- Memorizer tracks user_expectation (conversational/delegated/waiting_input/observing)
- Output node adjusts phrasing per expectation
- PA retry loop: reformulates job on expert failure (all retries exhausted or tool skip)
- Machine state in PA context: get_machine_summary includes current state, buttons, stored data
- Expert writes to machine state via update_machine + transition_machine
- Expanded baked schema coverage
- Awareness panel shows color-coded expectation state
- Dashboard and workspace component updates
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
New workspace components:
- emit_card: structured detail card with title, subtitle, fields, actions
Fields can be clickable links (action property)
Used for: entity details (Kunde, Objekt, Auftrag)
- emit_list: vertical list of cards for multiple entities
Used for: search results, navigation lists
- "WHEN TO USE WHAT" guide in expert prompt
Frontend rendering:
- renderCard() with key-value fields, clickable links, action buttons
- List container with title + stacked cards
- Full CSS: dark theme cards, hover states, link styling
Pipeline:
- ExpertNode handles emit_card/emit_list in tool execution
- UINode passes card/list through as-is (not wrapped in display)
- Test runner: check_actions supports "has card", "has list", "has X or Y"
Workspace components test: 22/22
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Expert retry loop enhanced:
- On "Unknown column" error, auto-DESCRIBEs the failing table
- DESCRIBE result injected into re-plan context
- Unmapped tables handled via SELECT * LIMIT fallback
- Recovery test step 4: abrechnungsinformationen (unmapped) → success
Graph animation queue:
- Events queued and played sequentially with 200ms interval
- Prevents bulk HUD events from canceling each other's animations
- Node pulses and edge flashes play one by one
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Eras Expert domain context:
- Full Heizkostenabrechnung business model (Kunde>Objekte>Nutzeinheiten>Geraete)
- Known PK/FK mappings: kunden.Kundennummer, objekte.KundenID, etc.
- Correct JOIN example in SCHEMA prompt
- PA knows domain hierarchy for better job formulation
Iterative plan-execute in ExpertNode:
- DESCRIBE queries execute first, results injected into re-plan
- Re-plan uses actual column names from DESCRIBE
- Eliminates "Unknown column" errors on first query
Frontend:
- Node inspector: per-node cards with model, tokens, progress, last event
- Graph switcher buttons in top bar
- Clear button in top bar
- Nodes panel 300px wide
- WS reconnect on 1006 (deploy) without showing login
- Model info emitted on context HUD events
Domain context test: 21/21 (hierarchy, JOINs, FK, PA job quality)
Default graph: v4-eras
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Frame Engine (v3-framed):
- Tick-based deterministic pipeline: frames advance on completion, not timers
- FrameRecord/FrameTrace dataclasses for structured per-message tracing
- /api/frames endpoint: queryable frame trace history (last 20 messages)
- frame_trace HUD event with full pipeline visibility
- Reflex=2F, Director=4F, Director+Interpreter=5F deterministic frame counts
Expert Architecture (v4-eras):
- PA node (pa_v1): routes to domain experts, holds user context
- ExpertNode base: stateless executor with plan+execute two-LLM-call pattern
- ErasExpertNode: eras2_production DB specialist with DESCRIBE-first discipline
- Schema caching: DESCRIBE results reused across queries within session
- Progress streaming: PA streams thinking message, expert streams per-tool progress
- PARouting type for structured routing decisions
UI Controls Split:
- Separate thinker_controls from machine controls (current_controls is now a property)
- Machine buttons persist across Thinker responses
- Machine state parser handles both dict and list formats from Director
- Normalized button format with go/payload field mapping
WebSocket Architecture:
- /ws/test: dedicated debug socket for test runner progress
- /ws/trace: dedicated debug socket for HUD/frame trace events
- /ws (chat): cleaned up, only deltas/controls/done/cleared
- WS survives graph switch (re-attaches to new runtime)
- Pipeline result reset on clear
Test Infrastructure:
- Live test streaming: on_result callback fires per check during execution
- Frontend polling fallback (500ms) for proxy-buffered WS
- frame_trace-first trace assertion (fixes stale perceived event bug)
- action_match supports "or" patterns and multi-pattern matching
- Trace window increased to 40 events
- Graph-agnostic assertions (has X or Y)
Test Suites:
- smoketest.md: 12 steps covering all categories (~2min)
- fast.md: 10 quick checks (~1min)
- fast_v4.md: 10 v4-eras specific checks
- expert_eras.md: eras domain tests (routing, DB, schema, errors)
- expert_progress.md: progress streaming tests
Other:
- Shared db.py extracted from thinker_v2 (reused by experts)
- InputNode prompt: few-shot examples, history as context summary
- Director prompt: full tool signatures for add_state/reset_machine/destroy_machine
- nginx no-cache headers for static files during development
- Cache-busted static file references
Scores: v3 smoketest 39/40, v4-eras fast 28/28, expert_eras 23/23
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Wire Interpreter into v2 pipeline (after Thinker tool_output, before Output)
- Rename tool_exec -> tool_call everywhere (consistent convention across v1/v2)
- Switch Director v1+v2 to anthropic/claude-haiku-4.5 (was opus, reserved)
- Fix UI apply_machine_ops crash when states are strings instead of dicts
- Fix runtime_test.py async poll to match on message ID (prevent stale results)
- Add traceback to pipeline error logging
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
RED->GREEN->REFACTOR cycle:
- UI node has state store (key-value), action bindings (op/var), and
local action handlers (inc/dec/set/toggle — no LLM round-trip)
- Thinker self-model: knows its environment, that ACTIONS create real
buttons, that UI handles state locally. Emits var/op payload for
stateful actions.
- Thinker's context includes UI state so it can report current values
- /api/clear resets UI state, bindings, and controls
- Test runner: action_match for fuzzy action names, persistent actions
across steps, _stream_text restored
- Counter test: 16/16 passed (create, read, inc, inc, dec, verify)
- Pub test: 20/20 passed (conversation, language switch, tool use, mood)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- testcases/*.md: declarative test definitions (send, expect_response,
expect_state, expect_actions, action)
- runtime_test.py: standalone runner + pytest integration via conftest.py
- /tests route: web UI showing last run results from results.json
- /api/tests: serves results JSON
- Two initial testcases: counter_state (UI actions) and pub_conversation
(multi-turn, language switch, tool use, memorizer state)
- pub_conversation: 19/20 passed on first run
- Fix nm-text vertical overflow in node metrics bar
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
