@bridge_gpt/mcp-server 0.2.53 → 0.2.55

package/build/conductor-claude-hook-bin.js

@@ -1,3 +1,3 @@
 #!/usr/bin/env node
-import{spawnSync}from"node:child_process";import{readFileSync}from"node:fs";var CONDUCTOR_HOOK_EMIT_FAILED_WARNING="Warning: conductor hook emit failed.";function resolveClaudeHookEventName(payload){if(payload===null||typeof payload!="object"||Array.isArray(payload))return null;let record=payload,candidates=["hook_event_name","hookEventName","event_name","event"];for(let key of candidates){let value=record[key];if(typeof value=="string"&&value.trim().length>0)return value.trim()}return null}function mapClaudeHookEventToSemanticType(eventName){switch(eventName){case"SessionStart":return"run.started";case"SessionEnd":return"run.stopped";case"Stop":return null;case"SubagentStop":return null;case"Notification":return"agent.notification";case"PreToolUse":return"tool.intent";default:return null}}var REQUIRED_IDENTITY_ENV=["BAPI_CONDUCTOR_RUN_ID","BAPI_CONDUCTOR_WORKER_ID","BAPI_CONDUCTOR_TICKET_KEY","BAPI_CONDUCTOR_WORKTREE_PATH"];function nonEmpty(value){return typeof value=="string"&&value.trim().length>0}function buildClaudeHookConductorEvent(payload,env){let eventName=resolveClaudeHookEventName(payload),type=mapClaudeHookEventToSemanticType(eventName);if(type===null||env.BAPI_CONDUCTOR_ENABLED!=="1")return null;for(let key of REQUIRED_IDENTITY_ENV)if(!nonEmpty(env[key]))return null;let ticketKey=env.BAPI_CONDUCTOR_TICKET_KEY.trim(),worktreePath=env.BAPI_CONDUCTOR_WORKTREE_PATH.trim(),details={ticket_key:ticketKey,worktree_path:worktreePath};nonEmpty(env.BAPI_CONDUCTOR_REPO_NAME)&&(details.repo=env.BAPI_CONDUCTOR_REPO_NAME.trim());let raw=payload!==null&&typeof payload=="object"&&!Array.isArray(payload)?payload:{payload};return{source:"claude-code",type,subject:ticketKey,run_id:env.BAPI_CONDUCTOR_RUN_ID.trim(),worker_id:env.BAPI_CONDUCTOR_WORKER_ID.trim(),producer:"claude-code-hook",observed_via:"claude-code-hook",data:{details,raw}}}function buildConductorEmitEventArgs(event){let args=["--type",event.type,"--source",event.source];return nonEmpty(event.subject??void 0)&&args.push("--subject",event.subject),nonEmpty(event.run_id??void 0)&&args.push("--run-id",event.run_id),nonEmpty(event.worker_id??void 0)&&args.push("--worker-id",event.worker_id),nonEmpty(event.producer??void 0)&&args.push("--producer",event.producer),nonEmpty(event.observed_via??void 0)&&args.push("--observed-via",event.observed_via),args.push("--data-json-stdin","--json"),args}function resolveConductorEmitCommand(env,emitArgs){let cliFile=env.BAPI_CONDUCTOR_CLI_FILE;return nonEmpty(cliFile)?{command:process.execPath,args:[cliFile.trim(),"emit-event",...emitArgs]}:{command:nonEmpty(env.BAPI_CONDUCTOR_BIN)?env.BAPI_CONDUCTOR_BIN.trim():"conductor",args:["emit-event",...emitArgs]}}var defaultConductorSpawn=(command,args,input)=>{let result=spawnSync(command,args,{input,encoding:"utf-8",shell:!1});return{status:result.status,error:result.error}};function emitClaudeHookEventWithConductorCli(event,deps={}){let env=deps.env??process.env,spawn=deps.spawn??defaultConductorSpawn,emitArgs=buildConductorEmitEventArgs(event),{command,args}=resolveConductorEmitCommand(env,emitArgs),stdinPayload=JSON.stringify(event.data??{});try{let result=spawn(command,args,stdinPayload);return result.error?!1:result.status===0}catch{return!1}}function runClaudeConductorHookCli(deps={}){let env=deps.env??process.env,readStdin=deps.readStdin??(()=>readStdinSync()),warn=deps.warn??(m=>process.stderr.write(`${m}
-`)),payload;try{let raw=readStdin();payload=JSON.parse(raw)}catch{return warn(CONDUCTOR_HOOK_EMIT_FAILED_WARNING),0}let event;try{event=buildClaudeHookConductorEvent(payload,env)}catch{return warn(CONDUCTOR_HOOK_EMIT_FAILED_WARNING),0}return event===null||emitClaudeHookEventWithConductorCli(event,{env,spawn:deps.spawn})||warn(CONDUCTOR_HOOK_EMIT_FAILED_WARNING),0}function readStdinSync(){return readFileSync(0,"utf-8")}var exitCode=0;try{exitCode=runClaudeConductorHookCli()}catch{exitCode=0}process.exit(exitCode);
+import path from"node:path";import{fileURLToPath}from"node:url";var CONDUCTOR_CLAUDE_HOOK_REMOVED_STUB_MESSAGE=`'conductor-claude-hook' was renamed to 'epic-implementer-claude-hook'. Run 'epic-implementer-claude-hook ...' instead.
+`;function runConductorClaudeHookRemovedStubBin(deps={}){let writeStderr=deps.writeStderr??(chunk=>process.stderr.write(chunk)),exit=deps.exit??process.exit.bind(process);writeStderr(CONDUCTOR_CLAUDE_HOOK_REMOVED_STUB_MESSAGE),exit(1)}var invokedDirectly=process.argv[1]!==void 0&&path.resolve(process.argv[1])===fileURLToPath(import.meta.url);invokedDirectly&&runConductorClaudeHookRemovedStubBin();export{CONDUCTOR_CLAUDE_HOOK_REMOVED_STUB_MESSAGE,runConductorClaudeHookRemovedStubBin};

package/build/conductor-claude-hook-removed-stub-bin.js

@@ -0,0 +1,31 @@
+#!/usr/bin/env node
+/**
+ * Fixed migration stub for the retired `conductor-claude-hook` bin name (S4).
+ *
+ * The real Claude lifecycle hook bin moved to `epic-implementer-claude-hook`
+ * (see `epic-implementer-claude-hook-bin.ts`). This stub occupies the legacy
+ * `conductor-claude-hook` package.json bin key so the old executable name
+ * still resolves to something on a stale global install or a stale
+ * `.claude/settings.local.json` hook registration, but it performs no
+ * delegated hook work: it writes exactly one fixed line to stderr, nothing to
+ * stdout, and always exits `1`.
+ */
+import path from "node:path";
+import { fileURLToPath } from "node:url";
+/** The fixed migration-pointer line this stub writes to stderr, and nowhere else. */
+export const CONDUCTOR_CLAUDE_HOOK_REMOVED_STUB_MESSAGE = "'conductor-claude-hook' was renamed to 'epic-implementer-claude-hook'. Run 'epic-implementer-claude-hook ...' instead.\n";
+/** Run the stub: write the fixed line to stderr and exit `1`. Delegates to nothing. */
+export function runConductorClaudeHookRemovedStubBin(deps = {}) {
+    const writeStderr = deps.writeStderr ?? ((chunk) => process.stderr.write(chunk));
+    const exit = deps.exit ?? process.exit.bind(process);
+    writeStderr(CONDUCTOR_CLAUDE_HOOK_REMOVED_STUB_MESSAGE);
+    exit(1);
+}
+// Run for real ONLY when this file is the process's own entry — importing it
+// for its exported runner/deps (e.g. from a unit test) must never spend a real
+// process.exit as a side effect of import.
+const invokedDirectly = process.argv[1] !== undefined &&
+    path.resolve(process.argv[1]) === fileURLToPath(import.meta.url);
+if (invokedDirectly) {
+    runConductorClaudeHookRemovedStubBin();
+}

package/build/conductor-removed-stub-bin.js

@@ -0,0 +1,30 @@
+#!/usr/bin/env node
+/**
+ * Fixed migration stub for the retired `conductor` bin name (S4).
+ *
+ * The real event-ledger CLI moved to `epic-implementer` (see
+ * `epic-implementer-bin.ts`). This stub occupies the legacy `conductor`
+ * package.json bin key so the old executable name still resolves to
+ * something on a stale global install, but it performs no delegated work: it
+ * writes exactly one fixed line to stderr, nothing to stdout, and always
+ * exits `1`.
+ */
+import path from "node:path";
+import { fileURLToPath } from "node:url";
+/** The fixed migration-pointer line this stub writes to stderr, and nowhere else. */
+export const CONDUCTOR_REMOVED_STUB_MESSAGE = "'conductor' was renamed to 'epic-implementer'. Run 'epic-implementer ...' instead.\n";
+/** Run the stub: write the fixed line to stderr and exit `1`. Delegates to nothing. */
+export function runConductorRemovedStubBin(deps = {}) {
+    const writeStderr = deps.writeStderr ?? ((chunk) => process.stderr.write(chunk));
+    const exit = deps.exit ?? process.exit.bind(process);
+    writeStderr(CONDUCTOR_REMOVED_STUB_MESSAGE);
+    exit(1);
+}
+// Run for real ONLY when this file is the process's own entry — importing it
+// for its exported runner/deps (e.g. from a unit test) must never spend a real
+// process.exit as a side effect of import.
+const invokedDirectly = process.argv[1] !== undefined &&
+    path.resolve(process.argv[1]) === fileURLToPath(import.meta.url);
+if (invokedDirectly) {
+    runConductorRemovedStubBin();
+}

package/build/docs.generated.js

@@ -3,5 +3,5 @@
 export const DOCS = {
     "docs/mcp-tool-integrations.md": "# MCP tool integrations — the human \"why\" behind the capability report\n\nThis catalog is **explanatory prose only**. It exists so the `/install-bridge`\ncapability report can cite a human-readable \"why\" for each gate. It is **not** a\nsource of truth for gating: the server computes every `locked_tools` /\n`unlocked_tools` membership decision itself and the agent must never recompute a\ntool's dependencies from this document.\n\n**Authoritative source of gating.** The enforced rules — which tools are blocked,\nwhich are degraded, and what each requires — live in\n`api/library/vcs/vcs_route_operations.py`:\n\n- `VCS_ROUTE_REQUIREMENTS` — routes that **BLOCK** (are unavailable) without a\n  VCS connection.\n- `VCS_ROUTE_WARNINGS` — routes that **DEGRADE** (stay usable, but without\n  codebase context) without a VCS connection.\n- `NEVER_GATED_ROUTE_KEYS` — routes that are never gated on any integration.\n- `INDEX_REQUIRED_ROUTE_KEYS`, `INDEX_REQUIRED_COUNCIL_MODES`,\n  `CREATE_DOC_CODEBASE_CONTEXT_DOC_TYPES`, `CREATE_DOC_WARN_DOC_TYPES` — the\n  conditional \"requires a successful code index\" dimension.\n- The resolver helpers `get_required_vcs_operation()`, `get_warn_vcs_operation()`,\n  and `requires_successful_index()` are the authoritative functions that decide a\n  case. The capability report is derived from these; this catalog explains them.\n\n## Reading the capability report\n\nEach tool entry the server returns has the exact shape\n`{tool, effect, missing, semantics}`:\n\n- **`effect`**\n  - **`BLOCK`** — the tool is **unavailable** until every listed dependency is\n    met. It will refuse to run without them.\n  - **`DEGRADE`** — the tool is **usable right now**, but **without codebase\n    context** (it cannot ground its output in your repository). Connecting the\n    listed dependency upgrades it from \"works blind\" to \"works with full context\".\n    A `DEGRADE` tool is never \"failed\".\n- **`missing`** — the server-computed dependency identifiers still needed:\n  integration ids such as `github_app` / `vcs_access_token`, and the synthetic\n  `code_index` (a successful repository index).\n- **`semantics`**\n  - **`all_of`** — every id in `missing` is required.\n  - **`any_of`** — the VCS-provider candidates in `missing` are alternatives:\n    **either** `github_app` **or** `vcs_access_token` satisfies the VCS\n    requirement (this is the \"provider unknown\" case). When `code_index` also\n    appears, it remains separately required — `semantics` describes only the VCS\n    provider candidates, and a code index is always mandatory in addition.\n\nThe three readiness dimensions `configured` / `learned` / `indexed` are reported\nindependently. `indexed` may be `true`, `false`, or `null` — a `null` means the\nindex status could not be confirmed and must **not** be read as \"indexed\".\n\n## The integrations\n\n| Integration id | What it is | What it unlocks |\n| --- | --- | --- |\n| `jira` | Jira API access | Ticket reads/writes, estimation and review automations, status transitions. |\n| `github_app` | GitHub App installation | Pull requests, code review, and private-repo parsing on GitHub projects. |\n| `vcs_access_token` | VCS access token | Pull requests, code review, and private-repo parsing on Bitbucket projects. |\n| `vcs_webhook` | VCS webhook secret | Merge webhooks and CI follow-up triggers. |\n| `code_index` | A successful repository index | Codebase-grounded planning, architecture, reimplementation, and technical/discovery councils. Produced by `/parse-repository`. |\n\nA project's `github_app` **or** `vcs_access_token` provides the VCS connection;\nwhich one applies depends on the project's version-control system. When the\nproject's provider is unknown, either credential satisfies the requirement — the\nreport expresses that as `semantics: any_of`.\n\n## The gates, by capability\n\n### Pull requests and CI (BLOCK on VCS)\n\nTools like `create_pull_request`, `resolve_ci_checks`, `poll_ci_checks`, and\n`fresh_base` are **unavailable** (`BLOCK`) until a VCS connection is\nconfigured. They act directly on the version-control host, so without a\nconnection there is nothing for them to talk to.\n\n### Repository indexing and maps (BLOCK on VCS)\n\n`parse_repository` and `regenerate_directory_map` need a VCS connection to read\nthe repository. They **BLOCK** until VCS is connected.\n\n### Codebase-grounded generation (BLOCK on VCS **and** a code index)\n\nPlanning and architecture tools — `generate_plan_direct`,\n`generate_architecture_direct`, `request_reimplement_context`,\n`code_writer_generate_plan`, `code_writer_generate_architecture`, and\n`create_doc` for **TDD** / **architecture** documents — ground their output in\nyour indexed codebase. They **BLOCK** until BOTH a VCS connection AND a\nsuccessful code index exist (`all_of`, with `code_index` in `missing`).\n\n### Council (BLOCK on a code index, mode-dependent)\n\n`request_council` in **technical** or **discovery** mode searches your indexed\ncodebase, so it **BLOCK**s on `code_index`. **Design**-mode council requests never\nquery the index and are never gated.\n\n### Document generation that DEGRADEs (usable without codebase context)\n\nTools like `generate_prd_direct`, `generate_fsd_direct`,\n`code_writer_generate_fsd`, `generate_clarifying_questions_direct`,\n`generate_ticket_critique_direct`, `generate_ticket_review_direct`, and\n`create_doc` for **PRD** / **FSD** documents **DEGRADE** rather than block: they\nrun today from the ticket alone, and connecting VCS simply lets them ground their\noutput in your codebase. They always appear under \"Tools you can use now\", with a\nreduced-context caveat when the VCS connection is missing.\n\n### Never gated\n\nSetup and bootstrap tools (`ping`, `config_field`, `get_install_manifest`,\n`apply_install_manifest`, `persist_routing_credential`, and the\nbootstrap-invite exchange) are always available — they\nare how you configure everything else.\n",
     "docs/install/sfcc-integration.md": "# Installing the SFCC Integration (OCAPI)\n\nBridge's Salesforce B2C Commerce (SFCC) tools give an AI coding agent read access to\na sandbox's object model, custom object definitions, and site preferences — plus a\nsmall set of sandbox-only writes — through the **OCAPI Data API**. This guide covers\nsetting up the OCAPI client that those tools authenticate against.\n\n> **Sandbox / local development only.** This integration is intended for a **developer\n> sandbox**, and that restriction is **enforced in code**: before any SFCC tool runs,\n> Bridge validates the hostname your credentials actually resolve to — from `dw.json`\n> or `SFCC_*` — against the sandbox forms listed below. An unrecognized host is refused\n> with a `403` (`error.code: \"TARGET_NOT_SANDBOX\"`) before any request leaves your\n> machine. The check reads the resolved hostname, never the `instance` tool argument,\n> so omitting `instance` or passing `\"sandbox\"` cannot bypass it.\n>\n> Accepted sandbox hostname forms:\n>\n> - `<realm>-<nnn>.sandbox.<region>.dx.commercecloud.salesforce.com`\n> - `<realm>-<nnn>.sandbox.dx.commercecloud.salesforce.com`\n> - `<realm>-<nnn>.dx.commercecloud.salesforce.com`\n>\n> Anything else — a `production-`/`staging-`/`development-` prefixed host, or any\n> `*.demandware.net` host — is rejected.\n>\n> Still do not configure the grants below on an instance that holds real data.\n> Credentials stay local (in `dw.json` or `SFCC_*` env vars) and are never sent to\n> Bridge.\n\nFor the full per-tool list and what each SFCC tool depends on, see\n[MCP Tool Integration Dependencies](./mcp-tool-integrations.md). For the tool reference\nand the `BRIDGE_MCP_PROFILE` gating, see the SFCC section of the\n[package README](../../README.md).\n\n## Prerequisites\n\n- A running SFCC **developer sandbox** and its hostname\n  (e.g. `zzzz-001.sandbox.us01.dx.commercecloud.salesforce.com`).\n- An **Account Manager API client** — a `client-id` and `client-secret`. This is the\n  OCAPI client the tools use to obtain an OAuth token. Create one in Account Manager\n  (**API Client** → *Add API Client*) if you don't already have it, and note its\n  `client_id`.\n- Business Manager access to the sandbox with permission to edit **Open Commerce API\n  Settings**.\n\n## 1. Grant the OCAPI client access in Business Manager\n\nIn Business Manager for the sandbox:\n\n**Administration → Site Development → Open Commerce API Settings → Data API** tab.\n\nAdd the client entry below to the `clients` array of the Data API settings, then\n**Save**. It grants only the resource families and HTTP methods Bridge's SFCC tools\nactually call — not a global `/**` grant. `check_permissions` prints the same JSON on\na 401/403, split into the two blocks.\n\n**READ/SEARCH TOOL GRANTS** — required by the `sfcc` read tools. (`post` is OCAPI's\nconvention for its `*_search` endpoints, not a mutation.)\n\n```json\n{\n  \"client_id\": \"<your-client-id-here>\",\n  \"resources\": [\n    { \"resource_id\": \"/system_object_definitions\",    \"methods\": [\"get\"],         \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" },\n    { \"resource_id\": \"/system_object_definitions/**\", \"methods\": [\"get\", \"post\"], \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" },\n    { \"resource_id\": \"/site_preferences/**\",          \"methods\": [\"get\", \"post\"], \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" },\n    { \"resource_id\": \"/custom_object_definitions/**\", \"methods\": [\"get\", \"post\"], \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" }\n  ]\n}\n```\n\n**MUTATION GRANTS** — required **only if you enable `BRIDGE_MCP_PROFILE=sfcc-write`**,\nwhich registers the nine destructive write tools. These are shipped capabilities, not\nfuture work. No `delete` is granted, because no shipped write tool performs one; the\n`get` entries are needed for the If-Match ETag round trip that precedes each `PATCH`.\n\n```json\n{\n  \"client_id\": \"<your-client-id-here>\",\n  \"resources\": [\n    { \"resource_id\": \"/system_object_definitions\",    \"methods\": [\"get\"],                  \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" },\n    { \"resource_id\": \"/system_object_definitions/**\", \"methods\": [\"get\", \"put\", \"patch\"],  \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" },\n    { \"resource_id\": \"/custom_object_definitions/**\", \"methods\": [\"get\", \"put\", \"patch\"],  \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" },\n    { \"resource_id\": \"/site_preferences/**\",          \"methods\": [\"get\", \"patch\"],         \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" }\n  ]\n}\n```\n\nNotes:\n\n- The `client_id` **must match** the Account Manager API client whose credentials you\n  put in `dw.json` / `SFCC_*` below. Replace the value above with your own client id if\n  it differs.\n- If the Data API settings are empty, wrap the entries in the standard settings\n  envelope. Merge the resource lists from the block(s) above into one `resources`\n  array — do not substitute a global `\"resource_id\": \"/**\"` grant:\n\n  ```json\n  {\n    \"_v\": \"23.2\",\n    \"clients\": [\n      {\n        \"client_id\": \"<your-client-id-here>\",\n        \"resources\": [\n          { \"resource_id\": \"/system_object_definitions\",    \"methods\": [\"get\"],         \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" },\n          { \"resource_id\": \"/system_object_definitions/**\", \"methods\": [\"get\", \"post\"], \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" },\n          { \"resource_id\": \"/site_preferences/**\",          \"methods\": [\"get\", \"post\"], \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" },\n          { \"resource_id\": \"/custom_object_definitions/**\", \"methods\": [\"get\", \"post\"], \"read_attributes\": \"(**)\", \"write_attributes\": \"(**)\" }\n        ]\n      }\n    ]\n  }\n  ```\n\n- `check_permissions` (below) prints a ready-to-paste grant JSON on a 401/403, so you can\n  also let the tool tell you exactly what to add.\n\n## 2. Provide credentials locally\n\nCreate a `dw.json` in your project root (auto-added to git exclude — never commit it):\n\n```json\n{\n  \"hostname\": \"zzzz-001.sandbox.us01.dx.commercecloud.salesforce.com\",\n  \"client-id\": \"<your-client-id-here>\",\n  \"client-secret\": \"<account-manager-client-secret>\"\n}\n```\n\nAccepted key spellings: `hostname`/`host`, `client-id`/`clientId`/`client_id`,\n`client-secret`/`clientSecret`/`client_secret`. Prefer a single config — a multi-entry\n`configs[]` array forces an explicit `instance` on every call. Alternatively, export\n`SFCC_HOSTNAME` / `SFCC_CLIENT_ID` / `SFCC_CLIENT_SECRET` in the MCP server environment.\n\n## 3. Set the repo `version` config field\n\nSet the repo's `version` config to your SFCC project type — one of\n`sfra | pwakit | sitegenesis | storefrontnext | hybrid`. The call-time gate reads this;\na non-SFCC value blocks every SFCC tool except `sfcc_setup_status`. Set it via your\nnormal config path, the `config_field` MCP tool (operation `update`, field `version`),\nor the `/teach-bridge` skill.\n\n## 4. Enable the SFCC tools\n\nThe two diagnostic tools (`sfcc_setup_status`, `check_permissions`) are always\nregistered. Everything else is gated, behind **two independent profile groups**:\n\n| Group | Registers |\n|---|---|\n| `sfcc` | the 8 OCAPI read tools + `sfcc_log_query` — read-only |\n| `sfcc-write` | the 9 destructive write tools |\n\nNeither implies the other. Add what you need to `BRIDGE_MCP_PROFILE` in the MCP server\n`env` block (it is comma-separated), then **restart the MCP client**:\n\n```json\n\"env\": { \"BRIDGE_MCP_PROFILE\": \"sfcc\" }\n```\n\nFor reads plus writes, use `\"sfcc,sfcc-write\"`. `full` expands to every group and is\ntherefore write-capable.\n\n> **Migration.** `sfcc` used to register the nine write tools too. It no longer does.\n> If you were relying on SFCC writes through `BRIDGE_MCP_PROFILE=sfcc`, change it to\n> `BRIDGE_MCP_PROFILE=sfcc,sfcc-write`. `full` users keep write access and need no\n> change.\n\n## 5. Verify\n\nAsk your agent to run:\n\n1. `sfcc_setup_status` — expect all prerequisite checks ✓ (Bridge API key, repo name,\n   `version` config, `dw.json` presence/uniqueness, AM/OCAPI token acquisition).\n2. `check_permissions` — probes OCAPI via `GET /system_object_definitions`. A 200 (with\n   the OCAPI version) confirms the grant. On 401/403 it prints the exact grant JSON to\n   paste back in step 1.\n\nRestart the MCP client after any credential, grant, or env change — a running session\ndoes not pick them up.\n\n## Notes\n\n- **WebDAV logs are separate.** `sfcc_log_query` authenticates with a Business Manager\n  username + a 40-character **WebDAV access key** over HTTP Basic auth — *not* the OCAPI\n  OAuth token configured here. `sfcc_setup_status` reports OCAPI (step 5) and WebDAV\n  (step 6) independently; one can be green while the other is not.\n- **Writes are sandbox-only.** The write tools (attribute/preference create/update) target\n  a developer sandbox and echo a paste-ready grant JSON on a 403.\n",
-    "docs/bridge-ticket-authoring.md": "# Bridge ticket-authoring posture\n\nBridge has several surfaces that can create a ticket. Without a shared posture\neach one behaves differently, and the most-used surface carries none of the\nmaintainer's preferences at all. This document is the deep reference behind the\nshort posture block that every one of those surfaces carries verbatim.\n\nThe block itself is short on purpose — it competes for attention inside prompts\nthat are already long. Everything that explains *why* lives here.\n\n## The canonical block\n\nThis file **is** the canonical source. The marker-delimited block below is\nduplicated byte-identically onto every carrier — every surface that decides\nticket shape holds these exact bytes, so no surface can quietly drift into its\nown house style.\n\nCarriers (all four hold the block verbatim):\n\n- `agents/src/jira-ticket-writer.md` — the writer itself, plus a compressed\n  posture line in its `description:` frontmatter, which is the only coverage a\n  bare-chat session gets with no file read and no `tools/list` cost.\n- `commands/src/explore-ticket.md` — Stage 9, the most-used authoring surface.\n- `mcp_server/instructions/decompose-epic-candidate.md` — the `idea-to-ticket`\n  decomposition step.\n- `mcp_server/instructions/decompose-epic.md` — the `plan-epic` decomposition\n  step.\n\nEdit the block here, copy it verbatim to each carrier, and let\n`tests/pytest/mcp_server/test_ticket_authoring_posture_assets.py` prove it\nlanded. That test permits **no** per-surface variation.\n\n<!-- BEGIN BRIDGE TICKET-AUTHORING POSTURE -->\n<!-- Canonical source: docs/bridge-ticket-authoring.md.\n     This block is duplicated byte-identically onto every carrier. Never edit a\n     copy: edit the canonical source and re-copy it verbatim. A cross-surface\n     byte-equality test fails the build if any copy drifts by a single byte. -->\n\n## Ticket-authoring posture\n\nDeep reference: `docs/bridge-ticket-authoring.md`.\n\n**Draft through the writer.** Every ticket body — an epic parent, an epic child,\nand an ordinary sibling alike — is drafted by the `jira-ticket-writer` agent\nbefore `create_ticket` is called. Do not compose a ticket description inline.\n\n**Size the work.** Size each ticket by file-touch breadth and depth plus rough\nlines of code (LOC) changed:\n\n- `S = 1-2 files / <~80 LOC`\n- `M = ~3-8 files / ~80-400 LOC`\n- `L = ~8-15 files / ~400-900 LOC`\n- `XL = >15 files / >~900 LOC`\n\nTarget size priority: **L (target) -> XL (when the work does not fit in L) -> M\n(third choice) -> S (only when unavoidable)**. This applies equally to a\nstandalone ticket and to an epic child.\n\nAim each slice at L. When one will not fit, grow it to XL rather than splitting\nit — split only when the slice is genuinely two independent pieces of work,\nnever merely to land inside a band. Bridge's grooming and implementation process\nhandles a large vertical slice well and is overkill on small ones: every extra\nticket is another worktree, another PR, another rebase, and another chance for\ntwo workers to touch the same file. Reach for M because the work genuinely is\nthat size, not to avoid an XL.\n\nBeyond roughly 40 files or ~3000 LOC, split anyway. Past that point review\nturnaround and rebase cost dominate the run's budget, and a review that wedges\nholds the gate to its full retry ceiling before anyone notices.\n\n**Group at three.** Three or more implementable tickets is an epic: propose an\nepic parent plus an ordered child manifest, and resolve this surface's own\napproval gate before anything is created. One or two tickets are ordinary\nsiblings — no epic parent, no manifest. The threshold is exactly three.\n\n**Hand off once.** An epic handoff names exactly one conductor entry point,\n`drive-epic`, which selects the runnable path itself. Never present a choice\nbetween conductors.\n\n**Departure is closed-list only.** These three exceptions, and no others, permit\ndeparting from the rules above. Invoking one requires no announcement.\n\n- **E1 External-tracker mirroring** — a recorded upstream identifier exists and\n  its granularity is contractual. Bypasses sizing and the epic threshold.\n- **E2 Discovery-only spike** — no committed production-code deliverable.\n  Bypasses sizing only; does not bypass drafting through the writer.\n- **E3 Authorized incident containment** — tied to an active incident record,\n  not to schedule pressure. Bypasses sizing and the epic threshold.\n\nThe list is closed. Anything outside it is an escalation to the operator, not a\njudgement call. Explicitly refused as grounds for departure: a single-file\ntrivial fix (that is `S` reached through the normal path, not an exception),\ngeneric time pressure, \"already well specified\", \"faster without the writer\",\ndeveloper discretion, minor refactor, unattended mode, context limits, and \"hard\nto decompose\" (XL is the normal overflow, so that is the ordinary path and not a\ndeparture). Writer unavailability escalates; it never silently authorizes inline\ndrafting.\n\n<!-- END BRIDGE TICKET-AUTHORING POSTURE -->\n\nThe rest of this document is the rationale the block is deliberately too short to\ncarry.\n\n## Decision: Jira ticket authoring ships through the Jira Ticket Writer (BAPI-900)\n\nBridge ships two very different kinds of ticket-authoring surface, and customers\nneed to know which one they actually have.\n\n**Shipped customer surface.** A customer project gets the `jira-ticket-writer`\nagent — the same writer this posture requires every ticket body to go through —\nplus the agent-directed capability to revise an existing ticket's description.\nAsk your agent to draft a ticket with the Jira Ticket Writer, and ask your agent\nto update an existing ticket's description when it needs revising. Both reach a\ncustomer project because they are packaged: the writer through `AGENTS`\n(`mcp_server/src/agents.generated.ts`) and the description-update path through\nthe registered `update_ticket_description` / `request_ticket_update` MCP tools.\n\n**Repository-local workflows.** `.claude/commands/write-ticket.md` and\n`.claude/commands/update-ticket.md` are bridge-api's own repository-maintenance\ncommands. They are **not** scaffolded into a customer project by `--init`, have\nno `commands/src/` source, and have no generated Cursor or `mcp_server/`\nmirror — deliberately, not by omission. A customer asking their agent to run\nthe write-ticket or update-ticket slash command will not find either one,\nbecause neither ships.\n\n**Why (Option B, not a promotion to shipped status).** The Jira Ticket Writer is\nalready the packaged drafting surface this posture mandates, so shipping\n`write-ticket.md` as a second drafting entry point would duplicate it. More\nimportantly, `write-ticket.md` is today an autonomous, single-ticket, no-halt\npipeline (\"No human confirmation gates — run end-to-end\") with no decomposition\nstep and no approval gate — it cannot honor the \"group at three\" epic rule or\nthe epic approval gate this posture requires, because it was never built to\npropose an epic at all. Promoting it to a shipped surface without that redesign\nwould ship a customer-facing command that silently violates this file's own\nposture. Until that redesign happens, `write-ticket.md` and `update-ticket.md`\nstay repository-local, and every packaged surface directs customers to the Jira\nTicket Writer and to agent-directed description updates instead.\n\n\n## The four rules\n\n### 1. Draft through `jira-ticket-writer`\n\nEvery ticket body is drafted by the `jira-ticket-writer` agent before\n`create_ticket` is called — an epic parent, an epic child, and an ordinary\nsibling alike. Nothing composes a ticket description inline.\n\nThe writer is not a formatter. It runs a codebase-research pass first, so its\ntickets cite the files, functions, and extension points a change actually\ntouches. A description written inline skips that pass, and the difference shows\nup two steps later: plan generation and implementation both ground themselves in\nthe ticket body, so a body with no code references produces a plan with no code\nreferences.\n\n\"The ticket is already well specified\" is not a reason to skip the writer. A\nwell-specified *request* is the writer's input, not a substitute for its output.\n\n### 2. Size toward L\n\nSize each ticket by file-touch breadth and depth plus rough lines of code\nchanged:\n\n| Band | Files | LOC |\n| --- | --- | --- |\n| `S` | 1–2 | `<~80` |\n| `M` | ~3–8 | ~80–400 |\n| `L` | ~8–15 | ~400–900 |\n| `XL` | >15 | `>~900` |\n\nPriority: **L (target) → XL (when the work does not fit in L) → M (third choice)\n→ S (only when unavoidable)**.\n\nThe target is L because the Bridge implementation tooling works best on\nindependently implementable vertical slices. What matters as much as the target\nis the **direction you move when a slice misses it**: upward, not downward.\n\nA slice that will not fit in L becomes **one XL ticket**, not two L ones. Split\nonly when the slice is genuinely two independent pieces of work — never merely to\nland inside a band. Fragmenting a coherent slice to fit is the failure this\nladder exists to prevent: every extra ticket is another worktree, another PR,\nanother rebase, and another chance for two workers to touch the same file, and\nBridge's grooming process is overkill on small tickets. Fewer, larger slices\nspend less of the run's budget on coordination.\n\nThis applies equally to a standalone ticket and to an epic child. There is no\nsize ceiling on a child that a lone ticket does not also have.\n\n`M` is where you land when the work genuinely is three to eight files — not\nsomewhere to retreat to in order to avoid an XL. `S` is likewise not forbidden:\nit is simply what you reach when the work genuinely is one or two files. A\nsingle-file trivial fix is `S` arrived at through the normal path. It is not an\nexception to anything, and it does not license skipping the writer.\n\n**Beyond roughly 40 files or ~3000 LOC, split anyway.** XL is the preferred\noverflow, not an unbounded one. Past that point review turnaround and rebase cost\ndominate the run's budget, and a review that wedges holds the gate to its full\nretry ceiling before anyone notices. That is a real bound, not a preference — and\nit is high enough that reaching it means the work really is two things.\n\n### 3. Group at three\n\nThree or more implementable tickets is an epic. The surface proposes an epic\nparent plus an **ordered child manifest**, and resolves its own approval gate\nbefore anything is created.\n\nOne or two tickets are ordinary siblings: no epic parent, no manifest. The\nthreshold is exactly three — not \"several\", not \"a lot\".\n\nThe manifest carries, per child: the boundary of its scope, its size band,\n`depends_on` (hard prerequisites that must land first), `recommended_after` (soft\nsequencing preferences that are not blockers), and a one-line order rationale.\nHard prerequisites and soft sequencing stay strictly separate, because the\nrecommended implementation order is derived from them and conflating the two\nproduces a serialized order where a parallel one was available.\n\nApproval follows each surface's **existing** attended/unattended rule. Nothing\nhere introduces a new gate policy: `/explore-ticket` requires an explicit\naffirmative because creation is irreversible, and the recipe path gates on the\npipeline's own auto-approval variable. What is *not* conditional is the grouping\nitself — an unattended run still produces the epic; only the gate's behavior\nvaries.\n\nDecomposition happens **once**. The pass that decides the split freezes the\nmanifest; body rendering then fans out one writer invocation per entry against\nthat frozen manifest. A rendering invocation may not re-split, merge, reorder,\nrenumber, or rescope. Two independent decisions about the same split disagree,\nand the disagreement surfaces as children that overlap or contradict their\nparent.\n\n### 4. Hand off to exactly one conductor\n\nAn epic handoff names exactly one conductor entry point: `drive-epic`.\n\nBridge currently has two conductors — the v2 server-side engine and the LLM\nconductor pilot — and a standing rule that they must never operate on the same\nepic, because two transition authorities on one epic wedge it permanently. Asking\na model to pick correctly every time is not a control. `drive-epic` makes the\nchoice structural instead: it reads conductor readiness and routes to the one\npath the project can actually run, so no prompt names either underlying conductor\nand no prompt can present both.\n\nTwo conductors is a transitional state. When one is eliminated, `drive-epic` is\nthe only thing that changes — no prompt, bundled doc, command mirror, or posture\ntest moves.\n\n## The closed exception list\n\nExactly three exceptions permit departing from the rules above. Invoking one\nrequires **no announcement** — the departure is silent by design, because a\nmandatory announcement would be one more instruction to drift from, and the cost\nof silence was weighed and accepted.\n\n| Id | Exception | Objective trigger | Bypasses |\n| --- | --- | --- | --- |\n| **E1** | External-tracker mirroring | A recorded upstream identifier exists and its granularity is contractual | Sizing and the epic threshold |\n| **E2** | Discovery-only spike | No committed production-code deliverable | Sizing only — **not** drafting through the writer |\n| **E3** | Authorized incident containment | Tied to an active incident record, not to schedule pressure | Sizing and the epic threshold |\n\nEach trigger is objective: an identifier that exists, a deliverable that is\nabsent, an incident record that is open. None of them is a judgement about how\nthe work feels.\n\n### The list is closed\n\nAnything outside the three rows above is an **escalation to the operator**, not a\njudgement call. The following are explicitly refused as grounds for departure:\n\n- a single-file trivial fix — that is `S` reached through the normal path;\n- generic time pressure;\n- \"the request is already well specified\";\n- \"it would be faster without the writer\";\n- developer discretion;\n- \"it's just a minor refactor\";\n- running unattended;\n- context limits;\n- \"this is hard to decompose\" — XL is the normal overflow, so that is the\n  ordinary path and not a departure.\n\n**Writer unavailability escalates.** It never silently authorizes inline\ndrafting. A surface that cannot reach `jira-ticket-writer` stops and says so.\n\n## Isolation binding for shared-state test support\n\nA ticket that builds or changes test support which resets shared state — a\nharness, a fixture, a reset helper, anything that truncates, drops, or\nreinitializes state another process or another run can also read or write —\nmust state its isolation binding as a requirement: which database, directory,\nor other shared resource the reset targets, and how the ticket's own\ndeliverable proves that target's identity before it destroys anything.\n\nThis doctrine exists because BAPI-1006 shipped a conductor integration-test\nharness with nothing in its ticket stating what the harness's destructive\nreset was bound to, and a v2 worker dispatched to build it truncated the\noperator's operational `bridgeapi` database (Architecture Miss 28). The\ncontainment-hazard classifier this repository runs at planning time\n(`api/library/github/workflow_planning_prediction.py`) can flag such a ticket\nfrom its text, but the flag is advisory — it surfaces the hazard before\ndispatch, it does not prevent a destructive worker on its own. Stating the\nisolation binding in the ticket itself is the durable requirement; treat this\nas an authoring-posture rule, not as runtime enforcement.\n\n## Accepted trade-off: silent departure is unobservable\n\nObservability was deliberately dropped when this posture was ratified. A model\nmay invoke E1, E2, or E3 without recording that it did, so posture drift is only\ndetectable through ticket quality — not through a log, a counter, or a report.\n\nThis is known and accepted. The alternative was another mandatory instruction on\nevery surface, and an instruction that is skipped silently is worse than one that\ndoes not exist: it reads as coverage while providing none.\n\n## Why duplication, not a shared include\n\nCommands, agents, instructions, and docs have four separate build paths in this\nrepository and no shared compiler. Introducing a generated include step to share\none block would mean a fifth build path, a placeholder that can go unresolved,\nand a failure mode where a carrier ships with the placeholder text still in it.\n\nMarker-delimited duplication plus one byte-equality test is the right mechanism\nat this scale. The test reads the canonical sources directly — never the\ngenerated command mirrors, whose byte-identity the command tests already cover —\nand permits **no** per-surface variation. Any drift, down to a single byte, fails.\n\n## A fresh install inherits this\n\nNo configuration step, no server call. The posture reaches a new project through\nthe packaged bundles that `--init` scaffolds:\n\n- `COMMANDS` (`mcp_server/src/commands.generated.ts`) — carries\n  `commands/src/explore-ticket.md`;\n- `AGENTS` (`mcp_server/src/agents.generated.ts`) — carries\n  `agents/src/jira-ticket-writer.md`, including the compressed posture line in\n  its `description:` frontmatter;\n- `INSTRUCTIONS` (`mcp_server/src/pipelines.generated.ts`) — carries the\n  canonical source and both decomposition instructions;\n- `DOCS` (`mcp_server/src/docs.generated.ts`) — carries this document.\n\nThe compressed frontmatter line matters more than its size suggests: agent\ndescriptions land in every session's system prompt with no file read and no\n`tools/list` cost, so it is the entire bare-chat coverage story.\n\n## Worked examples\n\n**One ticket.** \"Add a `--json` flag to `doctor`.\" Two files and a test, ~90 LOC.\nThat is `M`. One ticket, drafted by the writer, no epic, no manifest, no\nconductor handoff.\n\n**Two tickets.** \"Add rate limiting to the LLM client, and surface the limit in\nthe config UI.\" Backend and frontend are independently implementable and land\nseparately: two ordinary siblings. Still no epic — the threshold is three.\n\n**Four tickets → an epic.** \"Make local ticket mode a first-class system.\"\nDecomposition freezes a parent plus four children, each `L`, with `depends_on`\nnaming the one child that must land first. The full manifest goes to the approval\ngate; on approval, four writer invocations render four bodies against their\nfrozen entries; creation follows `upload-epic-hierarchy.md`; the handoff names\n`drive-epic` and nothing else.\n\n**A child that outgrows `L`.** A proposed child comes out at 19 files. It ships\nas one `XL` child. Do not split it into two `L` children to make it fit — the\nslice is one coherent piece of work, and halving it buys a second worktree, a\nsecond PR, and a rebase between them in exchange for nothing. Split only if the\n19 files really are two independent deliverables.\n\n**Past the ceiling.** A proposed ticket comes out at 60 files and ~5000 LOC.\nThat is over the bound, so it splits — but into the largest coherent pieces\navailable, not into a swarm. Two `XL` tickets is the right answer here; six `M`\nones is not.\n"
+    "docs/bridge-ticket-authoring.md": "# Bridge ticket-authoring posture\n\nBridge has several surfaces that can create a ticket. Without a shared posture\neach one behaves differently, and the most-used surface carries none of the\nmaintainer's preferences at all. This document is the deep reference behind the\nshort posture block that every one of those surfaces carries verbatim.\n\nThe block itself is short on purpose — it competes for attention inside prompts\nthat are already long. Everything that explains *why* lives here.\n\n## The canonical block\n\nThis file **is** the canonical source. The marker-delimited block below is\nduplicated byte-identically onto every carrier — every surface that decides\nticket shape holds these exact bytes, so no surface can quietly drift into its\nown house style.\n\nCarriers (all four hold the block verbatim):\n\n- `agents/src/jira-ticket-writer.md` — the writer itself, plus a compressed\n  posture line in its `description:` frontmatter, which is the only coverage a\n  bare-chat session gets with no file read and no `tools/list` cost.\n- `commands/src/explore-ticket.md` — Stage 9, the most-used authoring surface.\n- `mcp_server/instructions/decompose-epic-candidate.md` — the `idea-to-ticket`\n  decomposition step.\n- `mcp_server/instructions/decompose-epic.md` — the `plan-epic` decomposition\n  step.\n\nEdit the block here, copy it verbatim to each carrier, and let\n`tests/pytest/mcp_server/test_ticket_authoring_posture_assets.py` prove it\nlanded. That test permits **no** per-surface variation.\n\n<!-- BEGIN BRIDGE TICKET-AUTHORING POSTURE -->\n<!-- Canonical source: docs/bridge-ticket-authoring.md.\n     This block is duplicated byte-identically onto every carrier. Never edit a\n     copy: edit the canonical source and re-copy it verbatim. A cross-surface\n     byte-equality test fails the build if any copy drifts by a single byte. -->\n\n## Ticket-authoring posture\n\nDeep reference: `docs/bridge-ticket-authoring.md`.\n\n**Draft through the writer.** Every ticket body — an epic parent, an epic child,\nand an ordinary sibling alike — is drafted by the `jira-ticket-writer` agent\nbefore `create_ticket` is called. Do not compose a ticket description inline.\n\n**Size the work.** Size each ticket by file-touch breadth and depth plus rough\nlines of code (LOC) changed:\n\n- `S = 1-2 files / <~80 LOC`\n- `M = ~3-8 files / ~80-400 LOC`\n- `L = ~8-15 files / ~400-900 LOC`\n- `XL = >15 files / >~900 LOC`\n\nTarget size priority: **L (target) -> XL (when the work does not fit in L) -> M\n(third choice) -> S (only when unavoidable)**. This applies equally to a\nstandalone ticket and to an epic child.\n\nAim each slice at L. When one will not fit, grow it to XL rather than splitting\nit — split only when the slice is genuinely two independent pieces of work,\nnever merely to land inside a band. Bridge's grooming and implementation process\nhandles a large vertical slice well and is overkill on small ones: every extra\nticket is another worktree, another PR, another rebase, and another chance for\ntwo workers to touch the same file. Reach for M because the work genuinely is\nthat size, not to avoid an XL.\n\nBeyond roughly 40 files or ~3000 LOC, split anyway. Past that point review\nturnaround and rebase cost dominate the run's budget, and a review that wedges\nholds the gate to its full retry ceiling before anyone notices.\n\n**Group at three.** Three or more implementable tickets is an epic: propose an\nepic parent plus an ordered child manifest, and resolve this surface's own\napproval gate before anything is created. One or two tickets are ordinary\nsiblings — no epic parent, no manifest. The threshold is exactly three.\n\n**Hand off once.** An epic handoff names exactly one conductor entry point,\n`drive-epic`, which selects the runnable path itself. Never present a choice\nbetween conductors.\n\n**Departure is closed-list only.** These three exceptions, and no others, permit\ndeparting from the rules above. Invoking one requires no announcement.\n\n- **E1 External-tracker mirroring** — a recorded upstream identifier exists and\n  its granularity is contractual. Bypasses sizing and the epic threshold.\n- **E2 Discovery-only spike** — no committed production-code deliverable.\n  Bypasses sizing only; does not bypass drafting through the writer.\n- **E3 Authorized incident containment** — tied to an active incident record,\n  not to schedule pressure. Bypasses sizing and the epic threshold.\n\nThe list is closed. Anything outside it is an escalation to the operator, not a\njudgement call. Explicitly refused as grounds for departure: a single-file\ntrivial fix (that is `S` reached through the normal path, not an exception),\ngeneric time pressure, \"already well specified\", \"faster without the writer\",\ndeveloper discretion, minor refactor, unattended mode, context limits, and \"hard\nto decompose\" (XL is the normal overflow, so that is the ordinary path and not a\ndeparture). Writer unavailability escalates; it never silently authorizes inline\ndrafting.\n\n<!-- END BRIDGE TICKET-AUTHORING POSTURE -->\n\nThe rest of this document is the rationale the block is deliberately too short to\ncarry.\n\n## Decision: Jira ticket authoring ships through the Jira Ticket Writer (BAPI-900)\n\nBridge ships two very different kinds of ticket-authoring surface, and customers\nneed to know which one they actually have.\n\n**Shipped customer surface.** A customer project gets the `jira-ticket-writer`\nagent — the same writer this posture requires every ticket body to go through —\nplus the agent-directed capability to revise an existing ticket's description.\nAsk your agent to draft a ticket with the Jira Ticket Writer, and ask your agent\nto update an existing ticket's description when it needs revising. Both reach a\ncustomer project because they are packaged: the writer through `AGENTS`\n(`mcp_server/src/agents.generated.ts`) and the description-update path through\nthe registered `update_ticket_description` / `request_ticket_update` MCP tools.\n\n**Repository-local workflows.** `.claude/commands/write-ticket.md` and\n`.claude/commands/update-ticket.md` are bridge-api's own repository-maintenance\ncommands. They are **not** scaffolded into a customer project by `--init`, have\nno `commands/src/` source, and have no generated Cursor or `mcp_server/`\nmirror — deliberately, not by omission. A customer asking their agent to run\nthe write-ticket or update-ticket slash command will not find either one,\nbecause neither ships.\n\n**Why (Option B, not a promotion to shipped status).** The Jira Ticket Writer is\nalready the packaged drafting surface this posture mandates, so shipping\n`write-ticket.md` as a second drafting entry point would duplicate it. More\nimportantly, `write-ticket.md` is today an autonomous, single-ticket, no-halt\npipeline (\"No human confirmation gates — run end-to-end\") with no decomposition\nstep and no approval gate — it cannot honor the \"group at three\" epic rule or\nthe epic approval gate this posture requires, because it was never built to\npropose an epic at all. Promoting it to a shipped surface without that redesign\nwould ship a customer-facing command that silently violates this file's own\nposture. Until that redesign happens, `write-ticket.md` and `update-ticket.md`\nstay repository-local, and every packaged surface directs customers to the Jira\nTicket Writer and to agent-directed description updates instead.\n\n\n## The four rules\n\n### 1. Draft through `jira-ticket-writer`\n\nEvery ticket body is drafted by the `jira-ticket-writer` agent before\n`create_ticket` is called — an epic parent, an epic child, and an ordinary\nsibling alike. Nothing composes a ticket description inline.\n\nThe writer is not a formatter. It runs a codebase-research pass first, so its\ntickets cite the files, functions, and extension points a change actually\ntouches. A description written inline skips that pass, and the difference shows\nup two steps later: plan generation and implementation both ground themselves in\nthe ticket body, so a body with no code references produces a plan with no code\nreferences.\n\n\"The ticket is already well specified\" is not a reason to skip the writer. A\nwell-specified *request* is the writer's input, not a substitute for its output.\n\n### 2. Size toward L\n\nSize each ticket by file-touch breadth and depth plus rough lines of code\nchanged:\n\n| Band | Files | LOC |\n| --- | --- | --- |\n| `S` | 1–2 | `<~80` |\n| `M` | ~3–8 | ~80–400 |\n| `L` | ~8–15 | ~400–900 |\n| `XL` | >15 | `>~900` |\n\nPriority: **L (target) → XL (when the work does not fit in L) → M (third choice)\n→ S (only when unavoidable)**.\n\nThe target is L because the Bridge implementation tooling works best on\nindependently implementable vertical slices. What matters as much as the target\nis the **direction you move when a slice misses it**: upward, not downward.\n\nA slice that will not fit in L becomes **one XL ticket**, not two L ones. Split\nonly when the slice is genuinely two independent pieces of work — never merely to\nland inside a band. Fragmenting a coherent slice to fit is the failure this\nladder exists to prevent: every extra ticket is another worktree, another PR,\nanother rebase, and another chance for two workers to touch the same file, and\nBridge's grooming process is overkill on small tickets. Fewer, larger slices\nspend less of the run's budget on coordination.\n\nThis applies equally to a standalone ticket and to an epic child. There is no\nsize ceiling on a child that a lone ticket does not also have.\n\n`M` is where you land when the work genuinely is three to eight files — not\nsomewhere to retreat to in order to avoid an XL. `S` is likewise not forbidden:\nit is simply what you reach when the work genuinely is one or two files. A\nsingle-file trivial fix is `S` arrived at through the normal path. It is not an\nexception to anything, and it does not license skipping the writer.\n\n**Beyond roughly 40 files or ~3000 LOC, split anyway.** XL is the preferred\noverflow, not an unbounded one. Past that point review turnaround and rebase cost\ndominate the run's budget, and a review that wedges holds the gate to its full\nretry ceiling before anyone notices. That is a real bound, not a preference — and\nit is high enough that reaching it means the work really is two things.\n\n### 3. Group at three\n\nThree or more implementable tickets is an epic. The surface proposes an epic\nparent plus an **ordered child manifest**, and resolves its own approval gate\nbefore anything is created.\n\nOne or two tickets are ordinary siblings: no epic parent, no manifest. The\nthreshold is exactly three — not \"several\", not \"a lot\".\n\nThe manifest carries, per child: the boundary of its scope, its size band,\n`depends_on` (hard prerequisites that must land first), `recommended_after` (soft\nsequencing preferences that are not blockers), and a one-line order rationale.\nHard prerequisites and soft sequencing stay strictly separate, because the\nrecommended implementation order is derived from them and conflating the two\nproduces a serialized order where a parallel one was available.\n\nApproval follows each surface's **existing** attended/unattended rule. Nothing\nhere introduces a new gate policy: `/explore-ticket` requires an explicit\naffirmative because creation is irreversible, and the recipe path gates on the\npipeline's own auto-approval variable. What is *not* conditional is the grouping\nitself — an unattended run still produces the epic; only the gate's behavior\nvaries.\n\nDecomposition happens **once**. The pass that decides the split freezes the\nmanifest; body rendering then fans out one writer invocation per entry against\nthat frozen manifest. A rendering invocation may not re-split, merge, reorder,\nrenumber, or rescope. Two independent decisions about the same split disagree,\nand the disagreement surfaces as children that overlap or contradict their\nparent.\n\n### 4. Hand off to exactly one conductor\n\nAn epic handoff names exactly one conductor entry point: `drive-epic`.\n\nBridge currently has two conductors — the v2 server-side engine and the LLM\nconductor pilot — and a standing rule that they must never operate on the same\nepic, because two transition authorities on one epic wedge it permanently. Asking\na model to pick correctly every time is not a control. `drive-epic` makes the\nchoice structural instead: it reads conductor readiness and routes to the one\npath the project can actually run, so no prompt names either underlying conductor\nand no prompt can present both.\n\nTwo conductors is a transitional state. When one is eliminated, `drive-epic` is\nthe only thing that changes — no prompt, bundled doc, command mirror, or posture\ntest moves.\n\n## The closed exception list\n\nExactly three exceptions permit departing from the rules above. Invoking one\nrequires **no announcement** — the departure is silent by design, because a\nmandatory announcement would be one more instruction to drift from, and the cost\nof silence was weighed and accepted.\n\n| Id | Exception | Objective trigger | Bypasses |\n| --- | --- | --- | --- |\n| **E1** | External-tracker mirroring | A recorded upstream identifier exists and its granularity is contractual | Sizing and the epic threshold |\n| **E2** | Discovery-only spike | No committed production-code deliverable | Sizing only — **not** drafting through the writer |\n| **E3** | Authorized incident containment | Tied to an active incident record, not to schedule pressure | Sizing and the epic threshold |\n\nEach trigger is objective: an identifier that exists, a deliverable that is\nabsent, an incident record that is open. None of them is a judgement about how\nthe work feels.\n\n### The list is closed\n\nAnything outside the three rows above is an **escalation to the operator**, not a\njudgement call. The following are explicitly refused as grounds for departure:\n\n- a single-file trivial fix — that is `S` reached through the normal path;\n- generic time pressure;\n- \"the request is already well specified\";\n- \"it would be faster without the writer\";\n- developer discretion;\n- \"it's just a minor refactor\";\n- running unattended;\n- context limits;\n- \"this is hard to decompose\" — XL is the normal overflow, so that is the\n  ordinary path and not a departure.\n\n**Writer unavailability escalates.** It never silently authorizes inline\ndrafting. A surface that cannot reach `jira-ticket-writer` stops and says so.\n\n## The spike ticket format (BAPI-986)\n\nA spike ticket defines a finding to be produced, not code to be written, so it\ngets its own body shape. This is a second **format**, not a fourth exception:\nthe writer still drafts it, the sizing ladder still applies, and E2 still governs\nwhether the posture's sizing rule is bypassed at all.\n\n### Who chooses, and on what\n\nThe run manifest's `scope` chooses, and it is resolved once, upstream, in\n`mcp_server/instructions/preflight-and-readiness.md`. The writer receives that\nvalue and never decides it. Only `scope: spike` selects the spike format.\n\nThe trigger is E2's exact objective condition — **no committed production-code\ndeliverable**. A deliverable that is absent, not a judgement about how the work\nfeels. Every other case produces the ordinary code-ticket format:\n\n- `scope: task` and `scope: epic_candidate`;\n- a missing scope value;\n- a malformed or unrecognized scope value;\n- a standalone writer invocation with no resolved spike scope;\n- any ambiguity.\n\nCode is the default **in code, not in prose**: it is what every unresolved path\nalready produces, so no one has to remember a rule to get it.\n\n### The five body sections\n\nA spike draft's substantive body is exactly these five, in order:\n\n1. `## Question` — the single question the investigation must answer.\n2. `## Scope` — the systems, code paths, data, and behavior in bounds.\n3. `## Out-of-scope` — what it will not examine, stated explicitly.\n4. `## What the findings must answer (the deliverable)` — names an inspectable\n   findings artifact at a specific repository path, and states what that artifact\n   must contain: the decisions it settles, the evidence it cites, the\n   recommendations it makes, and the unresolved risks it records. This is the\n   spike's analogue of Acceptance Criteria — a reviewer holds the finished\n   artifact against it to tell whether the spike is done.\n5. `## Which related tickets consume the finding` — names real consumer tickets\n   by key, or the literal `none yet`. Never an invented key.\n\nThose five are the spike-specific **body** sections. They are not the whole\ndraft. The following remain mandatory structural metadata, identical to a code\ndraft, and are not additional spike sections:\n\n- the `# [Title]` heading;\n- the execution-class marker line (below);\n- a `## Regression Completeness Notes` block when the gated regression pass\n  applies;\n- the trailing `## Materials & Access` section, always last.\n\nThe code-ticket structure — Summary, Requirements, Acceptance Criteria,\nMaterials & Access — is unchanged, and a code draft carries no marker.\n\n### The execution-class marker\n\nA spike draft carries exactly one canonical marker line, alone on its own line,\nimmediately after the title and before `## Question`:\n\n```markdown\n# [Concise Title Describing the Investigation]\n<!-- bridge:execution-class=investigation -->\n\n## Question\n```\n\nIt appears **exactly once**, never in a code-format ticket, and never\nillustratively inside a generated ticket body — not in prose, not in a fence,\nnot in backticks. Duplicates do not reinforce it: a second occurrence makes the\ndescription ambiguous and the parser discards the whole thing, leaving no signal.\n\n**It renders as visible text.** Bridge converts the description from Markdown to\nAtlassian Document Format, and ADF has no comment node, so the marker becomes one\nvisible line in the Jira description rather than a hidden comment. The exact\ntoken survives conversion and stays parseable from the stored description, which\nis what it is for. The placement immediately after the title is therefore an\neditorial choice as much as a parsing one.\n\n**It is a weak hint.** One non-authoritative input alongside the existing weak\nJira issue-type signal. It never overrides the five-way ticket-type\nclassification and never bypasses a human gate. A classifier verdict that\ncontradicts it wins, and the disagreement is reported rather than reconciled.\n\nThe marker's shape lives in exactly one runtime place —\n`parse_execution_class_marker` in\n`src/python/llms/agents/planner_agent/ticket_evaluator/execution_class_marker_utils.py`,\nwhich imports the `code`/`investigation` vocabulary from BAPI-980's constants in\n`api/models/epic_run.py` rather than redeclaring it. The literal in this document\nand in `agents/src/jira-ticket-writer.md` is pinned against that runtime constant\nby test, because Markdown cannot import a Python value.\n\n### The marker survives to the ticket record\n\nThe single-ticket path creates the Jira issue from `slim_description`; the full\ndraft is only an attachment. A marker preserved solely in the attachment would\nleave the ticket record with no signal at all. Two rules close that:\n\n- `mcp_server/instructions/draft-and-critique.md` carries the title and marker\n  into `slim_description` in their original order, exactly once, and exempts that\n  one literal from the forbidden-raw-HTML hygiene rule that would otherwise strip\n  it. A `task` draft has no exemption, and slimming must not synthesize a marker.\n- `mcp_server/instructions/upload-and-track.md` passes `slim_description`\n  unchanged as `create_ticket`'s `description`, without stripping, reconstructing,\n  relocating, duplicating, or validating the marker.\n\n`create_ticket` gains no execution-class parameter and the MCP tool schema is\nunchanged: the marker rides in `description` and nowhere else.\n\n### Post-creation marker loss is out of scope\n\nA later description rewrite can drop the marker. `ticket_store_lib.update_ticket`\nforwards a full replacement description and the Jira backend re-renders all of it\nthrough `render_adf`, so anything a rewrite omits is simply gone — there is no\nmerge. Preserving the marker across rewrites would mean auditing every\ndescription-rewriting surface, which is excluded here.\n\nThis is a named, owned gap rather than an unstated one: preservation belongs to\nthe downstream slice that enables investigation routing. No local design record\nnames that slice yet, so its ownership is recorded here as an unresolved\ndownstream discovery rather than assigned to an invented slice name.\n\n## Residual risks and their operational contracts\n\nFour limitations ship with the spike format. Each is stated as detection,\ncontainment, and escalation, because a residual-risk note without those three\nreads as coverage while providing none.\n\n### Incorrect E1/E2/E3 invocation\n\n- **Detection**: manual ticket review only. There is no log, counter, or report\n  (see the accepted trade-off below).\n- **Containment**: the objective selection rule — any ambiguity produces a code\n  ticket — plus the marker's non-authority over classification and every human\n  gate.\n- **Escalation**: suspected misuse goes to the authoring-workflow owner.\n\n### Class observability does not cover departure invocation\n\nThe marker makes a spike's intended execution **class** observable. It does not\nmake E1/E2/E3 posture-departure **invocation** observable; that remains silent by\naccepted design, and the accepted trade-off below is unchanged by this slice.\n\n- **Detection**: none for invocation, by design. Ticket review is the only signal.\n- **Containment**: the closed exception list itself — anything outside those\n  three rows is an escalation, not a judgement call.\n- **Escalation**: the authoring-workflow owner, as above.\n\n### Premature routing on the marker\n\nMarker-bearing tickets exist before any consumer does. Nothing routes on the\nmarker yet, and the guard for that is **structural, not a feature flag** — no\nsuch flag exists, and naming an imaginary control would be exactly the failure\nthe accepted trade-off below warns about.\n\n- **Detection**: the absence of any marker reader outside the parse/normalize\n  helper and the disagreement observer. A static test pins that set, so the first\n  premature consumer fails at review time.\n- **Containment**: BAPI-980 seeds every run node `execution_class = 'code'` and\n  exposes no caller-controlled `investigation` override anywhere — not on the DAL\n  seed signature, not on a Pydantic request model, not on an MCP input. No code\n  path writes `investigation`.\n- **Escalation**: any proposal to consume the field in runtime conductor behavior\n  goes to the Conductor owner before implementation, per BAPI-980's decision D10;\n  any discovered marker-based routing is a release-blocking regression on that\n  same path. Enabling investigation routing belongs to the downstream epic\n  rollout owner, once the complete path and its human gate exist.\n\n### Marker/classifier disagreement\n\n- **Detection**: the reserved structured-log event\n  `ticket_classification_event=execution_class_marker_disagreement`, emitted at\n  warning level when an investigation marker meets a code-facing classifier\n  verdict. Every `evaluate_ticket_type` entry point compares, so the signal\n  covers the ordinary Bridge classification path and not only the estimator\n  backfill; a cached verdict is not a classification and is not compared.\n  Persistent or high-volume disagreement is surfaced by querying that reserved\n  key through the existing logging/Sentry workflow.\n- **Containment**: the comparison is non-authoritative. The classifier verdict is\n  persisted and returned exactly as produced, whether or not an event fires.\n- **Escalation**: the event is **diagnostic-only** and the Bridge platform team\n  owns it operationally. No alert rule, threshold, or paging behavior ships with\n  it; that is net-new work belonging to the slice that enables routing. The field\n  and redaction contract lives in\n  `docs/claude/jira-optional-ticket-storage.md`, not here.\n\n## Isolation binding for shared-state test support\n\nA ticket that builds or changes test support which resets shared state — a\nharness, a fixture, a reset helper, anything that truncates, drops, or\nreinitializes state another process or another run can also read or write —\nmust state its isolation binding as a requirement: which database, directory,\nor other shared resource the reset targets, and how the ticket's own\ndeliverable proves that target's identity before it destroys anything.\n\nThis doctrine exists because BAPI-1006 shipped a conductor integration-test\nharness with nothing in its ticket stating what the harness's destructive\nreset was bound to, and a v2 worker dispatched to build it truncated the\noperator's operational `bridgeapi` database (Architecture Miss 28). The\ncontainment-hazard classifier this repository runs at planning time\n(`api/library/github/workflow_planning_prediction.py`) can flag such a ticket\nfrom its text, but the flag is advisory — it surfaces the hazard before\ndispatch, it does not prevent a destructive worker on its own. Stating the\nisolation binding in the ticket itself is the durable requirement; treat this\nas an authoring-posture rule, not as runtime enforcement.\n\n## Accepted trade-off: silent departure is unobservable\n\nObservability was deliberately dropped when this posture was ratified. A model\nmay invoke E1, E2, or E3 without recording that it did, so posture drift is only\ndetectable through ticket quality — not through a log, a counter, or a report.\n\nThis is known and accepted. The alternative was another mandatory instruction on\nevery surface, and an instruction that is skipped silently is worse than one that\ndoes not exist: it reads as coverage while providing none.\n\n## Why duplication, not a shared include\n\nCommands, agents, instructions, and docs have four separate build paths in this\nrepository and no shared compiler. Introducing a generated include step to share\none block would mean a fifth build path, a placeholder that can go unresolved,\nand a failure mode where a carrier ships with the placeholder text still in it.\n\nMarker-delimited duplication plus one byte-equality test is the right mechanism\nat this scale. The test reads the canonical sources directly — never the\ngenerated command mirrors, whose byte-identity the command tests already cover —\nand permits **no** per-surface variation. Any drift, down to a single byte, fails.\n\n## A fresh install inherits this\n\nNo configuration step, no server call. The posture reaches a new project through\nthe packaged bundles that `--init` scaffolds:\n\n- `COMMANDS` (`mcp_server/src/commands.generated.ts`) — carries\n  `commands/src/explore-ticket.md`;\n- `AGENTS` (`mcp_server/src/agents.generated.ts`) — carries\n  `agents/src/jira-ticket-writer.md`, including the compressed posture line in\n  its `description:` frontmatter;\n- `INSTRUCTIONS` (`mcp_server/src/pipelines.generated.ts`) — carries the\n  canonical source and both decomposition instructions;\n- `DOCS` (`mcp_server/src/docs.generated.ts`) — carries this document.\n\nThe compressed frontmatter line matters more than its size suggests: agent\ndescriptions land in every session's system prompt with no file read and no\n`tools/list` cost, so it is the entire bare-chat coverage story.\n\n## Worked examples\n\n**One ticket.** \"Add a `--json` flag to `doctor`.\" Two files and a test, ~90 LOC.\nThat is `M`. One ticket, drafted by the writer, no epic, no manifest, no\nconductor handoff.\n\n**Two tickets.** \"Add rate limiting to the LLM client, and surface the limit in\nthe config UI.\" Backend and frontend are independently implementable and land\nseparately: two ordinary siblings. Still no epic — the threshold is three.\n\n**Four tickets → an epic.** \"Make local ticket mode a first-class system.\"\nDecomposition freezes a parent plus four children, each `L`, with `depends_on`\nnaming the one child that must land first. The full manifest goes to the approval\ngate; on approval, four writer invocations render four bodies against their\nfrozen entries; creation follows `upload-epic-hierarchy.md`; the handoff names\n`drive-epic` and nothing else.\n\n**A child that outgrows `L`.** A proposed child comes out at 19 files. It ships\nas one `XL` child. Do not split it into two `L` children to make it fit — the\nslice is one coherent piece of work, and halving it buys a second worktree, a\nsecond PR, and a rebase between them in exchange for nothing. Split only if the\n19 files really are two independent deliverables.\n\n**Past the ceiling.** A proposed ticket comes out at 60 files and ~5000 LOC.\nThat is over the bound, so it splits — but into the largest coherent pieces\navailable, not into a swarm. Two `XL` tickets is the right answer here; six `M`\nones is not.\n"
 };

package/build/doctor.js

@@ -28,9 +28,9 @@ import { createBridgeApiUrls } from "./bridge-api-urls.js";
 import { probeToolSurface } from "./tool-surface-gating.js";
 import { resolveBapiCredentials } from "./credential-store.js";
 import { resolveConductorBridgeApiAccess } from "./conductor/bridge-api-client.js";
-import { getLiveRepositoryConductors, getParseDispatcherHealth, } from "./conduct-epic/bridge-client.js";
-import { resolveConductEpicStateDirectory } from "./conduct-epic/checkpoint-store.js";
-import { isConductEpicLockOwnerAlive, parseConductEpicLock, } from "./conduct-epic/lock.js";
+import { getLiveRepositoryConductors, getParseDispatcherHealth, } from "./implement-epic/bridge-client.js";
+import { resolveConductEpicStateDirectory } from "./implement-epic/checkpoint-store.js";
+import { isConductEpicLockOwnerAlive, parseConductEpicLock, } from "./implement-epic/lock.js";
 import { resolveRequiredStartTicketsRepoName } from "./start-tickets-repo.js";
 import { collectWorkerContainmentDiagnostic, formatWorkerContainmentDiagnosticReport, } from "./worker-containment-diagnostic.js";
 import { BRIDGE_PACKAGE_NAME, describeLauncherReason, DUPLICATE_REGISTRATION_GUIDANCE, inspectLauncherConfigs, parseLauncherPin as parseSharedLauncherPin, } from "./launcher-config-inspection.js";
@@ -42,6 +42,7 @@ import { executorLaunchdDirForHome, executorSystemdDirForHome, executorIdFromLau
 import { DEFAULT_BAPI_BASE_URL } from "./executor/credentials.js";
 import { detectClaudeLogin, formatClaudeLoginAdvisory } from "./claude-login.js";
 import { validateBranchName } from "./base-ref.js";
+import { readPlaneManifest } from "./plane/manifest.js";
 import { validateTicketKey } from "./ticket-key-utils.js";
 import { resolveBranchForTicket } from "./worktree-core.js";
 import { diagnoseStaleWorktreeBranches, formatStaleWorktreeDiagnosticReport, } from "./stale-worktree-doctor.js";
@@ -145,7 +146,7 @@ export function getDoctorUsage() {
         "",
         "Conductor ledger / native-module diagnostics (the SQLite ledger's native",
         "binding load status and Node-version skew) live under a separate command:",
-        "  conductor doctor",
+        "  epic-implementer doctor",
         "That command is likewise strictly read-only — it does not install, rebuild,",
         "migrate, or write ledger files.",
         "",
@@ -161,6 +162,13 @@ export function getDoctorUsage() {
         "deletes a branch, or repairs any git state, and never changes the exit code.",
         "Without --stale-branch it runs no git probe at all and prints no section.",
         "",
+        "The 'operational advisories' section also reports RETIRED local drive helpers",
+        "(~/.local/bin/bapi-runtime-up, ~/.local/bin/bapi-drive) when they are still on",
+        "this machine (BAPI-1102). That is a PATH-PRESENCE check only: doctor does not",
+        "run, read, source, chmod, or delete either file, and cannot remove them for you",
+        "— they are outside this repository, so their removal is an operator step. The",
+        "row is advisory and never changes the exit code.",
+        "",
         "Exit code: 0 when all required prerequisites are present, non-zero otherwise.",
     ].join("\n");
 }
@@ -413,7 +421,7 @@ export function formatDoctorPrereqSection(platform, collection) {
         ? "Some prerequisites are missing — install the ones above manually, then re-run doctor."
         : "All required prerequisites are present.");
     // Advisory pointer only (BAPI-526): informational, independent of exit code.
-    lines.push("For conductor ledger/native-module diagnostics, run: conductor doctor");
+    lines.push("For conductor ledger/native-module diagnostics, run: epic-implementer doctor");
     return lines.join("\n");
 }
 /**
@@ -431,7 +439,7 @@ export function formatDoctorReport(platform, agent, collection) {
  * Inspect the selected agent's executor adapter.
  *
  * Probes the executable version (cheap, read-only) but NOT deny enforcement:
- * that probe spawns a real headless agent, and `conductor doctor` already owns
+ * that probe spawns a real headless agent, and `epic-implementer doctor` already owns
  * that diagnostic behind its own `--no-deny-probe` switch. Duplicating it here
  * would make a plain `doctor` run spawn an agent the operator did not ask for.
  */
@@ -1193,10 +1201,20 @@ export async function collectPlaneCredentialDiagnostic(deps) {
     // `formatClaudeLoginAdvisory`), not per-repo here. This section is now scoped
     // to exactly what `plane up` still refuses on for THIS repository: a resolvable
     // Bridge credential.
+    const launch = await resolvePlaneCredentialAt(deps, deps.cwd);
+    const attach = await collectPlaneAttachCredentialDiagnostic(deps);
+    return { ...launch, attach };
+}
+/**
+ * Resolve the repository identity at `root`, then probe its credential, keeping
+ * ONLY non-secret labels. Shared by the launch and attach halves so both ask the
+ * shared resolvers exactly the same way.
+ */
+async function resolvePlaneCredentialAt(deps, root) {
     const resolveRepo = deps.resolveRepoName ?? resolveRequiredStartTicketsRepoName;
     let repo = null;
     try {
-        const result = await resolveRepo({ env: deps.env, cwd: deps.cwd, readFile: deps.readFile });
+        const result = await resolveRepo({ env: deps.env, cwd: root, readFile: deps.readFile });
         if (result.ok)
             repo = result.repoName;
     }
@@ -1225,6 +1243,29 @@ export async function collectPlaneCredentialDiagnostic(deps) {
         kind: status.kind,
     };
 }
+/**
+ * The attach half (BAPI-1153): read the plane manifest once, and when it is
+ * valid resolve credentials scoped to the MANIFEST's repository root — the root
+ * `drive-epic` attaches with — never the shell's working directory alone.
+ * Read-only: no manifest, credential, or configuration is written.
+ */
+export async function collectPlaneAttachCredentialDiagnostic(deps) {
+    let read;
+    try {
+        read = await (deps.readPlaneManifest ??
+            ((root) => readPlaneManifest(root, { readFile: deps.readFile })))(deps.cwd);
+    }
+    catch {
+        read = { kind: "unreadable", error: "read failed" };
+    }
+    if (read.kind === "missing") {
+        return { manifest: "missing", repo: null, target: null, bridgeCredentialResolved: false };
+    }
+    if (read.kind !== "valid") {
+        return { manifest: "unvalidated", repo: null, target: null, bridgeCredentialResolved: false };
+    }
+    return { manifest: "valid", ...(await resolvePlaneCredentialAt(deps, read.manifest.repoRoot)) };
+}
 /** Render the plane readiness section. Advisory: never changes the exit code. */
 export function formatPlaneCredentialDiagnosticReport(diagnostic) {
     const lines = ["", "Conductor plane credentials (`plane up` — advisory)"];
@@ -1240,12 +1281,37 @@ export function formatPlaneCredentialDiagnosticReport(diagnostic) {
             "           A spawned shell never sees .mcp.json env — set BAPI_API_KEY here, or store\n" +
             "           it with `mcp-server credentials`.");
     }
+    const attach = diagnostic.attach;
+    if (attach !== undefined) {
+        // BAPI-1153 — attaching to a running plane (`drive-epic`).
+        if (attach.manifest === "missing") {
+            lines.push("  INFO     attach: no plane manifest is present, so there is no running plane to attach to.");
+        }
+        else if (attach.manifest === "unvalidated") {
+            lines.push("  WARN     attach: .bridge/plane/plane.json could not be validated, so drive-epic would\n" +
+                "           refuse to attach to it.");
+        }
+        else if (attach.repo === null) {
+            lines.push("  MISSING  attach: the Bridge repository identity could not be resolved at the running\n" +
+                "           plane's repository root. Set BAPI_REPO_NAME or add a valid .bridge/config there.");
+        }
+        else if (attach.bridgeCredentialResolved) {
+            lines.push(`  OK       attach: credential ${attach.target} resolves for the running plane's repository ` +
+                `(source: ${attach.source}).`);
+        }
+        else {
+            lines.push(`  MISSING  attach: credential ${attach.target}: NOT resolved for the running plane's\n` +
+                `           repository (${attach.kind}). drive-epic resolves attach credentials against\n` +
+                "           the plane manifest's repository root — set BAPI_API_KEY here, or store it with\n" +
+                "           `mcp-server credentials`.");
+        }
+    }
     lines.push("           Read-only: this section resolves an identity and probes a credential. It creates");
     lines.push("           no .bridge/plane/ directory, persists nothing, and starts no plane member.");
     return lines.join("\n");
 }
 /**
- * Collect conduct-epic readiness, read-only.
+ * Collect implement-epic readiness, read-only.
  *
  * The credential is resolved only to establish that it CAN be, and the resolved
  * access object is discarded immediately: only the repo name and a boolean
@@ -1357,14 +1423,14 @@ export async function collectConductEpicDiagnostic(deps) {
         locks,
     };
 }
-/** Render the conduct-epic section. Advisory: never changes the exit code. */
+/** Render the implement-epic section. Advisory: never changes the exit code. */
 export function formatConductEpicDiagnosticReport(diagnostic) {
-    const lines = ["", "conduct-epic readiness (advisory)"];
+    const lines = ["", "implement-epic readiness (advisory)"];
     lines.push(diagnostic.ghAuthenticated
         ? "  OK       gh: present and authenticated."
         : diagnostic.ghPresent
             ? "  MISSING  gh: present but NOT authenticated. Run `gh auth login`."
-            : "  MISSING  gh: not found on PATH. `conduct-epic init` and `status` need it.");
+            : "  MISSING  gh: not found on PATH. `implement-epic init` and `status` need it.");
     lines.push(diagnostic.worktrunkAvailable
         ? `  OK       Worktrunk: '${diagnostic.worktrunkBinary}' resolves.`
         : `  MISSING  Worktrunk: '${diagnostic.worktrunkBinary}' not found (honors BAPI_WORKTRUNK_BIN).`);
@@ -1383,7 +1449,7 @@ export function formatConductEpicDiagnosticReport(diagnostic) {
     }
     else if (!diagnostic.stateDirectoryReadable) {
         lines.push(`  SKIP     Checkpoint directory ${diagnostic.stateDirectory}: absent or unreadable\n` +
-            "           (normal before the first `conduct-epic init`).");
+            "           (normal before the first `implement-epic init`).");
     }
     else {
         lines.push(`  OK       Checkpoint directory ${diagnostic.stateDirectory}: readable, ` +
@@ -1413,11 +1479,29 @@ export function formatConductEpicDiagnosticReport(diagnostic) {
     lines.push("           lock, rewrites no checkpoint, and never changes the exit code.");
     return lines.join("\n");
 }
+/**
+ * The transitional local helpers BAPI-1102 retires.
+ *
+ * `~/.local/bin` scripts, never shipped in this package and not in this
+ * repository, so nothing here can delete them — removal is an OPERATOR step. What
+ * the repository CAN do is notice them and say so, which is the difference
+ * between a documented retirement and a silent one: an operator whose muscle
+ * memory still types `bapi-drive` would otherwise keep driving epics through a
+ * path that predates the scoped-lane bring-up, and diagnose the resulting
+ * unscoped run as a server problem.
+ *
+ * Relative to the home directory, joined at collection time so no absolute path
+ * is baked into the module.
+ */
+export const LEGACY_DRIVE_HELPER_RELATIVE_PATHS = [
+    ".local/bin/bapi-runtime-up",
+    ".local/bin/bapi-drive",
+];
 /**
  * Collect the operational advisories, read-only.
  *
  * Local pilot conductors are identified from the SAME checkpoint-directory and
- * lock inspection `conduct-epic readiness` uses — `parseConductEpicLock` plus the
+ * lock inspection `implement-epic readiness` uses — `parseConductEpicLock` plus the
  * injected liveness seam — never from the process table. Only a lock proven live
  * on THIS host counts; malformed, unreadable, dead, and remote-host locks are
  * excluded from the live set, with the indeterminate ones counted separately.
@@ -1514,7 +1598,30 @@ export async function collectOperationalAdvisories(deps) {
             conductorObservation = "observed";
         }
     }
-    return { dispatcher, conductorObservation, conductors, indeterminateLocks };
+    // BAPI-1102 — a pure path-presence check, using the SAME injected `stat` and
+    // `homedir` seams every other advisory here uses, so it stays deterministic
+    // under test and reaches no real filesystem in one. A `stat` that throws is
+    // "absent"; it is never retried, and a permission error is not reported as a
+    // finding, because "I could not stat it" is not evidence that a stale helper is
+    // in use.
+    const legacyDriveHelpers = [];
+    for (const relative of LEGACY_DRIVE_HELPER_RELATIVE_PATHS) {
+        const absolute = path.join(deps.homedir(), relative);
+        try {
+            await deps.stat(absolute);
+            legacyDriveHelpers.push(absolute);
+        }
+        catch {
+            /* absent, or unreadable — either way, nothing to report */
+        }
+    }
+    return {
+        dispatcher,
+        conductorObservation,
+        conductors,
+        indeterminateLocks,
+        legacyDriveHelpers,
+    };
 }
 /** Render the operational-advisories section. Advisory: never changes the exit code. */
 export function formatOperationalAdvisoryReport(diagnostic) {
@@ -1554,6 +1661,21 @@ export function formatOperationalAdvisoryReport(diagnostic) {
         lines.push(`           ${diagnostic.indeterminateLocks} local lock(s) could not be judged (remote host,\n` +
             "           malformed, or unreadable) and are excluded from the live count.");
     }
+    // BAPI-1102. A WARN, never a failure, and deliberately separate from every
+    // readiness signal above: a stale helper says nothing about whether this
+    // repository's conductor works, so classifying it as a readiness problem would
+    // report a perfectly healthy install as runtime-broken and could block a setup
+    // that has nothing wrong with it.
+    if (diagnostic.legacyDriveHelpers.length > 0) {
+        lines.push(`  WARN     Legacy local drive helpers detected: ${diagnostic.legacyDriveHelpers.length} file(s).`);
+        for (const helper of diagnostic.legacyDriveHelpers) {
+            lines.push(`           ${helper}`);
+        }
+        lines.push("           These predate the scoped two-phase bring-up and are retired. Confirm\n" +
+            "           `drive-epic <EPIC> --plan-file <dag>` works for you, then remove them.\n" +
+            "           doctor performed a PATH-PRESENCE check only: it did not run, read, or\n" +
+            "           modify either file, and it cannot delete them for you.");
+    }
     lines.push("           Read-only: this section issues two Bridge GETs and reads local lock state. It");
     lines.push("           runs NO command probe, repairs no scheduler, and never changes the exit code.");
     return lines.join("\n");
@@ -1827,6 +1949,7 @@ export async function runDoctorCli(argv, overrides = {}) {
                 stat: overrides.planeCredentials?.stat ?? injectedFs.stat ?? ((p) => stat(p)),
                 resolveRepoName: overrides.planeCredentials?.resolveRepoName,
                 resolveCredentials: overrides.planeCredentials?.resolveCredentials,
+                readPlaneManifest: overrides.planeCredentials?.readPlaneManifest,
             };
             log(formatPlaneCredentialDiagnosticReport(await collectPlaneCredentialDiagnostic(planeDeps)));
         }
@@ -1840,15 +1963,15 @@ export async function runDoctorCli(argv, overrides = {}) {
             }));
         }
     }
-    // Advisory conduct-epic section (BAPI-803). Read-only, and — like every
-    // section above — it cannot change the exit code: `conduct-epic init` enforces
+    // Advisory implement-epic section (BAPI-803). Read-only, and — like every
+    // section above — it cannot change the exit code: `implement-epic init` enforces
     // these same invariants at the point where they actually block, and someone who
     // never conducts an epic should not see a failing doctor because of it.
     //
     // Skipped entirely on an unsupported platform. This section is the only
     // advisory one that runs COMMAND probes (`gh`, Worktrunk), and doctor's
     // standing contract is that an unsupported platform probes nothing at all —
-    // reporting on tooling for a `conduct-epic` that cannot run there would buy
+    // reporting on tooling for a `implement-epic` that cannot run there would buy
     // nothing and break that contract.
     if (overrides.conductEpic !== false && collection.ok) {
         try {
@@ -1887,7 +2010,7 @@ export async function runDoctorCli(argv, overrides = {}) {
         }
     }
     // Advisory operational-advisories section (BAPI-963), placed immediately after
-    // `conduct-epic readiness` because both are read by the same operator at the
+    // `implement-epic readiness` because both are read by the same operator at the
     // same moment — "can I conduct?" then "what else is already running?".
     //
     // Gated on `collection.ok` for the same reason the section above is: an
@@ -1927,6 +2050,10 @@ export async function runDoctorCli(argv, overrides = {}) {
                 conductorObservation: "unavailable",
                 conductors: [],
                 indeterminateLocks: 0,
+                // Empty, not omitted: a collection that failed has not established
+                // that a legacy helper is absent, and a fallback that CLAIMED to have
+                // checked would be the one kind of wrong answer worse than silence.
+                legacyDriveHelpers: [],
             }));
         }
     }