adelorenzo/konstruct
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(06-web-chat): create phase plan

Browse Source
This commit is contained in:
Adolfo Delorenzo
2026-03-25 10:08:44 -06:00
parent 5e4dd34331
commit c0fa0cefee
4 changed files with 792 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.planning/ROADMAP.md
View File

@@ -111,6 +111,23 @@ Plans:
- [ ] 05-03-PLAN.md — Human verification: test all three creation paths, RBAC enforcement, system prompt auto-generation
- [ ] 05-04-PLAN.md — Gap closure: add /agents/new to proxy RBAC restrictions, hide New Employee button for operators, fix wizard deploy error handling
### Phase 6: Web Chat
**Goal**: Users can chat with AI Employees directly in the portal through a real-time web chat interface — no external messaging platform required
**Depends on**: Phase 5
**Requirements**: CHAT-01, CHAT-02, CHAT-03, CHAT-04, CHAT-05
**Success Criteria** (what must be TRUE):
1. A user can open a chat window with any AI Employee and have a real-time conversation within the portal
2. The chat interface supports the full agent pipeline — memory, tools, escalation, and media (same capabilities as Slack/WhatsApp)
3. Conversation history persists and is visible when the user returns to the chat
4. The chat respects RBAC — users can only chat with agents belonging to tenants they have access to
5. The chat interface feels responsive — typing indicators, message streaming or fast response display
**Plans**: 3 plans
Plans:
- [ ] 06-01-PLAN.md — Backend: DB migration (web_conversations + web_conversation_messages), ORM models, ChannelType.WEB, Redis pub-sub key, WebSocket endpoint, web channel adapter, chat REST API with RBAC, orchestrator _send_response wiring, unit tests
- [ ] 06-02-PLAN.md — Frontend: /chat page with conversation sidebar, message window with markdown rendering, typing indicators, WebSocket hook, agent picker dialog, nav link, react-markdown install
- [ ] 06-03-PLAN.md — Human verification: end-to-end chat flow, conversation persistence, RBAC enforcement, markdown rendering, all roles can chat
## Progress
**Execution Order:**
@@ -123,7 +140,7 @@ Phases execute in numeric order: 1 -> 2 -> 3 -> 4 -> 5 -> 6
| 3. Operator Experience | 5/5 | Complete | 2026-03-24 |
| 4. RBAC | 3/3 | Complete | 2026-03-24 |
| 5. Employee Design | 4/4 | Complete | 2026-03-25 |
| 6. Web Chat | 0/0 | Not started | - |
| 6. Web Chat | 0/3 | Not started | - |
---
@@ -131,21 +148,6 @@ Phases execute in numeric order: 1 -> 2 -> 3 -> 4 -> 5 -> 6
**LLM-03 conflict resolved:** BYO API keys confirmed in v1 scope per user decision during Phase 3 context gathering. Implemented via Fernet encryption in Phase 3.
### Phase 6: Web Chat
**Goal**: Users can chat with AI Employees directly in the portal through a real-time web chat interface — no external messaging platform required
**Depends on**: Phase 5
**Requirements**: CHAT-01, CHAT-02, CHAT-03, CHAT-04, CHAT-05
**Success Criteria** (what must be TRUE):
1. A user can open a chat window with any AI Employee and have a real-time conversation within the portal
2. The chat interface supports the full agent pipeline — memory, tools, escalation, and media (same capabilities as Slack/WhatsApp)
3. Conversation history persists and is visible when the user returns to the chat
4. The chat respects RBAC — users can only chat with agents belonging to tenants they have access to
5. The chat interface feels responsive — typing indicators, message streaming or fast response display
**Plans**: 0 plans
Plans:
- [ ] TBD (run /gsd:plan-phase 6 to break down)
---
*Roadmap created: 2026-03-23*
*Coverage: 25/25 v1 requirements + 6 RBAC requirements + 5 Employee Design requirements mapped*
*Coverage: 25/25 v1 requirements + 6 RBAC requirements + 5 Employee Design requirements + 5 Web Chat requirements mapped*

329
.planning/phases/06-web-chat/06-01-PLAN.md Normal file
View File

@@ -0,0 +1,329 @@
---
phase: 06-web-chat
plan: 01
type: execute
wave: 1
depends_on: []
files_modified:
- packages/shared/shared/models/message.py
- packages/shared/shared/redis_keys.py
- packages/shared/shared/models/chat.py
- packages/shared/shared/api/chat.py
- packages/shared/shared/api/__init__.py
- packages/gateway/gateway/channels/web.py
- packages/gateway/gateway/main.py
- packages/orchestrator/orchestrator/tasks.py
- migrations/versions/008_web_chat.py
- tests/unit/test_web_channel.py
- tests/unit/test_chat_api.py
autonomous: true
requirements:
- CHAT-01
- CHAT-02
- CHAT-03
- CHAT-04
- CHAT-05
must_haves:
truths:
- "Web channel messages normalize into valid KonstructMessage with channel='web'"
- "Celery _send_response publishes web channel responses to Redis pub-sub"
- "WebSocket endpoint accepts connections and dispatches messages to Celery pipeline"
- "Typing indicator event is sent immediately after receiving a user message"
- "Chat REST API enforces RBAC — non-members get 403"
- "Platform admin can access conversations for any tenant"
- "Conversation history persists in DB and is loadable via REST"
artifacts:
- path: "packages/shared/shared/models/chat.py"
provides: "WebConversation and WebConversationMessage ORM models"
contains: "class WebConversation"
- path: "packages/gateway/gateway/channels/web.py"
provides: "WebSocket endpoint and web channel normalizer"
contains: "async def chat_websocket"
- path: "packages/shared/shared/api/chat.py"
provides: "REST API for conversation CRUD"
exports: ["chat_router"]
- path: "migrations/versions/008_web_chat.py"
provides: "DB migration for web_conversations and web_conversation_messages tables"
contains: "web_conversations"
- path: "tests/unit/test_web_channel.py"
provides: "Unit tests for web channel adapter"
contains: "test_normalize_web_event"
- path: "tests/unit/test_chat_api.py"
provides: "Unit tests for chat REST API with RBAC"
contains: "test_chat_rbac_enforcement"
key_links:
- from: "packages/gateway/gateway/channels/web.py"
to: "packages/orchestrator/orchestrator/tasks.py"
via: "handle_message.delay() Celery dispatch"
pattern: "handle_message\\.delay"
- from: "packages/orchestrator/orchestrator/tasks.py"
to: "packages/shared/shared/redis_keys.py"
via: "Redis pub-sub publish for web channel"
pattern: "webchat_response_key"
- from: "packages/gateway/gateway/channels/web.py"
to: "packages/shared/shared/redis_keys.py"
via: "Redis pub-sub subscribe for response delivery"
pattern: "webchat_response_key"
- from: "packages/shared/shared/api/chat.py"
to: "packages/shared/shared/api/rbac.py"
via: "require_tenant_member RBAC guard"
pattern: "require_tenant_member"
user_setup: []
---
<objective>
Build the complete backend infrastructure for web chat: DB schema, ORM models, web channel adapter with WebSocket endpoint, Redis pub-sub response bridge, chat REST API with RBAC, and orchestrator integration. After this plan, the portal can send messages via WebSocket and receive responses through the full agent pipeline.
Purpose: Enables the portal to use the same agent pipeline as Slack/WhatsApp via a new "web" channel — the foundational plumbing that the frontend chat UI (Plan 02) connects to.
Output: Working WebSocket endpoint, conversation persistence, RBAC-enforced REST API, and unit tests.
</objective>
<execution_context>
@/home/adelorenzo/.claude/get-shit-done/workflows/execute-plan.md
@/home/adelorenzo/.claude/get-shit-done/templates/summary.md
</execution_context>
<context>
@.planning/PROJECT.md
@.planning/ROADMAP.md
@.planning/STATE.md
@.planning/phases/06-web-chat/06-CONTEXT.md
@.planning/phases/06-web-chat/06-RESEARCH.md
<interfaces>
<!-- Key types and contracts the executor needs. Extracted from codebase. -->
From packages/shared/shared/models/message.py:
```python
class ChannelType(StrEnum):
SLACK = "slack"
WHATSAPP = "whatsapp"
MATTERMOST = "mattermost"
ROCKETCHAT = "rocketchat"
TEAMS = "teams"
TELEGRAM = "telegram"
SIGNAL = "signal"
# WEB = "web" <-- ADD THIS
class KonstructMessage(BaseModel):
id: str
tenant_id: str | None
channel: ChannelType
channel_metadata: dict[str, Any]
sender: SenderInfo
content: MessageContent
timestamp: datetime
thread_id: str | None
reply_to: str | None
context: dict[str, Any]
```
From packages/shared/shared/redis_keys.py:
```python
# All keys follow: {tenant_id}:{key_type}:{discriminator}
def memory_short_key(tenant_id: str, agent_id: str, user_id: str) -> str
def escalation_status_key(tenant_id: str, thread_id: str) -> str
# ADD: webchat_response_key(tenant_id, conversation_id)
```
From packages/shared/shared/api/rbac.py:
```python
@dataclass
class PortalCaller:
user_id: uuid.UUID
role: str
tenant_id: uuid.UUID | None = None
async def get_portal_caller(...) -> PortalCaller
async def require_tenant_member(tenant_id: UUID, caller: PortalCaller, session: AsyncSession) -> None
async def require_tenant_admin(tenant_id: UUID, caller: PortalCaller, session: AsyncSession) -> None
```
From packages/orchestrator/orchestrator/tasks.py:
```python
# handle_message pops extras before model_validate:
# placeholder_ts, channel_id, phone_number_id, bot_token
# ADD: conversation_id, portal_user_id, tenant_id (for web)
# _send_response routes by channel_str:
# "slack" -> _update_slack_placeholder
# "whatsapp" -> send_whatsapp_message
# ADD: "web" -> Redis pub-sub publish
# _build_response_extras builds channel-specific extras dict
# ADD: "web" case returning conversation_id + tenant_id
```
From packages/shared/shared/api/__init__.py:
```python
# Current routers mounted on gateway:
# portal_router, billing_router, channels_router, llm_keys_router,
# usage_router, webhook_router, invitations_router, templates_router
# ADD: chat_router
```
From packages/gateway/gateway/main.py:
```python
# CORS allows: localhost:3000, 127.0.0.1:3000, 100.64.0.10:3000
# WebSocket doesn't use CORS (browser doesn't enforce) but same origin rules apply
# Include chat_router and WebSocket router here
```
</interfaces>
</context>
<tasks>
<task type="auto" tdd="true">
<name>Task 1: Backend models, migration, channel type, Redis key, and unit tests</name>
<files>
packages/shared/shared/models/message.py,
packages/shared/shared/redis_keys.py,
packages/shared/shared/models/chat.py,
migrations/versions/008_web_chat.py,
tests/unit/test_web_channel.py,
tests/unit/test_chat_api.py
</files>
<behavior>
- test_normalize_web_event: normalize_web_event({text, tenant_id, agent_id, user_id, conversation_id}) -> KonstructMessage with channel=WEB, thread_id=conversation_id, sender.user_id=portal_user_id
- test_send_response_web_publishes_to_redis: _send_response("web", "hello", {conversation_id, tenant_id}) publishes JSON to Redis channel matching webchat_response_key(tenant_id, conversation_id)
- test_typing_indicator_sent: WebSocket handler sends {"type": "typing"} immediately after receiving user message, before Celery dispatch
- test_chat_rbac_enforcement: GET /api/portal/chat/conversations?tenant_id=X returns 403 when caller is not a member of tenant X
- test_platform_admin_cross_tenant: GET /api/portal/chat/conversations?tenant_id=X returns 200 when caller is platform_admin (bypasses membership)
- test_list_conversation_history: GET /api/portal/chat/conversations/{id}/messages returns paginated messages ordered by created_at
- test_create_conversation: POST /api/portal/chat/conversations with {tenant_id, agent_id} creates or returns existing conversation for user+agent pair
</behavior>
<action>
1. Add WEB = "web" to ChannelType in packages/shared/shared/models/message.py
2. Add webchat_response_key(tenant_id, conversation_id) to packages/shared/shared/redis_keys.py following existing pattern: return f"{tenant_id}:webchat:response:{conversation_id}"
3. Create packages/shared/shared/models/chat.py with ORM models:
- WebConversation: id (UUID PK), tenant_id (UUID, FK tenants.id), agent_id (UUID, FK agents.id), user_id (UUID, FK portal_users.id), created_at, updated_at. UniqueConstraint on (tenant_id, agent_id, user_id). RLS via tenant_id.
- WebConversationMessage: id (UUID PK), conversation_id (UUID, FK web_conversations.id ON DELETE CASCADE), tenant_id (UUID), role (TEXT, CHECK "user"/"assistant"), content (TEXT), created_at. RLS via tenant_id.
Use mapped_column() + Mapped[] (SQLAlchemy 2.0 pattern, not Column()).
4. Create migration 008_web_chat.py:
- Create web_conversations table with columns matching ORM model
- Create web_conversation_messages table with FK to web_conversations
- Enable RLS on both tables (FORCE ROW LEVEL SECURITY)
- Create RLS policies matching existing pattern (current_setting('app.current_tenant')::uuid)
- ALTER CHECK constraint on channel_connections.channel_type to include 'web' (see Pitfall 5 in RESEARCH.md — the existing CHECK must be replaced, not just added to)
- Add index on web_conversation_messages(conversation_id, created_at)
5. Write test files FIRST (RED phase):
- tests/unit/test_web_channel.py: test normalize_web_event, test _send_response web publishes to Redis (mock aioredis), test typing indicator
- tests/unit/test_chat_api.py: test RBAC enforcement (403 for non-member), platform admin cross-tenant (200), list history (paginated), create conversation (get-or-create)
Use httpx AsyncClient with app fixture pattern from existing tests. Mock DB sessions and Redis.
IMPORTANT: Celery tasks MUST be sync def with asyncio.run() — never async def (hard architectural constraint).
IMPORTANT: Use TEXT+CHECK for role column (not sa.Enum) per Phase 1 convention.
IMPORTANT: _send_response "web" case must use try/finally around aioredis.from_url() to avoid connection leaks (Pitfall 2 from RESEARCH.md).
</action>
<verify>
<automated>cd /home/adelorenzo/repos/konstruct && python -m pytest tests/unit/test_web_channel.py tests/unit/test_chat_api.py -x -v</automated>
</verify>
<done>
ChannelType.WEB exists. webchat_response_key function exists. ORM models define web_conversations and web_conversation_messages. Migration 008 creates both tables with RLS and updates channel_type CHECK constraint. All test assertions pass (RED then GREEN).
</done>
</task>
<task type="auto">
<name>Task 2: WebSocket endpoint, web channel adapter, REST API, orchestrator wiring</name>
<files>
packages/gateway/gateway/channels/web.py,
packages/shared/shared/api/chat.py,
packages/shared/shared/api/__init__.py,
packages/gateway/gateway/main.py,
packages/orchestrator/orchestrator/tasks.py
</files>
<action>
1. Create packages/gateway/gateway/channels/web.py with:
a. normalize_web_event() function: takes dict with {text, tenant_id, agent_id, user_id, display_name, conversation_id} and returns KonstructMessage with channel=ChannelType.WEB, thread_id=conversation_id, sender.user_id=user_id (portal user UUID string), channel_metadata={portal_user_id, tenant_id, conversation_id}
b. WebSocket endpoint at /chat/ws/{conversation_id}:
- Accept connection
- Wait for first JSON message with type="auth" containing {userId, role, tenantId} (browser cannot send custom headers — Pitfall 1 from RESEARCH.md)
- Validate auth: userId must be non-empty UUID string, role must be valid
- For each subsequent message (type="message"):
* Immediately send {"type": "typing"} back to client (CHAT-05)
* Normalize message to KonstructMessage via normalize_web_event
* Save user message to web_conversation_messages table
* Build extras dict: conversation_id, portal_user_id, tenant_id
* Dispatch handle_message.delay(msg.model_dump() | extras)
* Subscribe to Redis pub-sub channel webchat_response_key(tenant_id, conversation_id) with 60s timeout
* When response arrives: save assistant message to web_conversation_messages, send {"type": "response", "text": ..., "conversation_id": ...} to WebSocket
- On disconnect: unsubscribe and close Redis connections
c. Create an APIRouter with the WebSocket route for mounting
2. Create packages/shared/shared/api/chat.py with REST endpoints:
a. GET /api/portal/chat/conversations?tenant_id={id} — list conversations for the authenticated user within a tenant. For platform_admin: returns conversations across all tenants if no tenant_id. Uses require_tenant_member for RBAC. Returns [{id, agent_id, agent_name, updated_at, last_message_preview}] sorted by updated_at DESC.
b. GET /api/portal/chat/conversations/{id}/messages?limit=50&before={cursor} — paginated message history. Verify caller owns the conversation (same user_id) OR is platform_admin. Returns [{id, role, content, created_at}] ordered by created_at ASC.
c. POST /api/portal/chat/conversations — create or get-or-create conversation. Body: {tenant_id, agent_id}. Uses require_tenant_member. Returns conversation object with id.
d. DELETE /api/portal/chat/conversations/{id} — reset conversation (delete messages, keep row). Updates updated_at. Verify ownership.
All endpoints use Depends(get_portal_caller) and Depends(get_session). Set RLS context var (configure_rls_hook + current_tenant_id.set) before DB queries.
3. Update packages/shared/shared/api/__init__.py: add chat_router to imports and __all__
4. Update packages/gateway/gateway/main.py:
- Import chat_router from shared.api and web channel router from gateway.channels.web
- app.include_router(chat_router) for REST endpoints
- app.include_router(web_chat_router) for WebSocket endpoint
- Add comment block "Phase 6 Web Chat routers"
5. Update packages/orchestrator/orchestrator/tasks.py:
a. In handle_message: pop "conversation_id" and "portal_user_id" before model_validate (same pattern as placeholder_ts, channel_id). Add to extras dict.
b. In _build_response_extras: add "web" case returning {"conversation_id": extras.get("conversation_id"), "tenant_id": extras.get("tenant_id")}. Note: tenant_id for web comes from extras, not from channel_metadata like Slack.
c. In _send_response: add "web" case that publishes to Redis pub-sub:
```python
elif channel_str == "web":
conversation_id = extras.get("conversation_id", "")
tenant_id = extras.get("tenant_id", "")
if not conversation_id or not tenant_id:
logger.warning("_send_response: web channel missing conversation_id or tenant_id")
return
response_channel = webchat_response_key(tenant_id, conversation_id)
publish_redis = aioredis.from_url(settings.redis_url)
try:
await publish_redis.publish(response_channel, json.dumps({
"type": "response", "text": text, "conversation_id": conversation_id,
}))
finally:
await publish_redis.aclose()
```
d. Import webchat_response_key from shared.redis_keys at module level (matches existing import pattern for other keys)
IMPORTANT: WebSocket auth via JSON message after connection (NOT URL params or headers — browser limitation).
IMPORTANT: Redis pub-sub subscribe in WebSocket handler must use try/finally for cleanup (Pitfall 2).
IMPORTANT: The web normalizer must set thread_id = conversation_id (Pitfall 3 — conversation ID scopes memory correctly).
IMPORTANT: For DB access in WebSocket handler, use configure_rls_hook + current_tenant_id context var per existing pattern.
</action>
<verify>
<automated>cd /home/adelorenzo/repos/konstruct && python -m pytest tests/unit/test_web_channel.py tests/unit/test_chat_api.py -x -v</automated>
</verify>
<done>
WebSocket endpoint at /chat/ws/{conversation_id} accepts connections, authenticates via JSON message, dispatches to Celery, subscribes to Redis for response. REST API provides conversation CRUD with RBAC. Orchestrator _send_response handles "web" channel via Redis pub-sub publish. All unit tests pass. Gateway mounts both routers.
</done>
</task>
</tasks>
<verification>
1. All unit tests pass: `pytest tests/unit/test_web_channel.py tests/unit/test_chat_api.py -x`
2. Migration 008 applies cleanly: `cd /home/adelorenzo/repos/konstruct && alembic upgrade head`
3. Gateway starts without errors: `cd /home/adelorenzo/repos/konstruct/packages/gateway && python -c "from gateway.main import app; print('OK')"`
4. Full test suite still green: `pytest tests/unit -x`
</verification>
<success_criteria>
- ChannelType includes WEB
- WebSocket endpoint exists at /chat/ws/{conversation_id}
- REST API at /api/portal/chat/* provides conversation CRUD with RBAC
- _send_response in tasks.py handles "web" channel via Redis pub-sub
- web_conversations and web_conversation_messages tables created with RLS
- All 7+ unit tests pass covering CHAT-01 through CHAT-05
</success_criteria>
<output>
After completion, create `.planning/phases/06-web-chat/06-01-SUMMARY.md`
</output>

325
.planning/phases/06-web-chat/06-02-PLAN.md Normal file
View File

@@ -0,0 +1,325 @@
---
phase: 06-web-chat
plan: 02
type: execute
wave: 2
depends_on: ["06-01"]
files_modified:
- packages/portal/app/(dashboard)/chat/page.tsx
- packages/portal/components/chat-sidebar.tsx
- packages/portal/components/chat-window.tsx
- packages/portal/components/chat-message.tsx
- packages/portal/components/typing-indicator.tsx
- packages/portal/lib/use-chat-socket.ts
- packages/portal/lib/queries.ts
- packages/portal/lib/api.ts
- packages/portal/components/nav.tsx
- packages/portal/package.json
autonomous: true
requirements:
- CHAT-01
- CHAT-03
- CHAT-04
- CHAT-05
must_haves:
truths:
- "User can navigate to /chat from the sidebar and see a conversation list"
- "User can select an agent and start a new conversation"
- "User can type a message and see it appear as a right-aligned bubble"
- "Agent response appears as a left-aligned bubble with markdown rendering"
- "Typing indicator (animated dots) shows while waiting for agent response"
- "Conversation history loads when user returns to a previous conversation"
- "Operator, customer admin, and platform admin can all access /chat"
artifacts:
- path: "packages/portal/app/(dashboard)/chat/page.tsx"
provides: "Main chat page with sidebar + active conversation"
min_lines: 50
- path: "packages/portal/components/chat-sidebar.tsx"
provides: "Conversation list with agent names and timestamps"
contains: "ChatSidebar"
- path: "packages/portal/components/chat-window.tsx"
provides: "Active conversation with message list, input, and send button"
contains: "ChatWindow"
- path: "packages/portal/components/chat-message.tsx"
provides: "Message bubble with markdown rendering and role-based alignment"
contains: "ChatMessage"
- path: "packages/portal/components/typing-indicator.tsx"
provides: "Animated typing dots component"
contains: "TypingIndicator"
- path: "packages/portal/lib/use-chat-socket.ts"
provides: "React hook managing WebSocket lifecycle"
contains: "useChatSocket"
key_links:
- from: "packages/portal/lib/use-chat-socket.ts"
to: "packages/gateway/gateway/channels/web.py"
via: "WebSocket connection to /chat/ws/{conversationId}"
pattern: "new WebSocket"
- from: "packages/portal/app/(dashboard)/chat/page.tsx"
to: "packages/portal/lib/queries.ts"
via: "useConversations + useConversationHistory hooks"
pattern: "useConversations|useConversationHistory"
- from: "packages/portal/components/nav.tsx"
to: "packages/portal/app/(dashboard)/chat/page.tsx"
via: "Nav link to /chat"
pattern: 'href.*"/chat"'
---
<objective>
Build the complete portal chat UI: a dedicated /chat page with conversation sidebar, message window with markdown rendering, typing indicators, and WebSocket integration. Users can start conversations with AI Employees, see real-time responses, and browse conversation history.
Purpose: Delivers the user-facing chat experience that connects to the backend infrastructure from Plan 01.
Output: Fully interactive chat page in the portal with all CHAT requirements addressed.
</objective>
<execution_context>
@/home/adelorenzo/.claude/get-shit-done/workflows/execute-plan.md
@/home/adelorenzo/.claude/get-shit-done/templates/summary.md
</execution_context>
<context>
@.planning/PROJECT.md
@.planning/ROADMAP.md
@.planning/STATE.md
@.planning/phases/06-web-chat/06-CONTEXT.md
@.planning/phases/06-web-chat/06-RESEARCH.md
@.planning/phases/06-web-chat/06-01-SUMMARY.md
<interfaces>
<!-- From Plan 01 — backend contracts the frontend connects to -->
WebSocket endpoint: ws://localhost:8001/chat/ws/{conversationId}
Protocol:
1. Client connects
2. Client sends: {"type": "auth", "userId": "uuid", "role": "role_string", "tenantId": "uuid|null"}
3. Client sends: {"type": "message", "text": "user message"}
4. Server sends: {"type": "typing"} (immediate)
5. Server sends: {"type": "response", "text": "agent reply", "conversation_id": "uuid"}
REST API:
GET /api/portal/chat/conversations?tenant_id={id}
-> [{id, agent_id, agent_name, updated_at, last_message_preview}]
GET /api/portal/chat/conversations/{id}/messages?limit=50&before={cursor}
-> [{id, role, content, created_at}]
POST /api/portal/chat/conversations
Body: {tenant_id, agent_id}
-> {id, tenant_id, agent_id, user_id, created_at, updated_at}
DELETE /api/portal/chat/conversations/{id}
-> 204
From packages/portal/lib/api.ts:
```typescript
export function setPortalSession(session: {...}): void;
function getAuthHeaders(): Record<string, string>;
const api = { get<T>, post<T>, put<T>, delete };
```
From packages/portal/lib/queries.ts:
```typescript
export const queryKeys = { tenants, agents, ... };
export function useAgents(tenantId: string): UseQueryResult<Agent[]>;
export function useTenants(page?: number): UseQueryResult<TenantsListResponse>;
// ADD: useConversations, useConversationHistory, useCreateConversation, useDeleteConversation
```
From packages/portal/components/nav.tsx:
```typescript
const navItems: NavItem[] = [
{ href: "/dashboard", ... },
{ href: "/agents", label: "Employees", ... },
// ADD: { href: "/chat", label: "Chat", icon: MessageSquare }
// Visible to ALL roles (no allowedRoles restriction)
];
```
From packages/portal/proxy.ts:
```typescript
const CUSTOMER_OPERATOR_RESTRICTED = ["/billing", "/settings/api-keys", "/users", "/admin", "/agents/new"];
// /chat is NOT in this list — operators CAN access chat (per CONTEXT.md: "chatting IS the product")
```
</interfaces>
</context>
<tasks>
<task type="auto">
<name>Task 1: Install dependencies, add API types/hooks, create WebSocket hook</name>
<files>
packages/portal/package.json,
packages/portal/lib/api.ts,
packages/portal/lib/queries.ts,
packages/portal/lib/use-chat-socket.ts
</files>
<action>
1. Install react-markdown and remark-gfm:
`cd packages/portal && npm install react-markdown remark-gfm`
2. Add chat types to packages/portal/lib/api.ts (at the bottom, after existing types):
```typescript
// Chat types
export interface Conversation {
id: string;
agent_id: string;
agent_name: string;
updated_at: string;
last_message_preview: string | null;
}
export interface ConversationMessage {
id: string;
role: "user" | "assistant";
content: string;
created_at: string;
}
export interface CreateConversationRequest {
tenant_id: string;
agent_id: string;
}
export interface ConversationDetail {
id: string;
tenant_id: string;
agent_id: string;
user_id: string;
created_at: string;
updated_at: string;
}
```
3. Add chat hooks to packages/portal/lib/queries.ts:
- Add to queryKeys: conversations(tenantId) and conversationHistory(conversationId)
- useConversations(tenantId: string) — GET /api/portal/chat/conversations?tenant_id={tenantId}, returns Conversation[], enabled: !!tenantId
- useConversationHistory(conversationId: string) — GET /api/portal/chat/conversations/{conversationId}/messages, returns ConversationMessage[], enabled: !!conversationId
- useCreateConversation() — POST mutation to /api/portal/chat/conversations, invalidates conversations query on success
- useDeleteConversation() — DELETE mutation, invalidates conversations + history queries
Follow the exact same pattern as useAgents, useCreateAgent, etc.
4. Create packages/portal/lib/use-chat-socket.ts:
- "use client" directive at top
- useChatSocket({ conversationId, onMessage, onTyping, authHeaders }) hook
- authHeaders: { userId: string; role: string; tenantId: string | null }
- On mount: create WebSocket to `${NEXT_PUBLIC_WS_URL ?? "ws://localhost:8001"}/chat/ws/${conversationId}`
- On open: send auth JSON message immediately
- On message: parse JSON, if type="typing" call onTyping(true), if type="response" call onTyping(false) then onMessage(data.text)
- send(text: string) function: sends {"type": "message", "text": text} if connected
- Return { send, isConnected }
- On unmount/conversationId change: close WebSocket (useEffect cleanup)
- Simple reconnect: on close, attempt reconnect after 3s (limit to 3 retries, then show error)
- Use useRef for WebSocket instance, useState for isConnected
- Use useCallback for send to keep stable reference
IMPORTANT: Read packages/portal/node_modules/next/dist/docs/ for any relevant Next.js 16 patterns before writing code.
IMPORTANT: Use NEXT_PUBLIC_WS_URL env var (not NEXT_PUBLIC_API_URL) — WebSocket URL may differ from REST API URL.
IMPORTANT: Auth message sent as first JSON payload after connection (browser WebSocket cannot send custom headers).
</action>
<verify>
<automated>cd /home/adelorenzo/repos/konstruct/packages/portal && npx next build 2>&1 | tail -20</automated>
</verify>
<done>
react-markdown and remark-gfm installed. Chat types exported from api.ts. Four query hooks (useConversations, useConversationHistory, useCreateConversation, useDeleteConversation) added to queries.ts. useChatSocket hook manages WebSocket lifecycle with auth and reconnection. Portal builds without errors.
</done>
</task>
<task type="auto">
<name>Task 2: Chat page, components, nav link, and styling</name>
<files>
packages/portal/app/(dashboard)/chat/page.tsx,
packages/portal/components/chat-sidebar.tsx,
packages/portal/components/chat-window.tsx,
packages/portal/components/chat-message.tsx,
packages/portal/components/typing-indicator.tsx,
packages/portal/components/nav.tsx
</files>
<action>
1. Create packages/portal/components/typing-indicator.tsx:
- "use client" component
- Three animated dots with CSS animation (scale/opacity pulsing with staggered delays)
- Wrapped in a message-bubble-style container (left-aligned, muted background)
- Use Tailwind animate classes or inline keyframes
2. Create packages/portal/components/chat-message.tsx:
- "use client" component
- Props: { role: "user" | "assistant"; content: string; createdAt: string }
- User messages: right-aligned, primary color background, white text
- Assistant messages: left-aligned, muted background, with agent avatar icon (Bot from lucide-react)
- Render content with react-markdown + remark-gfm for assistant messages (code blocks, lists, bold, links)
- User messages: plain text (no markdown rendering needed)
- Show timestamp in relative format (e.g., "2m ago") on hover or below message
- Inline image display for any markdown image links in agent responses
3. Create packages/portal/components/chat-sidebar.tsx:
- "use client" component
- Props: { conversations: Conversation[]; activeId: string | null; onSelect: (id: string) => void; onNewChat: () => void }
- "New Conversation" button at top (Plus icon from lucide-react)
- Scrollable list of conversations showing: agent name (bold), last message preview (truncated, muted), relative timestamp
- Active conversation highlighted with accent background
- Empty state: "No conversations yet"
4. Create packages/portal/components/chat-window.tsx:
- "use client" component
- Props: { conversationId: string; authHeaders: { userId, role, tenantId } }
- Uses useConversationHistory(conversationId) for initial load
- Uses useChatSocket for real-time messaging
- State: messages array (merged from history + new), isTyping boolean, inputText string
- On history load: populate messages from query data
- On WebSocket message: append to messages array, scroll to bottom
- On typing indicator: show TypingIndicator below last message
- Input area at bottom: textarea (auto-growing, max 4 lines) + Send button (SendHorizontal icon from lucide-react)
- Send on Enter (Shift+Enter for newline), clear input after send
- Auto-scroll to bottom on new messages (use ref + scrollIntoView)
- Show "Connecting..." state when WebSocket not connected
- Empty state when no conversationId selected: "Select a conversation or start a new one"
5. Create packages/portal/app/(dashboard)/chat/page.tsx:
- "use client" component
- Layout: flex row, full height (h-[calc(100vh-4rem)] or similar to fill dashboard area)
- Left: ChatSidebar (w-80, border-right)
- Right: ChatWindow (flex-1)
- State: activeConversationId (string | null), showAgentPicker (boolean)
- On mount: load conversations via useConversations(activeTenantId)
- For platform admin: use tenant switcher pattern — show all tenants, load agents per tenant
- "New Conversation" flow: show agent picker dialog (Dialog from shadcn base-ui). List agents from useAgents(tenantId). On agent select: call useCreateConversation, set activeConversationId to result.id
- URL state: sync activeConversationId to URL search param ?id={conversationId} for bookmark/refresh support
- Get auth headers from session (useSession from next-auth/react) — userId, role, activeTenantId
6. Update packages/portal/components/nav.tsx:
- Import MessageSquare from lucide-react
- Add { href: "/chat", label: "Chat", icon: MessageSquare } to navItems array
- Position after "Employees" and before "Usage"
- No allowedRoles restriction (all roles can chat per CONTEXT.md)
The chat should feel like a modern messaging app (Slack DMs / iMessage style) — not a clinical chatbot widget. Clean spacing, smooth scrolling, readable typography.
IMPORTANT: Use standardSchemaResolver (not zodResolver) if any forms are needed (per STATE.md convention).
IMPORTANT: use(searchParams) pattern for reading URL params in client components (Next.js 15/16 convention).
IMPORTANT: base-ui DialogTrigger uses render prop not asChild (per Phase 4 STATE.md decision).
</action>
<verify>
<automated>cd /home/adelorenzo/repos/konstruct/packages/portal && npx next build 2>&1 | tail -20</automated>
</verify>
<done>
Chat page renders at /chat with sidebar (conversation list) and main panel (active conversation). New Conversation button opens agent picker dialog. Messages display with role-based alignment and markdown rendering. Typing indicator animates during response wait. Nav sidebar includes Chat link visible to all roles. Portal builds without errors.
</done>
</task>
</tasks>
<verification>
1. Portal builds: `cd packages/portal && npx next build`
2. Chat page accessible at /chat after login
3. Nav shows "Chat" link for all roles
4. No TypeScript errors in new files
</verification>
<success_criteria>
- /chat page renders with left sidebar and right conversation panel
- New Conversation flow: agent picker -> create conversation -> WebSocket connect
- Messages render with markdown (assistant) and plain text (user)
- Typing indicator shows animated dots during response generation
- Conversation history loads from REST API on page visit
- WebSocket connects and authenticates via JSON auth message
- Nav includes Chat link visible to all three roles
- Portal builds successfully
</success_criteria>
<output>
After completion, create `.planning/phases/06-web-chat/06-02-SUMMARY.md`
</output>

119
.planning/phases/06-web-chat/06-03-PLAN.md Normal file
View File

@@ -0,0 +1,119 @@
---
phase: 06-web-chat
plan: 03
type: execute
wave: 2
depends_on: ["06-01", "06-02"]
files_modified: []
autonomous: false
requirements:
- CHAT-01
- CHAT-02
- CHAT-03
- CHAT-04
- CHAT-05
must_haves:
truths:
- "End-to-end chat works: user sends message via WebSocket, receives LLM response"
- "Conversation history persists and loads on page revisit"
- "Typing indicator appears during response generation"
- "Markdown renders correctly in agent responses"
- "RBAC enforced: operator can chat, but cannot see admin-only nav items"
- "Platform admin can chat with agents across tenants"
artifacts: []
key_links: []
---
<objective>
Human verification of the complete web chat feature. Test end-to-end flow, RBAC enforcement, conversation persistence, and UX quality.
Purpose: Confirm all CHAT requirements are met before marking Phase 6 complete.
Output: Verified working chat feature.
</objective>
<execution_context>
@/home/adelorenzo/.claude/get-shit-done/workflows/execute-plan.md
@/home/adelorenzo/.claude/get-shit-done/templates/summary.md
</execution_context>
<context>
@.planning/phases/06-web-chat/06-01-SUMMARY.md
@.planning/phases/06-web-chat/06-02-SUMMARY.md
</context>
<tasks>
<task type="checkpoint:human-verify" gate="blocking">
<name>Task 1: Verify end-to-end web chat feature</name>
<files></files>
<action>
Present the following verification checklist to the user. This is a human verification checkpoint — no code changes needed.
What was built:
- WebSocket-based real-time chat in the portal at /chat
- Conversation sidebar with agent list, timestamps, message previews
- Message bubbles with markdown rendering and typing indicators
- Full agent pipeline integration (memory, tools, escalation, audit)
- Conversation history persistence in PostgreSQL
- RBAC enforcement (all roles can chat, scoped to accessible tenants)
Prerequisites:
- Docker Compose stack running (gateway, orchestrator, portal, postgres, redis)
- At least one active agent configured for a tenant
- Migration applied: `alembic upgrade head`
Test 1 — Basic Chat (CHAT-01, CHAT-05):
1. Log in to portal as customer_admin
2. Click "Chat" in the sidebar navigation
3. Click "New Conversation" and select an AI Employee
4. Type a message and press Enter
5. Verify: typing indicator (animated dots) appears immediately
6. Verify: agent response appears as a left-aligned message bubble
7. Verify: your message appears right-aligned
Test 2 — Markdown Rendering (CHAT-05):
1. Send a message that triggers a formatted response (e.g., "Give me a bulleted list of 3 tips")
2. Verify: response renders with proper markdown (bold, lists, code blocks)
Test 3 — Conversation History (CHAT-03):
1. After sending a few messages, navigate away from /chat (e.g., go to /dashboard)
2. Navigate back to /chat
3. Verify: previous conversation appears in sidebar with last message preview
4. Click the conversation
5. Verify: full message history loads (all previous messages visible)
Test 4 — RBAC (CHAT-04):
1. Log in as customer_operator
2. Verify: "Chat" link visible in sidebar
3. Navigate to /chat, start a conversation with an agent
4. Verify: chat works (operators can chat)
5. Verify: admin-only nav items (Billing, API Keys, Users) are still hidden
Test 5 — Full Pipeline (CHAT-02):
1. If the agent has tools configured, send a message that triggers tool use
2. Verify: agent invokes the tool and incorporates the result
3. (Optional) If escalation rules are configured, trigger one and verify handoff message
</action>
<verify>Human confirms all 5 test scenarios pass</verify>
<done>User types "approved" confirming end-to-end web chat works correctly across all CHAT requirements</done>
</task>
</tasks>
<verification>
All 5 test scenarios pass as described above.
</verification>
<success_criteria>
- Human confirms end-to-end chat works with real LLM responses
- Conversation history persists across page navigations
- Typing indicator visible during response generation
- Markdown renders correctly
- RBAC correctly scopes agent access
- All three roles (platform_admin, customer_admin, customer_operator) can chat
</success_criteria>
<output>
After completion, create `.planning/phases/06-web-chat/06-03-SUMMARY.md`
</output>