@juzser/blacksmith 0.3.0 → 0.5.0

package/factory/policies/crosscheck.yml

@@ -14,11 +14,11 @@
 # provider does not fail loudly; it spends a doomed call on every quorum
 # trigger, has it caught, and leaves a failure row that reads like an outage.
 # So turn on the one you actually have — a one-line edit, runbook §2, and
-# `smith judge preflight` says beforehand whether it will work.
+# `bs judge preflight` says beforehand whether it will work.
 # Full setup/calibration/promotion procedure: docs/runbooks/providers.md.
 #
 # Shadow mode (Phase 8 design decision): `mode: shadow` means a provider's
-# verdicts are RECORDED (judge-verdict events, `smith stats providers`) but
+# verdicts are RECORDED (judge-verdict events, `bs stats providers`) but
 # have ZERO gating power — quorum.ts falls back to the native verdict alone
 # whenever no provider in a case is `mode: active`. Flipping a provider to
 # `mode: active` in this file (an operator edit, never a runtime write) is
@@ -48,13 +48,21 @@ providers:
     # extractor generations diverge exactly as D-118 claimed: first-parseable
     # returns `[]`, first-validating returns the verdict. If you change these
     # args, re-run that comparison rather than reasoning about it.
-    args: ["exec", "--color", "never"]
-    model_tier: mid          # taxonomy.yml model_tier — judge tier, architecture §4
+    #
+    # Model and effort are pinned here, not inherited. Without `-m` the judge
+    # runs whatever `~/.codex/config.toml` defaults to — an interactive-use
+    # choice, often the frontier model at high effort — so a confirm/refute
+    # call billed at `model_tier: mid` spent frontier quota. `model` below must
+    # name the same id as `-m`: it is what the event log records (without it a
+    # cli judge is logged as `codex:default`), and nothing checks the two agree.
+    args: ["exec", "--color", "never", "-m", "gpt-6-sol", "-c", "model_reasoning_effort=\"medium\""]
+    model: gpt-6-sol
+    model_tier: mid         # taxonomy.yml model_tier — judge tier, architecture §4
     # PRECONDITION: `codex` on PATH, and `codex login` run on every machine
     # that dispatches a quorum trigger. Without either the CLI transport still
     # spawns, fails, and quorum.ts records a provider error per trigger —
     # caught, so nothing gates on it, but it is latency and noise.
-    # `smith judge preflight` checks the first half locally; only a real call
+    # `bs judge preflight` checks the first half locally; only a real call
     # can check the second.
     # `auto`, not `true`. This is the one field in the file that describes a
     # MACHINE, and the file is checked in, so `true` here would be a claim
@@ -69,7 +77,7 @@ providers:
     # session still spends a call per trigger and records the failure.
     #
     # Turned on for THIS box, 2026-09-02, by the operator who owns it: `codex`
-    # resolves on PATH and `codex login` is done, both checked by `smith judge
+    # resolves on PATH and `codex login` is done, both checked by `bs judge
     # preflight` and by a real `codex exec` call. Rollback for one box is
     # `enabled: false` here, which `auto` never overrides.
     enabled: auto
@@ -89,11 +97,30 @@ providers:
     # is make this box gate the moment one is enabled, with no second edit
     # and no second decision to remember. Rollback is `mode: shadow` here.
     mode: active
+    # OpenRouter substitution (operator decision 1a, docs/runbooks/providers.md
+    # §9): when `codex` is missing from PATH or not logged in, and
+    # OPENROUTER_API_KEY is set, this provider runs through OpenRouter
+    # instead — same name, same mode, same gating power, only the transport
+    # and model underneath change. `openai/gpt-6-sol` is an EXACT catalog
+    # match (`curl -s https://openrouter.ai/api/v1/models`, checked
+    # 2026-09-30) for the id `-m gpt-6-sol` pins above: codex substitutes as
+    # literally the same model, not an approximation. No
+    # response_format_json_object override: the catalog entry lists
+    # `response_format` among its supported parameters, so the default
+    # (true) applies.
+    openrouter_fallback:
+      model: openai/gpt-6-sol
   deepseek:
     kind: api
     transport: api
     base_url: https://api.deepseek.com
-    model: deepseek-reasoner
+    # `deepseek-reasoner` retired from DeepSeek's own `/models` listing
+    # (live check of `/models`, 2026-09-30): a call naming it is now silently
+    # answered by `deepseek-flash` instead of erroring, so the pin below
+    # matters -- a stale model id here fails open, not closed.
+    # `deepseek-v4-pro` is DeepSeek's current reasoning-tier model, the
+    # direct-API successor to the retired `deepseek-reasoner`.
+    model: deepseek-v4-pro
     response_format_json_object: true
     api_key_env: DEEPSEEK_API_KEY
     model_tier: mid
@@ -103,7 +130,7 @@ providers:
     # Without it api-transport.ts throws `Environment variable "DEEPSEEK_API_KEY"
     # is not set` on every quorum trigger; quorum.ts catches it, so the gate
     # holds on the native verdict alone, but each trigger records a provider
-    # error. `smith judge preflight` reports the name it looked for and never
+    # error. `bs judge preflight` reports the name it looked for and never
     # the value it found, so it is safe to run anywhere.
     #
     # `auto`, not `true`, for the same reason codex is: this file is checked in
@@ -123,6 +150,17 @@ providers:
     # two dogfooded product epics (docs/runbooks/providers.md §3).
     # Rollback is `mode: shadow` here; nothing else remembers the promotion.
     mode: active
+    # OpenRouter substitution (operator decision 1a): when DEEPSEEK_API_KEY
+    # is missing and OPENROUTER_API_KEY is set, this provider runs through
+    # OpenRouter instead. `deepseek/deepseek-v4-pro` is an EXACT catalog
+    # match (`curl -s https://openrouter.ai/api/v1/models`, checked
+    # 2026-09-30) for the id pinned above: the fallback substitutes as
+    # literally the same model, not an approximation, same as the codex
+    # substitution above. No response_format_json_object override: the
+    # catalog entry lists `response_format` among its supported parameters,
+    # same as the direct-API entry above, so the default (true) applies.
+    openrouter_fallback:
+      model: deepseek/deepseek-v4-pro
 
 quorum_triggers:
   # architecture §6, agent-constraints.md "cross-check (phase 8)" — all four,
@@ -195,7 +233,7 @@ quorum_rule:
   # deciding with two opinions in front of them rather than one — which is the
   # whole point of the file — not an automatic override.
   #
-  # It silences one advisory in `smith judge preflight` and nothing else. A
+  # It silences one advisory in `bs judge preflight` and nothing else. A
   # provider enabled where it cannot be called is still a problem, and
   # `gating.canDecide` still reports false, because it is false.
   accept_non_gating_actives: true
@@ -204,7 +242,7 @@ asymmetric_roles:
   finder_ne_critic: true
   critic_mandate: refute, not confirm
   # The machine-readable form of finder_ne_critic (P9-23). Each pair says
-  # "this critic must not run on that finder's own model"; `smith dispatch
+  # "this critic must not run on that finder's own model"; `bs dispatch
   # check <session>` asserts it against the event log after the fact, using
   # the `model` field every dispatch_decision now carries. Without this list
   # the rule was unenforceable prose: it named no roles.
@@ -229,13 +267,13 @@ role_isolation:
   #
   # The only evidence of a separate turn the event log can hold is a separate
   # `dispatch_decision`, written by the node that dispatched, never by an agent
-  # about itself. `smith tester check <session>` asserts that against the log
+  # about itself. `bs tester check <session>` asserts that against the log
   # after the fact, per `testgate-result`.
   #
   # That reading survives delegation.yml granting `Agent` because of what the
   # grant costs: a grantee must open its own session first, so its dispatches
   # are its own log's, and no grant may hand a role its own auditor from the
-  # `pairs` below. `smith delegation check` enforces both, which is what keeps
+  # `pairs` below. `bs delegation check` enforces both, which is what keeps
   # a widened grant from quietly disarming this file.
   #
   # One entry, and it is meant to stay one until a second role starts grading
@@ -289,7 +327,7 @@ independent_finder:
   # summary and the failure scenario and never the source. A finder cannot: it
   # has nothing to read but the diff. Shipping worktree source to a third-party
   # API is a decision no code in this repo has standing to make quietly, so it
-  # is a switch, it ships false, and `smith crossfind run` REFUSES rather than
+  # is a switch, it ships false, and `bs crossfind run` REFUSES rather than
   # falling back to a diffless "find bugs" prompt that would invent findings.
   send_diff: false
   max_diff_bytes: 120000 # refuse rather than truncate: half a diff produces confident findings about code that is not there

package/factory/policies/delegation.yml

@@ -9,15 +9,15 @@
 # event log for what it dispatches" (docs/standards/agent-constraints.md).
 # Until D13 step 3 that was enforced by granting `Agent` to nobody, which also
 # capped an epic at one operator session. A grantee that opens its own session
-# with `smith session start <id> --continues <dispatch-event-id>` is a real
+# with `bs session start <id> --continues <dispatch-event-id>` is a real
 # dispatching node with a real log, so the cap can lift without the rule
 # bending.
 #
-# What a grant may not do — asserted by `smith delegation check` and by
+# What a grant may not do — asserted by `bs delegation check` and by
 # delegation.test.ts against the shipped files, so a widened grant fails CI:
 #
 #   - dispatch itself (a role that dispatches itself writes dispatches about
-#     itself, and `smith tester check` reads a second dispatch as proof of a
+#     itself, and `bs tester check` reads a second dispatch as proof of a
 #     second turn),
 #   - dispatch its own auditor from crosscheck.yml `role_isolation.pairs`
 #     (a coder that picks and prompts its own tester grades itself), or

package/factory/policies/effort.yml

@@ -7,7 +7,7 @@
 # written for: a decision made fresh every time is a decision made differently
 # every time. So the tiers are declared here and asked for, never recalled.
 #
-# HOST: `smith effort show --plan <plan.json>` reads this file plus the plan's
+# HOST: `bs effort show --plan <plan.json>` reads this file plus the plan's
 # own `effort` field and returns the profile for that epic
 # (factory/orchestrator/src/effort.ts). `.claude/skills/bs/plan.md` and
 # `run.md` run that verb at the top of `/bs plan` and `/bs run` and obey the
@@ -19,6 +19,14 @@
 # `effort_scaling:` block is the prose sibling of this file — it says fan-out
 # is a wall-clock optimisation; this says how much judgment each epic buys.
 #
+# Budgets follow the same tier (2026-09-29): `budgets.yml` sizes the epic cap
+# and every per-task cap for small / medium / huge, and each budget reader
+# takes the tier the epic runs at — the plan's `effort`, else `default_tier`
+# below, raised to `security_floor` when the floor applies. That is
+# a size, not a skipped step — the budgets still report and alarm at every
+# tier. Agent `maxTurns` is not tiered: one ceiling per template, sized for
+# `huge`.
+#
 # THE INVARIANT THAT MAKES THIS SAFE: a tier scales judgment steps only. It
 # never touches a mechanical oracle or a guardrail — see `invariants:` at the
 # bottom, which the host returns alongside every profile so the list cannot be
@@ -61,7 +69,7 @@ tiers:
     pre_code_uiux: when-ui-criterion
     # /bs plan steps 3-4 — planner <-> spec-reviewer until nothing S1/S2 is left.
     spec_review_rounds: until-clean
-    # /bs plan step 4 — `smith plan quorum` before operator sign-off.
+    # /bs plan step 4 — `bs plan quorum` before operator sign-off.
     plan_quorum: always
     # /bs run step 6 — the grader's bounded rubric loop (agent-constraints.md
     # caps it at 2; a tier may lower that number, never raise it).
@@ -120,22 +128,22 @@ tiers:
 
 # ── What no tier may touch ──────────────────────────────────────────
 #
-# Returned verbatim by `smith effort show` next to every profile. These are
+# Returned verbatim by `bs effort show` next to every profile. These are
 # mechanical oracles and guardrails, not judgments: their cost is a command
 # exiting, not an agent thinking, so scaling them saves nothing and buys
 # nothing but a weaker claim about the result.
 invariants:
   - the gate pipeline — schema check, grader verdict, tests, coverage
-    evidence, findings intake, severity decision (`smith gate run`)
+    evidence, findings intake, severity decision (`bs gate run`)
   - the root-level integration check on the assembled branch
-    (`smith integration check`)
-  - claim disjointness and worktree isolation (`smith wave check`,
-    `smith worktree create/fingerprint/verify`)
+    (`bs integration check`)
+  - claim disjointness and worktree isolation (`bs wave check`,
+    `bs worktree create/fingerprint/verify`)
   - the security-reviewer's conditional dispatch
-    (`smith security triggers`) — sensitive-paths.yml decides it, not a tier
+    (`bs security triggers`) — sensitive-paths.yml decides it, not a tier
   - the operator's plan sign-off, which no tier may skip or infer
-  - the epic-final verdict and its mechanical holds (`smith epic verdict`,
-    `smith epic close`)
+  - the epic-final verdict and its mechanical holds (`bs epic verdict`,
+    `bs epic close`)
   - the event log — every dispatch is still a `dispatch_decision` with a
     causal parent, at every tier
   - the escalation ladder after a blocked round (budgets.yml

package/factory/policies/guardrails.yml

@@ -1,7 +1,7 @@
 # Blacksmith — guardrail enforcement policy
 #
 # docs/standards/guardrails.md is the contract; this file is the data half of
-# what enforces it. HOST: `smith policy check`/`smith policy hook`
+# what enforces it. HOST: `bs policy check`/`bs policy hook`
 # (factory/orchestrator/src/policy.ts), and — via `dist/policyHook.js` —
 # `.claude/hooks/guard.sh`, the PreToolUse gate on every guarded tool call
 # an agent session makes.
@@ -36,9 +36,11 @@ protected_branches:
   # history-rewrite rule only (rule 5) — worktree.yml's
   # `integration_branch.pattern`: a leaf ref "smith/<epic>" cannot coexist
   # with "smith/<epic>/<task-id>" refs in real git (D/F ref conflict), so the
-  # shape is "smith/<epic>/integration", never a bare "smith/<epic>".
+  # shape is "smith/<epic>/integration", never a bare "smith/<epic>". Both
+  # prefixes are listed (bs-rename, operator decision 2/3): new epics
+  # integrate on bs/, but one already under way on smith/ stays there.
   names: [main, master]
-  patterns: ["smith/*/integration"]
+  patterns: ["bs/*/integration", "smith/*/integration"]
 
 catch_up_remotes:
   # rule 3's one exception: the remotes a protected branch is allowed to
@@ -123,7 +125,7 @@ rules:
 # ---------------------------------------------------------------------------
 #
 # Everything above applies to every agent session. This block applies to one
-# additional condition: a `smith sandbox open` lease is active over the
+# additional condition: a `bs sandbox open` lease is active over the
 # directory the command will run in (factory/orchestrator/src/sandbox.ts).
 # The orchestrator opens a lease before handing a worktree to one of the six
 # read-only judge roles and closes it after.
@@ -141,7 +143,7 @@ rules:
 #
 # What it is not: a container, a seccomp profile, or a read-only mount. A
 # command that writes through an interpreter (`python3 -c "open(...,'w')"`)
-# is invisible to a matcher, and always will be. `smith worktree verify`
+# is invisible to a matcher, and always will be. `bs worktree verify`
 # stays in the pipeline behind this for exactly that reason. Both halves are
 # stated in docs/standards/guardrails.md; neither is sold as the other.
 #
@@ -157,7 +159,7 @@ judge_sandbox:
   # `Edit`/`Write` (.claude/agents/*.md). `researcher` is deliberately absent
   # — fetching is its job, and it is never leased. A lease is matched to a
   # rule set by role, and a role named in neither list falls back to *this*
-  # one, so the list is the vocabulary `smith sandbox open --role` validates
+  # one, so the list is the vocabulary `bs sandbox open --role` validates
   # against rather than a gate of its own.
   roles: [reviewer, verifier, spec-reviewer, security-reviewer, grader, uiux]
 

package/factory/policies/harness.yml

@@ -3,14 +3,14 @@
 # architecture §19 "Worker harness port". A *provider* is the model vendor a
 # judge's verdict comes from (crosscheck.yml); a *harness* is the program
 # that holds a worker turn — gives the agent its tools, its working directory,
-# its turn limit. HOST: `smith harness list` / `smith harness plan`
+# its turn limit. HOST: `bs harness list` / `bs harness plan`
 # (factory/orchestrator/src/harness.ts), which read this file when `--policy`
-# names no other. `smith` renders an invocation from it and never starts one
-# (§18 rule 3); `smith-run` (src/run-cli.ts) is the separate binary that does.
+# names no other. `bs` renders an invocation from it and never starts one
+# (§18 rule 3); `bs-run` (src/run-cli.ts) is the separate binary that does.
 #
 # Shape, per harness:
 #   kind          `in-process` — the Claude Code Agent tool, no program started
-#                 (`command`/`args` unused); `cli` — a program `smith-run` spawns
+#                 (`command`/`args` unused); `cli` — a program `bs-run` spawns
 #                 with the rendered prompt on stdin.
 #   roles         taxonomy roles this harness serves; empty = every role that
 #                 ships a `.claude/agents/<role>.md`.
@@ -25,7 +25,7 @@
 #                 when this is empty). Rule 6's fingerprint runs regardless.
 #   schema_args   appended only when the turn names a schema (`--schema`), so a
 #                 turn that validates nothing renders without one.
-#   output        how smith-run reads the program's output: `text` (default),
+#   output        how bs-run reads the program's output: `text` (default),
 #                 `codex-json` (the `codex exec --json` JSONL stream),
 #                 `claude-json` (the `claude -p --output-format json` object).
 #   models        tier → model id for `{model}`; tiers are taxonomy.yml

package/factory/policies/lessons.md

@@ -81,8 +81,8 @@ select on. Each names its own bullet, validated against `taxonomy.yml`:
 At dispatch, an `agent-role` entry reaches only the role its `agent_role`
 names, and a `case-type` entry only a task whose `case` its `case_type`
 names. An entry in one of those scopes with **no** selector reaches NOBODY —
-it is inert, not universal, and `smith lessons for-dispatch` reports it as
-such. `smith lessons raise` refuses to mint one; the entries that predate
+it is inert, not universal, and `bs lessons for-dispatch` reports it as
+such. `bs lessons raise` refuses to mint one; the entries that predate
 the selector (D-129) are the only ones that can still be in that state.
 
 Two kinds of entry are therefore injected at dispatch and still never
@@ -124,6 +124,26 @@ nothing.
 - agent_role: planner
 - statement: An acceptance criterion that probes a script running under 'set -e' must name the outer exit status it expects, never an echo the script prints afterwards: errexit ends the script at the first failing command, so a line printed after it is unreachable and the grader can only mark the wording, not the property.
 
+### lesson-raised-3aaf982e84ac: A file-length delta criterion must state whether the doc comments att...
+
+- lesson_id: lesson-raised-3aaf982e84ac
+- finding_category: correctness
+- agent_role: planner
+- statement: A file-length delta criterion must state whether the doc comments attached to the moved symbols move with them, and its window must be calibrated on that same choice; a window measured with comments included and silent about it fails a coder who leaves the comments behind.
+
+### lesson-raised-d478f9d6ea0b: Name an extraction task's scope as a symbol list, not a line range, a...
+
+- lesson_id: lesson-raised-d478f9d6ea0b
+- finding_category: correctness
+- agent_role: planner
+- statement: Name an extraction task's scope as a symbol list, not a line range, and derive its length window from the symbols that move; a window calibrated on a span that is wider than the enumerated symbols rewards the over-broad move and rejects the correct one, and a text-preserving destructure hides the difference from every other criterion.
+
+### bs-audit-3-scribe-cites-event-ids: A PR body or timeline summary cites events by event id (<session>#<n>...
+
+- lesson_id: bs-audit-3-scribe-cites-event-ids
+- agent_role: scribe
+- statement: A PR body or timeline summary cites events by event id (<session>#<n>, where n is the zero-based line index of the log), never by a line number of the log file, and states no number the event log does not carry: coverage percentages, turn caps, round reasons and provider counts included. The orchestrator checks every cited id against the log before the body is published.
+
 ## claim-path
 
 ### lesson-raised-3b5746704cfc: A function that computes a filesystem path and hands it to a child pr...
@@ -654,6 +674,37 @@ _(none yet)_
 - lesson_id: lesson-raised-3a400ca69b5e
 - statement: When two verbs are compared for cost, check when each one runs before concluding: the cheaper one may run after the very gate it was meant to save.
 
+### lesson-raised-44a58c2a7c7a: When checking a length-delta criterion, classify every line in the mo...
+
+- lesson_id: lesson-raised-44a58c2a7c7a
+- finding_category: correctness
+- statement: When checking a length-delta criterion, classify every line in the moved region as code, comment or blank and count them; never derive a line count by subtracting line numbers, because the span between two anchors includes whatever else lives there.
+
+### lesson-raised-394329488a2d: SMITH_EPIC_CAP_TOKENS in the gitignored .env overrides the epic cap i...
+
+- lesson_id: lesson-raised-394329488a2d
+- statement: SMITH_EPIC_CAP_TOKENS in the gitignored .env overrides the epic cap in budgets.yml, so the committed cap is not the enforced one; read budget alarm's capTokens and budgetEnvOverrides for the live cap, never budgets.yml.
+
+### lesson-raised-add2171a83a1: On a plan whose tasks are all origin user, the plan-quorum triggers a...
+
+- lesson_id: lesson-raised-add2171a83a1
+- statement: On a plan whose tasks are all origin user, the plan-quorum triggers are mechanically silent - trigger 1 sums declared budgets, not measured spend, and trigger 3's per-task arm only reads non-user origins - so the only live trigger is the orchestrator's own --confidence self-report; report it honestly below 0.8 when the draft needed repair rounds.
+
+### lesson-raised-be27b49f1d19: budget alarm reports unverifiable when dispatches for roles without a...
+
+- lesson_id: lesson-raised-be27b49f1d19
+- statement: budget alarm reports unverifiable when dispatches for roles without an attribution path (auditor, security-reviewer) are in the log, and the planner role has no per-role cap, so a planner overrun is only visible against the epic cap.
+
+### bs-audit-3-gate-timeout-under-load: Size a test-gate check's timeout for a loaded machine, not a quiet on...
+
+- lesson_id: bs-audit-3-gate-timeout-under-load
+- statement: Size a test-gate check's timeout for a loaded machine, not a quiet one: a suite that runs in about 200 s bare can be killed at a 300 s default with no output while another build shares the CPUs. When a check dies at its timeout with no test output, read machine load before blaming the code, log it as an env failure, and raise that check's timeout_ms through the per-check override; never drop or narrow the check to get it under the limit.
+
+### lesson-dream-vam-audit-7-2026-09-28-135: Every judge or worker dispatch brief names the JSON Schema its result...
+
+- lesson_id: lesson-dream-vam-audit-7-2026-09-28-135
+- statement: Every judge or worker dispatch brief names the JSON Schema its result file must satisfy: the full result envelope (task_id, agent, provider, model_tier, token_usage), the verdict at .structured_output, and the schema's own keys; the orchestrator schema-checks the file as soon as the agent returns, before gate run.
+
 ## security
 
 _(none yet)_

package/factory/policies/scheduler.yml

@@ -1,7 +1,7 @@
 # Blacksmith — scheduler policy
 #
 # Knobs for `factory/orchestrator/src/scheduler.ts` (architecture §12
-# "Recheck scheduling" + "Scheduled growth passes"; `smith scheduler run`).
+# "Recheck scheduling" + "Scheduled growth passes"; `bs scheduler run`).
 # A deterministic pass over the event log that only ever emits PROPOSAL
 # events — it never dispatches an agent or widens scope on its own.
 
@@ -50,7 +50,7 @@ lessons:
 autonomy:
   # Who says yes to what this pass proposes. The scheduler decides WHAT is
   # due; this block decides what may proceed without an operator tick, and
-  # `smith scheduler admit` (src/autonomy.ts) applies it. That command still
+  # `bs scheduler admit` (src/autonomy.ts) applies it. That command still
   # enacts nothing — it prints the classification so it can be read and
   # argued with before anything moves.
   #
@@ -71,7 +71,7 @@ autonomy:
   # or the enable marker classifies operator and never reaches the merge at
   # all. The loop may merge what it builds; it may not merge what bounds it.
   #
-  # None of those six is enforced by code yet, because `smith loop` does not
+  # None of those six is enforced by code yet, because `bs loop` does not
   # exist yet. Until it does, this block's `enabled: true` still only governs
   # dispatch, and the merge is performed by whoever is driving the session.
   enabled: true
@@ -82,7 +82,7 @@ autonomy:
   # says. The list is a ceiling, never a floor.
   #
   # `error-report` — the daemon proposing that an error the log holds with
-  # no `issue-reported` event be filed (`smith issues report`) — is left out
+  # no `issue-reported` event be filed (`bs issues report`) — is left out
   # on purpose, and listing it would not change that either. Filing writes
   # to an external issue tracker under an authenticated `gh` token whose
   # scope includes `repo`, and this block's standing decision is that

package/factory/policies/sensitive-paths.yml

@@ -13,7 +13,7 @@
 # a task can claim `src/auth/**` without writing the word "auth" anywhere in
 # its clauses, and that is exactly the task worth catching.
 #
-# HOST: `smith security triggers --task <spec.json>` reads this file and
+# HOST: `bs security triggers --task <spec.json>` reads this file and
 # returns the triggers that fired, with the claim and the glob that fired each
 # one (factory/orchestrator/src/security.ts, punch list P9-4). The dispatcher
 # in `.claude/skills/bs/dispatch.md` runs that verb rather than eyeballing the

package/factory/policies/severity.yml

@@ -31,6 +31,14 @@ levels:
       - a11y WCAG AA failure
       - new flaky test introduced by the task
       - behavioral-drift touching a core flow
+      - >
+          serious visual defect against the uiux spec or the project's design
+          system: a spec'd layout broken, or content clipped/overflowing, at
+          a required viewport; an interactive target below the project's
+          declared touch-target minimum (fall back to the WCAG 2.2 target
+          size minimum only when the project declares none); a required
+          state (empty, error, loading) missing (contrast: see a11y WCAG AA
+          above)
     on_trigger: >
       bounce to coder on the same branch; after 2 failed rounds, escalate
       model tier (mid -> frontier, budgets.yml); after 3, escalate to
@@ -40,7 +48,11 @@ levels:
     blocks_merge: false
     semantics: waivable — batched to operator at epic end
     classes:
-      - visual regression vs the uiux spec
+      - >
+          minor visual deviation from the uiux spec: spacing, color or type a
+          few px or a shade off a design-system token — not a broken layout,
+          clipped content, a missing required state, or a touch-target/
+          contrast failure below WCAG AA (those are S2-major, above)
       - performance regression > 20%
       - over-engineering (default severity — see rule below)
       - behavioral-drift not touching a core flow

package/factory/policies/stack.yml

@@ -2,7 +2,7 @@
 #
 # What the operator answered when they installed this clone (INSTALL.md
 # Step 6, "The stack interview"). Read by `factory/orchestrator/src/stack.ts`
-# via `smith stack show`, and through it by the scaffolder and by every agent
+# via `bs stack show`, and through it by the scaffolder and by every agent
 # that needs to know what this operator builds with.
 #
 # This file used to be a document. `docs/standards/stack.md` shipped one
@@ -13,20 +13,20 @@
 # question would otherwise put words in the operator's mouth.
 #
 # Not every answer is executable. The shipped templates implement a subset —
-# `smith stack check` prints which of your answers they honour and which are
-# recorded for the agents to read but not built into `smith new`. Nothing here
-# silently pretends: an answer the templates cannot honour makes `smith new`
+# `bs stack check` prints which of your answers they honour and which are
+# recorded for the agents to read but not built into `bs new`. Nothing here
+# silently pretends: an answer the templates cannot honour makes `bs new`
 # refuse rather than scaffold something else.
 
 # ── Language ────────────────────────────────────────────────────────
 # What the coder writes. `typescript` is the only value the shipped templates
-# scaffold; any other value is recorded, and `smith new` refuses rather than
+# scaffold; any other value is recorded, and `bs new` refuses rather than
 # handing you a TypeScript project you did not ask for.
 language: typescript # typescript | javascript | python | go | rust | other
 
 # ── Frontend ────────────────────────────────────────────────────────
 # `none` is the default because most projects are not UI projects, and the
-# base template is a plain library. `smith new --ui` needs a value the
+# base template is a plain library. `bs new --ui` needs a value the
 # templates implement — today that is `vue` and nothing else.
 frontend: none # none | vue | react | svelte | solid | vite-vanilla | other
 

package/factory/policies/taxonomy.yml

@@ -77,6 +77,7 @@ gate_event:      [schema-check-result, artifact-check-result,
                   finding-raised, finding-reverified, finding-suppressed,
                   finding-transitioned, finding-reattributed,
                   severity-decisions, waiver-granted, waiver-denied,
+                  task-waiver-approved,
                   gate-outcome, issue-reported]
                   # schema-check-result — task Result vs result.schema.json
                   # artifact-check-result — every artifacts[].path in that
@@ -95,7 +96,7 @@ gate_event:      [schema-check-result, artifact-check-result,
                   #                       always logged, including when the
                   #                       project declares nothing to install
                   # judges-outstanding  — a judge this task dispatched through
-                  #                       `smith judge dispatch` never reported
+                  #                       `bs judge dispatch` never reported
                   #                       back, so the gate refuses to score an
                   #                       unknown: a missing `--evidence` reads
                   #                       identically whether the judge found
@@ -194,6 +195,11 @@ gate_event:      [schema-check-result, artifact-check-result,
                   #                       waiver-batch / log-only)
                   # waiver-granted/-denied — operator waiver-batch answer,
                   #                       keyed by finding fingerprint
+                  # task-waiver-approved — operator approval of one waived
+                  #                       task, keyed by task id and valid from
+                  #                       its plan_version on; what the
+                  #                       epic gate accepts in place of a
+                  #                       gate run
                   # gate-outcome        — the composed gate pipeline's
                   #                       final structured result
                   # issue-reported      — issueReporter.ts's record of one
@@ -219,10 +225,10 @@ error:
                  # (planner, scribe) wrote outside its declared write root
                  # (P9-3); shipped as a code before it was a class
                  # judge-mutation — a read-only judge moved the worktree it
-                 # was judging (P9-5, `smith worktree verify`)
+                 # was judging (P9-5, `bs worktree verify`)
                  # uncited-claim — a researcher finding with no citation, or a
                  # citation that is neither a repo path with a line number nor
-                 # a URL actually fetched (P9-6, `smith research check`)
+                 # a URL actually fetched (P9-6, `bs research check`)
                  # unsourced-recommendation — a brief's recommendation names no
                  # finding, or names one the brief does not carry, so what came
                  # from fetched text is invisible (P9-6)

package/factory/policies/worktree.yml

@@ -17,19 +17,24 @@ worktree:
   # Relative to whatever directory the project was handed as, never to this
   # clone: a project beside the repo keeps its worktrees beside the repo too.
   path_pattern: "<project-parent>/.wt/<project>/<task-id>"
-  branch_pattern: "smith/<epic>/<task-id>"
-  created_from: integration branch head (smith/<epic>/integration), fresh each time
+  # bs-rename, operator decision 2/3: bs/ is the current prefix for every new
+  # epic; one that already integrates on the legacy smith/ prefix keeps it
+  # for its whole life rather than switching mid-epic (integration_branch
+  # below).
+  branch_pattern: "bs/<epic>/<task-id>"
+  created_from: integration branch head (bs/<epic>/integration), fresh each time
   lifecycle: deleted after merge — a stale worktree is a bug
   one_worktree_per_task: true
 
 integration_branch:
-  # Phase-3 correction: a bare "smith/<epic>" ref cannot coexist with
-  # "smith/<epic>/<task-id>" refs — git's ref namespace is hierarchical, so a
+  # Phase-3 correction: a bare "bs/<epic>" ref cannot coexist with
+  # "bs/<epic>/<task-id>" refs — git's ref namespace is hierarchical, so a
   # leaf ref and a directory prefix of the same name conflict (D/F conflict,
   # confirmed against a real git repo while implementing worktree.ts). The
   # integration branch is therefore a sibling of task branches under the
-  # epic's ref prefix, not a leaf at "smith/<epic>" itself.
-  pattern: "smith/<epic>/integration"
+  # epic's ref prefix, not a leaf at "bs/<epic>" itself. An epic that already
+  # integrates on smith/<epic>/integration (legacy) keeps that prefix instead.
+  pattern: "bs/<epic>/integration"
   rule: workers never touch main/master; only the operator merges the
     integration PR into the target repo's main.
 
@@ -75,7 +80,8 @@ merge_queue:
   mode: serial
   order: dependency order (topological, per recorded edges)
   admission_steps:
-    - rebase task branch onto current smith/<epic>/integration head
+    - rebase task branch onto current integration branch head (bs/<epic>/integration,
+      or smith/<epic>/integration for a legacy epic)
     - run the cumulative regression gate (every previously merged task's
       tests in this epic, not just the incoming task)
     - admit on green; reject and bounce on red
@@ -90,6 +96,6 @@ merge_queue:
     enabled: true
     max_lines_per_layer: 200
     note: >
-      workers emit small stacked layers (within the 400-line task diff cap)
-      rather than monolithic diffs; the queue lands stacks in dependency
+      workers emit small stacked layers (within the task diff cap,
+      budgets.yml `task.coder.cap_diff_lines`) rather than monolithic diffs; the queue lands stacks in dependency
       order (GitHub native stacked PRs).