The 45s timeout was too short for generation tasks with full flow
context in the system prompt. The Anthropic SDK's default 2 retries
caused requests to hang for ~136s before failing. Now: 120s timeout
with max 1 retry = faster failure if it does timeout.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Both editors now send name and description alongside the flow structure,
so the AI can reference what the flow is about when responding.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The AI panel now sends the current tree structure (troubleshooting) or
steps + intake form (procedural/maintenance) with each message. This
gives the AI full visibility into node details, questions, descriptions,
options, and intake form fields — not just the node ID.
- Backend: add flow_context param to schema, endpoint, and service
- Frontend: add getFlowContext callback to useEditorAI hook
- TreeEditorPage: passes treeStructure as flow context
- ProceduralEditorPage: passes steps + intakeForm as flow context
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The dated model ID `claude-sonnet-4-6-20250514` was causing 502 errors.
Use the alias `claude-sonnet-4-6` which matches AI_MODEL_ANTHROPIC.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove the old /ai/chat page, AI wizard modal, and all associated
components/stores/types now replaced by the editor-embedded AI panel.
Deleted:
- AIChatBuilderPage, ai-chat/ components, aiChatStore, aiChat API, ai-chat types
- AIFlowBuilderModal, ai-builder/ components, aiFlowBuilderStore
Cleaned up:
- Router (removed /ai/chat route)
- Sidebar (removed Flow Assist nav item)
- MyTreesPage (removed AI builder modal and button)
- TreeLibraryPage (removed Flow Assist button)
- API and type barrel exports
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Use .glass-card-static on AIPromptDialog card for consistent design system
- Add "Build with Flow Assist" button to maintenance section in CreateFlowDropdown
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace navigation to /ai/chat with an inline AIPromptDialog modal
that collects a single prompt, generates a flow via the editor AI API,
imports it, and navigates to the editor with the AI panel open.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Update get_ai_provider() to accept an optional model override parameter
(applied only to AnthropicProvider; Gemini always uses its own model).
Thread action_type-based model resolution through send_message() and
generate_final_tree() in the AI chat service.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add VALID_ACTION_TYPES literal and action_type/focal_node_id fields to
AIChatMessageRequest schema
- Add tree_id field to AIChatStartRequest schema for editor-embedded sessions
- Update send_message() signature with action_type and focal_node_id params
- Update start_chat_session() signature with tree_id param
- Pass new params through endpoints to service functions
- All new params have defaults so existing behavior is unchanged
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add tree_id FK (CASCADE) for editor-embedded sessions and archived_at
timestamp column to ai_chat_sessions table.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
AI-generated trees use descriptive IDs (e.g., "verify-account-exists")
instead of "root", causing the root node to be falsely flagged as orphaned.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Design for replacing the standalone /ai/chat page with context-aware
AI side panels embedded in each editor (Troubleshooting + Procedural).
Covers ghost node suggestion system, output-based thresholds,
config-driven model routing, knowledge integration, and per-flow
chat persistence.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Default AI_PROVIDER changed from gemini to anthropic
- AI_MODEL and AI_MODEL_ANTHROPIC updated to claude-sonnet-4-6
- Added "Shift + Enter for a new line" hint below all chat textareas
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- CreateFlowDropdown now shows "Build with Flow Assist" under each flow type
- Library page "Flow Assist" button respects current type filter
- Clean up unused AIFlowBuilderModal references
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add procedural-specific system prompts (schema, interview protocol, response format)
- Dispatch prompts by flow_type: procedural/maintenance use flat steps schema, troubleshooting uses decision tree schema
- Parse [STEPS_UPDATE] and [INTAKE_FORM] markers in AI responses
- Add validate_generated_procedural_steps() validator
- Handle intake form extraction in AI chat import endpoint
- Add StaticStepsPreview component for procedural flow preview
- Update store and page to render correct preview by flow type
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove XML builder, format query param, and XML tests
- Simplify ExportFlowModal (no format picker)
- Simplify rfflowParser (JSON-only)
- Remove format field from schemas and types
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add .rfflow file export/import support:
- Migration 050: import_metadata JSONB column on trees
- GET /trees/{id}/export?format=json|xml endpoint
- POST /trees/import endpoint (creates draft, resolves categories/tags)
- FlowExportEnvelope, FlowImportRequest/Response schemas
- import_metadata field on TreeResponse
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: increase assistant chat input height from 1 to 3 rows
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add Anthropic prompt caching to assistant chat
Cache the static system prompt and conversation history prefix across
turns, reducing input token costs by ~80% on multi-turn conversations.
RAG context is intentionally uncached since it changes per query.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add Microsoft Learn MCP integration + refine assistant system prompt
- Integrate Microsoft Learn MCP server via Anthropic's MCP connector
for real-time documentation lookups (docs search, fetch, code samples)
- Refine system prompt: clear persona, structured answer guidelines,
when to use RAG flows vs Microsoft Learn, guardrails against fabrication
- Add ENABLE_MCP_MICROSOFT_LEARN config toggle (default: True)
- Fix bugs from prior edit: wrong MCP URL, broken indentation, undefined
usage/token variables, NOT_GIVEN for disabled MCP params
- Log MCP tool usage and cache performance
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: AI chat session conclusion + survey completion & management
AI Assistant - Conclude Session:
- 3-step modal: select outcome (resolved/escalated/paused), add notes, AI-generated summary
- AI generates structured ticket notes from conversation transcript (PSA-ready format)
- Copy to clipboard for pasting into ticketing systems
- "Resume in New Chat" for paused sessions (pre-loads context into new chat)
- Backend: POST /chats/{id}/conclude endpoint, conclusion_summary/outcome/concluded_at fields
- Migration 048: add conclusion fields to assistant_chats
Survey Completion Flow:
- Email-to-self option after submission (branded HTML email with formatted responses)
- Finish button navigates to /survey/thank-you page
- Thank you page with close-window message and feedback email callout
- Already-submitted state updated with same messaging
- Backend: POST /survey/email-copy public endpoint
Survey Admin Management:
- Read/unread indicators (cyan dot, bold name, auto-mark on expand)
- Unread count stat card
- Per-row context menu: mark read/unread, archive/unarchive, delete
- Bulk actions bar: select all, mark read/unread, archive, delete
- Show Archived toggle to filter archived responses
- Backend: 7 new admin endpoints (read, unread, archive, unarchive, delete, bulk)
- Migration 049: add is_read, archived_at to survey_responses
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: initialize VerifyEmailPage state from token to avoid setState in effect
Moves the no-token error case from useEffect into initial state to satisfy
the react-hooks/set-state-in-effect ESLint rule.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Bump migration count to 49
- Add chat conclusion and survey management to recently completed
- Add lessons #41-43: assistant chat state pattern, public page fetch pattern, EmailService pattern
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Integrate Microsoft Learn MCP server via Anthropic's MCP connector
for real-time documentation lookups (docs search, fetch, code samples)
- Refine system prompt: clear persona, structured answer guidelines,
when to use RAG flows vs Microsoft Learn, guardrails against fabrication
- Add ENABLE_MCP_MICROSOFT_LEARN config toggle (default: True)
- Fix bugs from prior edit: wrong MCP URL, broken indentation, undefined
usage/token variables, NOT_GIVEN for disabled MCP params
- Log MCP tool usage and cache performance
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Cache the static system prompt and conversation history prefix across
turns, reducing input token costs by ~80% on multi-turn conversations.
RAG context is intentionally uncached since it changes per query.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Use CAST(:embedding AS vector) instead of :embedding::vector to avoid
SQLAlchemy named param conflict with PostgreSQL :: cast syntax
- Add db.rollback() before recording AI usage on failure to prevent
InFailedSQLTransactionError cascade
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move completed plan docs to docs/plans/archive/. Add survey migration 046
and reference HTML/plan files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
