (see
-   `templates/uiux/00_index.md#Forbidden Legacy Files`).
+   user carries `chosen_by: assumption`, never `user`. Its OQ stays open unless
+   an actual specifically applicable user instruction overrides the human-choice
+   requirement under the master's conditions; record that authority and the agents'
+   choice without falsifying the schema. General delegation alone does not waive
+   a genuinely reserved human input.
 
 Evaluation axes are global constants (4-step ordinal: weak / acceptable / strong /
-exceptional) and are NOT authored as discussion sidecars, so no scoring, override, strategy,
-taste-interview, option-comparison or selected-anchor sidecar is required or permitted.
+exceptional) and are NOT authored as discussion sidecars.
 
 ## CLI Packs
 
@@ -93,9 +99,8 @@ so conditions 1 and 5 above do not apply to it:
   `validators/designContractReadiness.ts` skips `QFAI-DCON-030`/`-033`/`-034` for it.
 - No design direction either: nothing downstream reads a theme for a surface that renders
   no tokens.
-- Conditions 2, 3, 4, 6 and 7 apply unchanged: all three canonical `uiux/` sidecars, the
-  full screen-contract schema, unranked exploration directions, no forbidden legacy
-  sidecar, and zero open OQs.
+- UI-bearing items 2, 3 and 4 and All Packs item 3 apply unchanged: all three canonical `uiux/` sidecars, the
+  full screen-contract schema, unranked exploration directions, and zero open OQs.
 - `route:` on a `cli` screen contract names the command invocation, not a web path, as the `cli` section of the UI-bearing playbook sets out.
 - No `prototyping.yaml`: `cli` is not a valid prototyping execution surface.
 - `primary_surface: cli` with a visual `secondary_surfaces` entry is NOT a cli-only pack —

package/assets/init/.qfai/assistant/skill/qfai-discussion/references/ui-bearing-playbook.md

@@ -74,7 +74,5 @@ shadows:
 
 Trend Scan is **not** a sidecar file. Trend Scan lives at
 `04_Sources.md#Trend Scan` (part of the core nine-file discussion pack).
-The legacy `uiux/20_trend_scan.md` template and the whole `uiux/20-24`
-design-evaluation family were removed; evaluation axes are now global
-constants and are not authored as discussion sidecars. UI-bearing
-completion checks read Trend Scan from `04_Sources.md`.
+Evaluation axes are global constants and are not authored as discussion
+sidecars. UI-bearing completion checks read Trend Scan from `04_Sources.md`.

package/assets/init/.qfai/assistant/skill/qfai-discussion/references/ui_ux_best_practices.md

@@ -116,12 +116,7 @@ Those three are the entire canonical sidecar family. Evaluation axes are global
 QFAI CLI applies — not by any file in this tree. The reviewer prompt that
 `/qfai-prototyping` ships restates that axis set; editing it does not change the set the CLI accepts. Axes are not
 authored as discussion sidecars. Discussion is planner-first: it carries exploration directions
-unranked and does not select a single visual winner, so there is no strategy, taste-interview, scoring,
-override, option-comparison or selected-anchor sidecar. Do NOT create
-`10_implementation_strategy.md`, `11_design_taste_interview.md`, the `20-24`
-design-evaluation family, `30_option_comparison.md`, or `31_selected_anchor_screen.md` —
-those filenames are forbidden, see `templates/uiux/00_index.md#Forbidden Legacy Files`, and
-creating them fails validation.
+unranked and does not select a single visual winner.
 
 ### What must be explicit in the discussion pack
 

package/assets/init/.qfai/assistant/skill/qfai-discussion/templates/uiux/00_index.md

@@ -30,19 +30,3 @@ cli-only pack — `primary_surface: cli` with no visual surface in
 `secondary_surfaces` — never gets one: the `common-design-md` step writes none, and
 `/qfai-prototyping` does not run on `cli`. Do not report any pack as
 incomplete for a missing `DESIGN.md`.
-
-## Forbidden Legacy Files
-
-The following files are NOT part of the canonical family and must NOT be created in new packs:
-
-- `10_implementation_strategy.md` — discussion carries directions unranked, so it selects no strategy
-- `11_design_taste_interview.md` — brand signals are recorded in `04_Sources.md`
-- `12_design_system.md` — replaced by root `DESIGN.md`
-- the `20`–`24` design-evaluation family — the evaluator axes are fixed by the CLI, not authored here
-- `30_option_comparison.md` — replaced by root `DESIGN.md`
-- `31_selected_anchor_screen.md` — replaced by root `DESIGN.md`
-- `33_exploration_rubric.md` — replaced by the fixed evaluator axes (`.qfai/assistant/skill/qfai-prototyping/references/reviewer-prompt.md`)
-- `34_evaluator_calibration.md` — replaced by the fixed evaluator axes (`.qfai/assistant/skill/qfai-prototyping/references/reviewer-prompt.md`)
-- `40_contracts.md` — replaced by `40_screen_contracts.md`
-- `50_review_bundle.md` — replaced by `50_review_input_bundle.md`
-- `60_critique_loop.md` — removed (critique integrated into review bundle)

package/assets/init/.qfai/assistant/skill/qfai-grilling/SKILL.md

@@ -24,11 +24,15 @@ shared, closes the asking, or stops the session, a delegated session adopts the
 griller's recommendations, or a run that may not ask writes every node left
 where its stage's gate reads it.
 
-**Which kind of session runs is the invoking stage's to say.** A stage whose
-work is the interview holds a user session; every other stage holds a delegated
-one, where a griller interviews the authors and the user is asked only a
-critical decision (`.agents/rules/grilling.md` § Two kinds of session). A stage
-that says nothing holds a delegated session.
+**The invoking stage picks the session.** A stage whose work is the
+interview holds a user session; any other holds a delegated one, where a griller
+interviews the authors and only a critical decision reaches the user, and only
+for a decision the repository cannot settle (`.agents/rules/grilling.md` § When
+a session is held). Without one, no griller starts. A stage that says nothing
+holds a delegated session where one is held. Read
+`.agents/rules/grilling.md#explicit-delegation-for-a-discussion` before
+delegating a user discussion; record actual authority. No-question alone is not
+delegation.
 
 **The request bounds the tree** (`.agents/rules/grilling.md`). A decision whose
 only outcome is whether to add something the request did not ask for is left
@@ -53,7 +57,8 @@ least beyond the request.
 | A no-question mode is active        | Run without asking; open every node left over as a question |
 | An ambiguity met while implementing | Not a session — stop under Article IX of the constitution   |
 
-**A no-question mode silences the questions, not the session.** An invocation
+**A no-question mode silences user questions, not the session.** The master's
+explicit-delegation conditions permit author rounds. Otherwise, an invocation
 told not to ask — `--auto`, or whatever the host spells it as — settles what the
 evidence settles, dispatches the lookups, and opens every node left over as
 a question in the register the stage reads, so the stage cannot complete over
@@ -115,19 +120,17 @@ re-opens it.
 1. Recompute the frontier from what is now settled.
 2. Dispatch the fact lookups the remaining decisions wait on. Do not block the
    round on them.
-3. Put the whole frontier at once, so the user sees what is being decided
-   together.
+3. Put the whole frontier at once to the session's answerer: the user by
+   default, or authors in a qualifying delegated session.
 4. Read the answers, then return to step 1.
 
 Two questions never share a round when one depends on the other; the dependent
 one belongs to a later round. The next round is never written ahead of the
 answers it is computed from.
 
-**A no-question mode is read before any of this.** Where the invocation is told
-not to ask — `--auto`, or whatever the host spells it as — no round is put at
-all, so nothing below applies and the no-question section above governs. A mode
-that withholds the tool while still permitting questions is a different thing,
-and is the fallback's case.
+**A no-question mode is read before any of this.** Agent rounds require
+explicit delegation; otherwise the section above governs. A withheld tool with questions still
+permitted uses the fallback.
 
 **Three things send a round to plain text**: the host has no structured question
 tool, the current mode withholds it while still permitting questions, or the
@@ -214,18 +217,22 @@ simple.
 **A delegated session has no condition 2**, because no user is there to
 confirm. A budget bounds its rounds: two, then every decision that is not
 critical takes the griller's recommendation — the ones the agents agreed on and
-the ones still open alike — and every critical decision goes to the user at
-once, without spending a round
+the ones still open alike. An uncovered critical decision goes to the user
+when asking is permitted, without spending a round
 (`.qfai/assistant/rule/review-convergence.md`). It ends `adopted` once
-no node is open and the user has answered every critical decision.
+the master's conditions hold: no open node or lookup, required inputs present,
+and actual authority for critical decisions. Record agent choices as agents'.
 
-**The budget ends the rounds, not the session.** While a critical decision is
-unanswered the session is still open: the user answers it, or ends the session
+**The budget ends the rounds, not the session.** While a critical decision
+lacks an actual answer or applicable recorded authorization, it stays open: the user answers it, or ends the session
 another way — or, under a no-question mode, the register write ends it
 `no-question`. How many went is a count a record carries, never an ending.
 
-**A session under a no-question mode cannot reach condition 2 either**, because
-there is a user and the mode forbids asking them. It ends when nothing on the
+**Only a no-question session meeting the master's explicit-delegation
+conditions ends `adopted`.**
+
+**Any other session under a no-question mode cannot reach condition 2
+either**, because the mode forbids asking the user. It ends when nothing on the
 frontier is still waiting: every decision the evidence settled is settled, and
 every one it did not is opened as a question where the stage's own gate reads it
 (`.qfai/assistant/rule/constitution.md` Article X, rule 6). The register
@@ -350,6 +357,9 @@ Every decision this skill meets falls in one of three named buckets.
   - grilling subject (the design to interrogate; a session has no default for
     what it is about)
 
+Explicit delegation is not `auto-decide` or a fact or human answer.
+These user-session entries remain the default.
+
 The asking is what this skill performs, so its `ask-user` entries are its own operations
 rather than an entry added to the prototype.
 

package/assets/init/.qfai/assistant/skill/qfai-grilling/references/delegated-session.md

@@ -53,6 +53,7 @@ decisions belonging to different drafting roles.
   report lists it; nothing waits for the user to read it.
 
   A critical decision is the exception: agreement closes its node for the
-  round, and only the user's answer settles it. Recording an agreed critical
-  decision as settled is how a choice nobody with the standing made reaches a
-  draft.
+  round, but only an actual user answer or an explicit applicable authorization
+  under `.agents/rules/grilling.md#explicit-delegation-for-a-discussion` settles
+  it. Record that authority separately from the agents' positions. Agreement
+  alone does not settle it, and an unknown user-held fact still stays open.

package/assets/init/.qfai/assistant/skill/qfai-grilling/references/session-record.md

@@ -18,7 +18,9 @@ Use the shared schema from
 The invoking stage's reviewer confirms this about the session:
 
 - no decision was recorded as the user's that the user did not answer, no
-  critical decision was adopted without them, and none was assumed that the
+  critical decision was adopted without an actual user answer or an explicit
+  applicable human authorization under the master's delegation conditions,
+  and none was assumed that the
   assumption path excludes;
 - every adopted decision has its `agents` row, and none of them adds what the
   request did not need;
@@ -27,7 +29,11 @@ The invoking stage's reviewer confirms this about the session:
   five endings `.agents/rules/grilling.md` names. Between agents a round budget
   bounds the rounds (`.qfai/assistant/rule/review-convergence.md`), and
   a session recorded as ended while a critical decision it escalated is still
-  unanswered is the finding.
+  unanswered and lacks that recorded authority is the finding;
+- for an explicitly delegated discussion, the actual user instruction, its
+  scope and authority, actual author rounds and dissent, no open node or
+  running lookup, all required consumed inputs, and actual end/authoring times
+  are evidenced. `adopted` without these is not a passing session.
 
 The reviewer works under these rules:
 

package/assets/init/.qfai/assistant/skill/qfai-implement/SKILL.md

@@ -40,6 +40,7 @@ steps:
   - implement-tooling
   - implement-backport
   - implement-acceptance
+  - implement-procedure
 requires: [common-review-cycle]
 mode: approval-gated
 ---
@@ -86,6 +87,11 @@ design. They are written by the `write-acceptance-tests` route, or by
 `implement-acceptance` run alone, and the report says which BF and AC tests
 still have an empty body.
 
+For that report or a handoff of unfinished BF/AC bodies, read
+`.qfai/assistant/step/verify-repo-gate/STEP.md#acceptance-evidence-and-follow-up`.
+It separates annotation proof, body states, actual behavior and execution,
+and the remaining work's owner and completion criteria.
+
 Each of these runs alone, instead of that order, when the request is not new
 behaviour but a failure, a repair or upkeep:
 
@@ -131,6 +137,12 @@ and reporting requirement, and states any assumption it built on
 (`.qfai/assistant/rule/test-layers.md#test-suite-sizing`,
 `.agents/rules/minimal-implementation.md` § 4).
 
+## Route-only procedure authoring
+
+When the plan names `implement-procedure`, follow
+`.qfai/assistant/step/implement-procedure/STEP.md`.
+Business-flow invocations skip it; existing flow steps apply.
+
 ## Completion
 
 The invocation completes on the gate of its last step once
@@ -139,9 +151,10 @@ every finding of its one review is fixed or answered. Invoked by name, it runs
 completion; when that fresh validate result has no test-obligation EX finding
 for this BF, the invocation reports "nothing to do", and reads or writes no
 ledger status. Inside a route it runs no validate: the verify stage does.
-The report ends with a question listing the next actions, `/qfai-verify`
-recommended, as `.agents/rules/user-questions.md` § 6 sets out.
-Under a no-question mode, list them in the report instead.
+When the next step needs the user's answer, ask a question listing the next
+actions, `/qfai-verify` recommended, per `.agents/rules/user-questions.md` § 6.
+Completion-only reports ask nothing. Under a no-question mode, list remaining
+actions instead.
 
 ## Default Autopilot Policy
 

package/assets/init/.qfai/assistant/skill/qfai-implement/references/parallelization-policy.md

@@ -10,7 +10,15 @@ For each candidate item, name its production files, test files, contracts, fixtu
 
 Deny parallel dispatch when two items write the same shared fixture or mock file, or mutate the same fixture instance. A shared fixture module that both items only read as-is does not by itself deny parallel dispatch.
 
-Give each worker a separate worktree and an exact file ownership list. Workers do not change another worker's files or the story tree. The orchestrator integrates their results and resolves every overlap before judging either item complete.
+Give each worker an exact file ownership list and a checkout assigned by the host.
+Use separate worktrees when the host supports editing them; otherwise use the
+existing shared-index mode in
+`.qfai/assistant/rule/workflow.md#concurrency-stage-independent-mandatory`.
+Creating a worktree does not grant edit permission. For a refused edit, follow
+`.qfai/assistant/rule/shared-skill-delegation-baseline.md#worker-edit-boundary`.
+Workers do not change another worker's files or the story tree. The orchestrator
+integrates their results and resolves every overlap before judging either item
+complete.
 
 ## Integration gate