diff --git a/docs/CHATWOOT_PARITY_DEVELOPMENT_PLAN.md b/docs/CHATWOOT_PARITY_DEVELOPMENT_PLAN.md
index 07fb2330..9d53a329 100644
--- a/docs/CHATWOOT_PARITY_DEVELOPMENT_PLAN.md
+++ b/docs/CHATWOOT_PARITY_DEVELOPMENT_PLAN.md
@@ -17,8 +17,8 @@ Build GoChat as a Go backend that can directly reuse the frontend from `referenc
 ## Current Baseline
 
 - Latest implementation checkpoint: `feat(captain): align preferences payloads`.
-- Latest documentation checkpoint: this checkpoint, recorded with the B11.3a Captain preferences account-level payload implementation.
-- Worktree status at this implementation checkpoint: B11.1a aligns Captain assistant CRUD/tools/inbox bindings; B11.1b aligns Captain scenarios and custom tools; B11.1c aligns Captain documents, assistant responses, bulk actions, and custom-tool test payloads; B11.2 aligns Copilot thread/message create/list/get/delete payloads, account/user scoping, and no-LLM fallback persistence; B11.3a aligns Captain preferences show/update payloads and account-level model/feature storage. Next active slice is B11.3b document sync, embedding, Meilisearch, and external LLM gates.
+- Latest documentation checkpoint: this documentation-only checkpoint, landing the remaining B11.3/B12 execution plan after B11.3a Captain preferences.
+- Worktree status at this implementation checkpoint: B11.1a aligns Captain assistant CRUD/tools/inbox bindings; B11.1b aligns Captain scenarios and custom tools; B11.1c aligns Captain documents, assistant responses, bulk actions, and custom-tool test payloads; B11.2 aligns Copilot thread/message create/list/get/delete payloads, account/user scoping, and no-LLM fallback persistence; B11.3a aligns Captain preferences show/update payloads and account-level model/feature storage. Next active slice is B11.3b Captain playground contract and safe LLM fallback, followed by B11.3c document sync/indexing, B11.3d Copilot tasks/tool-call depth, B11.3e streaming/realtime compatibility, and B12 reused frontend smoke.
 - `go test ./...` passes.
 - Route dump succeeds with `TOTAL: 830` after adding the Chatwoot-compatible applied-SLA index route.
 - Route parity artifacts now exist under `docs/parity/` and are generated by `cmd/route_parity`.
@@ -44,8 +44,11 @@ Next ordered checkpoints:
 
 | Order | Slice | Required outcome | Primary verification |
 | --- | --- | --- | --- |
-| 1 | B11 | Captain/Copilot enterprise screens have real persistence and safe LLM feature gates. | Captain/Copilot handler/service fixtures and disabled-state tests. |
-| 2 | B12 | Reused Chatwoot frontend smoke runs repeatably against GoChat. | Checked smoke command plus gap report under `docs/parity/`. |
+| 1 | B11.3b | Captain assistant playground accepts the Chatwoot frontend payload and returns a safe raw response when no LLM is configured. | Captain playground handler/service fixtures, account-scope tests, no-LLM fallback tests. |
+| 2 | B11.3c | Captain document sync has observable Meilisearch/embedding gates and fakeable indexing boundaries. | Document sync/indexing fixtures for disabled, failure, and fake-success paths. |
+| 3 | B11.3d | Copilot tasks, suggestions, and tool-call records persist enough frontend state for reloads. | Copilot task/tool-call handler/service fixtures and serializer tests. |
+| 4 | B11.3e | Streaming/realtime paths have frontend-compatible non-streaming or disabled fallbacks until true streaming is wired. | Deterministic response tests and event/push payload tests. |
+| 5 | B12 | Reused Chatwoot frontend smoke runs repeatably against GoChat. | Checked smoke command plus gap report under `docs/parity/`. |
 
 ## Execution Snapshot
 
@@ -151,12 +154,15 @@ This ledger records the committed parity checkpoints that future slices should b
 | `feat(captain): align document response actions` | Completes B11.1c frontend payload depth for Captain documents, assistant responses, bulk actions, and custom-tool test: document list/create/show/sync/delete now use account-scoped raw serializers and `{ payload, meta }`; assistant responses use nested `{ assistant_response }`, account-scoped raw serializers, filters, edited flag, and `204` delete; bulk actions accept Chatwoot `{ type, ids, fields.status }` for `AssistantResponse` and `AssistantDocument`; custom-tool test accepts unsaved nested `{ custom_tool }` configs and returns raw `{ status, body }` with a fakeable HTTP boundary. | Focused B11.1c handler tests cover document list/create/show/sync/delete, response list/create/show/update/delete, bulk approve/delete/sync/delete shapes, custom-tool test success/error contract, account scoping, sync status, and no local envelopes. Verification passed: focused B11.1c handler tests, Captain/Copilot service tests, Captain repository tests, handler/service package tests, escalated full `go test ./...`, and `git diff --check`. | Continue B11.2 with Copilot persistence, disabled-state payloads, and document/LLM/Meilisearch gates. B11 remains Doing until Copilot and external-provider gates are tracked and tested. |
 | `feat(copilot): align thread message payloads` | Completes the B11.2 Copilot thread/message frontend contract: thread create accepts Chatwoot `{ message, assistant_id, conversation_id }`, creates the initial user message plus deterministic assistant fallback when no LLM provider is configured, validates assistant account scope, and returns raw thread payloads. Thread list returns `{ payload }` scoped to current account/user with Chatwoot page size/order. Nested `copilot_messages` list/create returns raw message payloads with embedded thread/user/assistant push data and `204` delete remains available for local compatibility. | `go test ./internal/handler/api/v1 -run 'Copilot' -count=1`; `go test ./internal/handler/api/v1 -run 'Captain\|Copilot' -count=1`; `go test ./internal/service -run 'Captain\|Copilot' -count=1`; `go test ./internal/repository -run 'Copilot' -count=1`; handler/service/repository package tests; escalated full `go test ./...`; `git diff --check`. Focused handler fixtures cover no local envelopes, account/user isolation, assistant scope, nested message order, and no-LLM assistant fallback persistence. | Continue B11.3 with Captain document sync/indexing, Meilisearch/embedding gates, Copilot tasks/preferences/tool-call/playground depth, streaming/realtime compatibility, and reused frontend smoke coverage. |
 | `feat(captain): align preferences payloads` | Starts B11.3a by replacing the legacy local `captain_preferences` CRUD response with Chatwoot's account-level Captain preferences contract: `GET/PUT /captain/preferences` now return raw `{ providers, models, features }`, `captain_models` and `captain_features` persist on accounts, updates merge with existing account settings, invalid model selections return `422`, and update is administrator-gated. Route artifacts were regenerated after removing frontend-unused POST/DELETE preference routes and adding exact no-trailing-slash GET/PUT paths. | `go test ./internal/handler/api/v1 -run 'CaptainPreference' -count=1`; `go test ./internal/service -run 'CaptainPreference' -count=1`; `go test ./internal/handler/api/v1 -run 'Captain\|Copilot' -count=1`; `go test ./internal/service -run 'Captain\|Copilot' -count=1`; `go test ./internal/handler/api/v1 -count=1`; `go test ./internal/service -count=1`; `go test ./internal/model -count=1`; `go test ./internal/router -count=1`; `go test ./cmd/migrate -count=1`; `go run ./cmd/dump_routes > docs/parity/gochat_routes.txt`; `go run ./cmd/route_parity`; escalated full `go test ./...`; `git diff --check`. | Continue B11.3b with document sync/indexing, Meilisearch/embedding gates, remaining Copilot task/tool-call/playground depth, streaming/realtime compatibility, and reused frontend smoke coverage. |
+| `docs: land captain copilot completion plan` | Documentation-only handoff checkpoint that breaks the remaining B11.3 work into explicit Captain playground, document sync/indexing, Copilot task/tool-call, streaming/realtime, and B12 smoke slices. It also records the reference files, required payload contracts, fallback behavior, verification commands, and status gates so no Hermes-era plan remains implicit. | `git diff --check`; no Go code changed. | Start B11.3b Captain playground implementation from the recorded contract. |
 
 ## Next Slice Contract
 
 Completed implementation slice: B11.3a now aligns Captain preferences show/update payloads with the reused Chatwoot frontend, building on B11.1a-B11.2 Captain/Copilot resource contracts.
 
-Next implementation slice: continue B11.3b document sync/indexing, Meilisearch/embedding gates, Copilot tasks/tool-call/playground depth, and streaming/realtime compatibility. B9.3 delayed/durable worker scheduling and B9.4 macro attachment depth remain named Phase 5 follow-ups.
+Completed documentation slice: the remaining development plan is now fully landed in this tracker. B11.3 is split into concrete Captain playground, document sync/indexing, Copilot task/tool-call, and streaming/realtime checkpoints. B12 has a repeatable smoke-report contract. B9.3 delayed/durable worker scheduling and B9.4 macro attachment depth remain named Phase 5 follow-ups.
+
+Next implementation slice: start B11.3b Captain assistant playground parity. Do not expand to document indexing or Copilot tasks until playground request/response shape, account scoping, and no-LLM fallback are covered by tests.
 
 | Step | Required result | Reference source | Verification |
 | --- | --- | --- | --- |
@@ -181,7 +187,13 @@ Next implementation slice: continue B11.3b document sync/indexing, Meilisearch/e
 | N19 | Keep B11.1c Captain document/response/bulk/test resources as current Captain baseline. | Captain documents, assistant responses, bulk actions, custom-tool test controllers, Jbuilder views, and dashboard clients. | Done by `feat(captain): align document response actions`; documents, assistant responses, bulk resource actions, and unsaved custom-tool test use account-scoped Chatwoot payloads with a fakeable HTTP boundary. |
 | N20 | Keep B11.2 Copilot thread/message resources as current Copilot baseline. | `copilot_threads_controller.rb`, `copilot_messages_controller.rb`, Copilot Jbuilder partials, and dashboard `copilotThreads.js`/`copilotMessages.js` clients. | Done by `feat(copilot): align thread message payloads`; threads/messages persist account/user-scoped Chatwoot payloads and no-LLM fallback assistant messages. |
 | N21 | Keep B11.3a Captain preferences as current account-level Captain config baseline. | `preferences_controller.rb`, `CaptainFeaturable`, `config/llm.yml`, dashboard `preferences.js` API/store. | Done by `feat(captain): align preferences payloads`; raw model/provider/feature payloads, merge update behavior, account storage, admin gate, and exact preference routes are covered. |
-| N22 | Update this tracker after every implementation checkpoint. | This document. | `git diff --check`; `go test ./...` for Go changes. |
+| N22 | Implement B11.3b Captain assistant playground payload parity. | `reference/chatwoot/enterprise/app/controllers/api/v1/accounts/captain/assistants_controller.rb#playground`, dashboard `api/captain/assistant.js`, assistant playground component/store. | Top-level `message_content` and `message_history` are accepted; account-scoped assistant lookup is enforced; legacy `{ content }` and v2 `{ response }` response shape differences are handled or explicitly feature-gated; no-LLM fallback returns raw frontend-compatible JSON without 500. |
+| N23 | Implement B11.3c Captain document sync/indexing gates. | Captain document sync service/jobs, document controller `sync`, existing Meilisearch engine, and any local embedding boundary. | Disabled config, fake successful indexing, failed sync metadata, and account-scoped document lookup are covered without opening external network connections in default tests. |
+| N24 | Implement B11.3d Copilot task/tool-call persistence. | `resource :tasks` routes, Copilot/Captain task services, dashboard Copilot clients, current local `copilot_*` models. | Rewrite/summarize/reply suggestion/label suggestion/follow-up requests persist task/tool-call state or return documented raw disabled states; serializers survive frontend reload. |
+| N25 | Implement B11.3e streaming/realtime compatibility. | Chatwoot Copilot/Captain streaming, push/event payloads, current Go channel dispatcher. | If streaming is not implemented, the endpoint returns deterministic non-streaming payloads and records the fallback; no route returns placeholder success or local envelope. |
+| N26 | Start B12 smoke harness after B11.3 has a tested disabled/external-provider story. | `reference/chatwoot` frontend boot scripts and GoChat dev/test boot flow. | A checked command and `docs/parity/frontend_smoke_report.md` record core and enterprise smoke status. |
+| N27 | Keep Hermes source plans mapped but inactive. | `.hermes/plans/2025-05-24-global-search-meilisearch.md`, `.hermes/plans/2026-05-24-automation-macro-csat.md`. | New work must update this tracker directly; Hermes files are read-only source notes unless the user asks otherwise. |
+| N28 | Update this tracker after every implementation checkpoint. | This document. | `git diff --check`; `go test ./...` for Go changes. |
 
 Current B2 profile checkpoint:
 
@@ -774,7 +786,10 @@ B11 Captain/Copilot breakdown:
 | B11.1c | Align Captain documents, assistant responses, bulk actions, and custom-tool test execution. | `documents_controller.rb`, `assistant_responses_controller.rb`, `bulk_actions_controller.rb`, `custom_tools_controller#test`, dashboard Captain clients. | Handler/service fixtures for document list/create/show/sync/delete, response list/show/create/update/delete, bulk-action payloads, test execution errors, account scoping, sync status, and no local response envelopes. | Done by `feat(captain): align document response actions` |
 | B11.2 | Align Copilot thread/message APIs, account/user scoping, assistant scope, frontend payloads, and no-LLM fallback persistence. | `copilot_threads_controller.rb`, `copilot_messages_controller.rb`, Copilot Jbuilder partials, dashboard `copilotThreads.js` and `copilotMessages.js`. | Handler tests cover thread/message create/list/get/delete, nested message ordering, assistant/account isolation, user isolation, and deterministic disabled LLM fallback. | Done by `feat(copilot): align thread message payloads` |
 | B11.3a | Align Captain preferences show/update payloads, account-level model/feature storage, and admin update gate. | `preferences_controller.rb`, `CaptainFeaturable`, `config/llm.yml`, dashboard `preferences.js` API/store. | Handler tests cover raw `{ providers, models, features }`, default selected models, merge update behavior, account persistence, invalid model rejection, admin gate, and exact preference routes. | Done by `feat(captain): align preferences payloads` |
-| B11.3b | Implement document sync/indexing gates for Meilisearch or the chosen embedding/search backend, and finish Copilot task/playground/tool-call/streaming depth without blocking the frontend when LLM config is absent. | Captain document/embedding services plus remaining Copilot controllers/services/frontend clients. | Tests cover disabled state, failed sync observability, successful fake backend indexing, Copilot task/tool-call persistence, and non-streaming fallback. | Todo |
+| B11.3b | Align Captain assistant playground request/response behavior and no-LLM fallback. | `assistants_controller.rb#playground`, `Captain::Llm::AssistantChatService`, `AgentRunnerService`, dashboard `api/captain/assistant.js`, playground component/store. | Handler/service tests cover top-level `message_content`, `message_history`, account-scoped assistant lookup, no-history payloads, no duplicate latest user message for v2 behavior if enabled, raw `{ content }` or `{ response }` response shape, and safe no-LLM fallback. | Todo |
+| B11.3c | Implement document sync/indexing gates for Meilisearch or the chosen embedding/search backend. | Captain document sync/indexing services, document controller `sync`, existing Meilisearch engine, local embedding/config boundaries. | Tests cover disabled config, failed sync observability, successful fake backend indexing, account-scoped document lookup, and no external network call in default test mode. | Todo |
+| B11.3d | Finish Copilot task, suggestion, and tool-call persistence depth. | `resource :tasks` routes in `reference/chatwoot/config/routes.rb:62-89`, Copilot/Captain task services, dashboard Copilot clients. | Tests cover rewrite/summarize/reply suggestion/label suggestion/follow-up request payloads, persisted task/tool-call records, reloadable serializers, account/user scoping, and raw disabled state when provider config is missing. | Todo |
+| B11.3e | Add streaming/realtime compatibility or deterministic non-streaming fallback. | Chatwoot Captain/Copilot streaming paths, push payloads, current Go dispatcher/realtime boundaries. | Tests prove endpoints never return placeholder success/local envelopes; non-streaming fallback payloads are deterministic and frontend-compatible until true streaming is implemented. | Todo |
 
 B11.1a current checkpoint:
 
@@ -821,6 +836,25 @@ B11.3a current checkpoint:
 - Invalid model selections return `422 { error }`, non-admin updates return `401`, and agents can still read the preferences payload.
 - Route dump was regenerated and remains `TOTAL: 830`; route parity remains `270 exact, 7 parameter-compatible, 0 missing`.
 
+B11.3b Captain playground landing contract:
+
+| Area | Reference contract | Required Go work | Required tests |
+| --- | --- | --- | --- |
+| Route and request body | `POST /api/v1/accounts/:account_id/captain/assistants/:assistant_id/playground` receives top-level `message_content` and `message_history` from dashboard `api/captain/assistant.js`. | Mount the playground route in production and focused test routers; bind top-level payloads while retaining harmless local compatibility only inside the service boundary. | Handler test posts the exact frontend body and proves no local `{ success, data }` envelope. |
+| Account scope | Rails loads the assistant through the current account before executing playground logic. | Fetch assistant by `account_id` and `assistant_id`; reject cross-account assistant IDs. | Cross-account assistant test returns not found/unauthorized and never calls the LLM boundary. |
+| Legacy response shape | When Captain v2 is disabled, Rails calls `Captain::Llm::AssistantChatService#generate_response` and renders raw `{ content: ... }`. | Add a service method that can return the legacy raw content payload when the local v2 feature flag is absent/false. | No-v2 test asserts raw `{ content }` shape for the default path. |
+| V2 response shape | When `captain_integration_v2` is enabled, Rails appends the current user message unless it is already the last history item, calls `AgentRunnerService`, and renders raw `{ response: ... }`. | If a local account feature flag helper exists, implement the append/no-duplicate behavior; otherwise document the missing helper and keep v2 disabled until B11.3d/B11.3e. | V2-enabled test, if implemented, asserts appended history and no duplicate latest user message. If deferred, a disabled-state test records the raw fallback. |
+| No LLM config | The reused frontend must not fail just because provider credentials are missing in local/dev mode. | Guard nil/missing LLM providers and return deterministic raw frontend-compatible JSON with an explanatory disabled/fallback message. | No-provider test returns `200` and a raw payload, not panic/500. |
+| Message history | Chatwoot forwards `message_history` entries with `role`, `content`, and optional `agent_name`. | Preserve history order through the service boundary; include the current message only according to the selected legacy/v2 behavior. | Fake LLM/service test captures history and current message handling. |
+
+B11.3c-B11.3e follow-up contracts:
+
+| Slice | Landing rule | Status gate |
+| --- | --- | --- |
+| B11.3c document sync/indexing | Document sync must expose frontend-visible `syncing/synced/failed` states and call a fakeable Meilisearch/embedding boundary. Missing provider config must be a raw disabled/failure state, not a placeholder success. | B11 remains `Doing` until disabled, failed, and fake-success sync tests are present. |
+| B11.3d Copilot tasks/tool-calls | Rewrite, summarize, reply suggestion, label suggestion, and follow-up task routes must accept Chatwoot request payloads, persist enough task/tool-call output for reloads, and serialize raw frontend payloads. | B11 remains `Doing` until task/tool-call fixtures cover account/user scoping and no-provider fallback. |
+| B11.3e streaming/realtime | Streaming can be deferred only with a deterministic non-streaming response or explicit disabled state. Realtime push payloads should use the same thread/message serializer already landed in B11.2. | B11 moves to `Review` only after every streaming/realtime endpoint has a tested frontend-compatible fallback. |
+
 B11 landing rules:
 
 | Area | Landing requirement | Done signal |
@@ -862,6 +896,7 @@ Hermes plan material now mapped:
 
 - `.hermes/plans/2025-05-24-global-search-meilisearch.md` maps to Phase 1/B6. The Meilisearch interface, config, documents, indexing hooks, reindex command, payload shape, and live gate are already tracked here. Remaining search work is only future payload gaps discovered by frontend smoke or route expansion.
 - `.hermes/plans/2026-05-24-automation-macro-csat.md` maps to B8 and B9. CSAT model/service/listener/handlers, automation rule handlers, macro handlers, route wiring, action side effects, and durable jobs are tracked above instead of relying on the Hermes-era checklist.
+- Current rule: no active implementation task should be sourced only from `.hermes/plans`. If a later agent mines those files for additional context, the resulting task must be copied into this tracker before the checkpoint is considered planned.
 
 Next checkpoint contract for B7.6:
 
@@ -948,7 +983,7 @@ Work proceeds top-down unless a failing test or frontend blocker forces a narrow
 | B8 | CSAT account/public/send completion. | Chatwoot CSAT survey responses, reports, downloads, listeners. | Metrics/list/review/download/send idempotency tests. | Review |
 | B9 | Automation/macros durable side effects. | Chatwoot automation/macro services and jobs. | Action execution, logs, webhook/email transcript retry tests. | Review |
 | B10 | Audit, CustomRole, InboxLimit. | Chatwoot enterprise admin behavior and policies. | Authorization, audit emission, limits enforcement, admin payload fixtures. | Review |
-| B11 | Captain/Copilot deep behavior. | Chatwoot Captain/Copilot controllers, services, frontend clients. | Assistant/tool/document/scenario/copilot thread/task tests and feature gates. | Todo |
+| B11 | Captain/Copilot deep behavior. | Chatwoot Captain/Copilot controllers, services, frontend clients. | Assistant/tool/document/scenario/copilot thread/task tests and feature gates. | Doing |
 | B12 | Frontend smoke harness. | `reference/chatwoot` frontend. | Repeatable smoke command and checked gap report. | Todo |
 
 Remaining slice landing plan:
@@ -960,7 +995,7 @@ Remaining slice landing plan:
 | B8 | Done: account-side CSAT list/metrics/review-note payload parity, public submit/update idempotency, resolve-triggered generic survey message send, and CSV download filters/columns. | Channel-specific WhatsApp/Twilio template send hooks and durable queueing are tracked under Phase 5. | Review after `b36cf07`; move to Done only after channel-specific send hooks are either implemented or formally split as external integration scope. |
 | B9 | Done: B9.1 automation rule CRUD/listener/log/external-action parity and B9.2 macro frontend CRUD/execute side effects. | Delayed actions, durable queued worker scheduling, and deeper macro attachment/file parity remain named B9.3/B9.4 follow-ups. | Review after `feat(macros): align chatwoot macro payloads`; move to Done only after durable worker/attachment gaps are implemented or formally split out. |
 | B10 | Done: audit list payload, audit writer boundary for representative mutating core resources, CustomRole permission-key parity, AccountUser permission resolution, admin gates, delete nullification, and account-level InboxLimit enforcement in inbox/channel creation paths. | Frontend smoke coverage for enterprise settings remains B12, not a hidden B10 blocker. | Review after B10.4; move to Done only after reused frontend smoke confirms audit/custom-role/limit settings flows or any smoke gaps are split into owned follow-ups. |
-| B11 | Captain Assistant CRUD, inbox binding, responses, documents, and custom tools payload fixtures. | Copilot threads/messages/tasks, playground/tool-call behavior, document sync/embedding feature gates, streaming fallback. | Done only after LLM-dependent behavior is either implemented behind config or safely stubbed with frontend-compatible disabled states. |
+| B11 | Done through B11.3a: Captain Assistant CRUD, inbox binding, scenarios, documents, responses, custom tools, Copilot threads/messages, and Captain preferences payload fixtures. | B11.3b playground, B11.3c document sync/embedding gates, B11.3d Copilot tasks/tool-calls, and B11.3e streaming/realtime fallback. | Done only after LLM-dependent behavior is either implemented behind config or safely stubbed with frontend-compatible disabled states. |
 | B12 | Boot reused Chatwoot frontend against GoChat auth/profile/inbox/conversation/contact flows. | Add smoke paths for widget init/message, public CSAT, reports, and enterprise screens as B7-B11 land. | Done only after the smoke command is repeatable and writes a checked gap report. |
 
 Per-slice documentation rule:
@@ -1238,7 +1273,7 @@ Enterprise tracking table:
 | P4.3 | Custom roles/permissions | `internal/model/custom_role.go`, `internal/service/custom_role_service.go`, `internal/middleware/role_check.go`, `internal/handler/api/v1/custom_role_handler.go` | Permission arrays, raw admin payloads, administrator gates, account-user resolution, profile permissions, and delete nullification are implemented; keep in Review until frontend smoke covers enterprise settings. | Review |
 | P4.4 | Agent capacity | `internal/model/agent_capacity_policy.go`, `internal/service/agent_capacity_policy_service.go`, `internal/handler/api/v1/agent_capacity_handler.go`, `internal/autoassignment/*` | First align AgentCapacityPolicy API, serializers, nested users, and `InboxCapacityLimit` data contracts; then enforce capacity in manual/auto assignment. | Review |
 | P4.5 | Inbox limits | `internal/model/agent_capacity_policy.go` `InboxCapacityLimit`, plus legacy `internal/model/inbox_limit.go`, `internal/service/inbox_limit_service.go`, `internal/repository/inbox_limit_repo.go`, `internal/handler/api/v1/inbox_limit_handler.go` | Chatwoot enterprise nested `agent_capacity_policies/:policy_id/inbox_limits`, assignment-path enforcement, and account-level `usage_limits[:inboxes]` create-path enforcement are covered. | Review |
-| P4.6 | Captain/Copilot | `internal/model/captain_models.go`, `internal/model/copilot_models.go`, `internal/service/captain_*`, `internal/service/copilot_*`, `internal/handler/api/v1/captain_*`, `internal/handler/api/v1/copilot_handler.go` | Captain resource payloads through B11.1c, Copilot thread/message payloads through B11.2, and Captain preferences through B11.3a are aligned; complete Copilot tasks/tool-call depth, suggestions, document/LLM gates, and streaming compatibility. | Doing |
+| P4.6 | Captain/Copilot | `internal/model/captain_models.go`, `internal/model/copilot_models.go`, `internal/service/captain_*`, `internal/service/copilot_*`, `internal/handler/api/v1/captain_*`, `internal/handler/api/v1/copilot_handler.go` | Captain resource payloads through B11.1c, Copilot thread/message payloads through B11.2, and Captain preferences through B11.3a are aligned; complete B11.3b playground, B11.3c document/LLM/Meilisearch gates, B11.3d Copilot task/tool-call depth, and B11.3e streaming compatibility. | Doing |
 | P4.7 | CSAT | `internal/csat/*`, `internal/automation/csat_survey_*`, `internal/handler/api/v1/csat_*`, `internal/service/csat_metrics_service.go` | Account-side list/metrics/review-note payloads, public update depth, resolve-triggered generic survey send, and download CSV are aligned; channel-specific template send hooks remain Phase 5 integration work. | Review |
 | P4.8 | Automation and macros | `internal/automation/*`, `internal/handler/api/v1/automation_rule_handler.go`, `internal/handler/api/v1/macro_handler.go` | Automation-rule CRUD/listener/log/external-action delivery and macro CRUD/display-ID execution parity are implemented; durable delayed actions and deeper macro attachment/file parity remain B9.3/B9.4 follow-ups. | Review |
 | P4.9 | Assignment policies | `internal/autoassignment/*`, `internal/automation/agent_bot_rule_listener.go` | Match Chatwoot assignment policy behavior and availability/capacity rules. | Doing |
@@ -1255,7 +1290,7 @@ Enterprise work package breakdown:
 | Audit | Audit model parity, mutating action coverage, request metadata, filters/pagination, admin endpoint payloads. | List/admin payload parity is covered by `feat(audit): align chatwoot audit log payloads`; named representative writer coverage is covered by `feat(audit): record enterprise mutations` and `feat(audit): cover operational mutations`. | Review |
 | Custom roles | Permission-key parity, account-user role resolution, policy middleware, create/update/delete behavior. | Permission arrays, raw admin payloads, admin gates, RBAC/account-scope/profile resolution, and delete nullification are covered by `feat(custom-roles): align chatwoot permissions`. | Review |
 | Inbox limits | Account/inbox limit models, create/update enforcement, UI-readable limit responses, admin overrides. | Chatwoot nested capacity-limit API, assignment-path enforcement, and account-level create-limit `402` behavior are covered by B5/B7/B10.4. | Review |
-| Captain/Copilot | Assistants, inbox bindings, scenarios, responses, documents, tools, preferences, copilot threads/messages, tasks, streaming/tool-call behavior. | Assistant CRUD/tools/inbox binding fixtures are covered by `feat(captain): align assistant resources`; scenario/custom-tool fixtures are covered by `feat(captain): align scenario and tool payloads`; document/assistant-response/bulk/custom-tool-test fixtures are covered by `feat(captain): align document response actions`; Copilot thread/message fixtures are covered by `feat(copilot): align thread message payloads`; preferences fixtures are covered by `feat(captain): align preferences payloads`; feature gates for external LLM dependencies, remaining Copilot tasks/tool-calls, and frontend smoke screens remain. | Doing |
+| Captain/Copilot | Assistants, inbox bindings, scenarios, responses, documents, tools, preferences, copilot threads/messages, tasks, streaming/tool-call behavior. | Assistant CRUD/tools/inbox binding fixtures are covered by `feat(captain): align assistant resources`; scenario/custom-tool fixtures are covered by `feat(captain): align scenario and tool payloads`; document/assistant-response/bulk/custom-tool-test fixtures are covered by `feat(captain): align document response actions`; Copilot thread/message fixtures are covered by `feat(copilot): align thread message payloads`; preferences fixtures are covered by `feat(captain): align preferences payloads`; B11.3b-B11.3e now track playground, external LLM/document gates, remaining Copilot task/tool-call behavior, streaming fallback, and frontend smoke screens. | Doing |
 
 Enterprise acceptance gates: