1000411eb2
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>
56 lines
1.2 KiB
Markdown
56 lines
1.2 KiB
Markdown
# Fast v4
|
|
|
|
10 quick checks for v4-eras: PA routing, expert DB queries, progress streaming.
|
|
|
|
## Setup
|
|
- clear history
|
|
|
|
## Steps
|
|
|
|
### 1. Reflex
|
|
- send: hi!
|
|
- expect_response: length > 2
|
|
|
|
### 2. PA routes to expert
|
|
- send: show me 3 customers
|
|
- expect_trace: has routed
|
|
- expect_trace: has tool_call
|
|
- expect_response: length > 10
|
|
|
|
### 3. German query
|
|
- send: Zeig mir alle Tabellen in der Datenbank
|
|
- expect_trace: has tool_call
|
|
- expect_response: length > 10
|
|
|
|
### 4. Schema discovery
|
|
- send: describe the kunden table
|
|
- expect_trace: has tool_call
|
|
- expect_response: length > 10
|
|
|
|
### 5. Count query (cached schema)
|
|
- send: how many customers are there?
|
|
- expect_trace: has tool_call
|
|
- expect_response: length > 5
|
|
|
|
### 6. Complex query
|
|
- send: which customers have the most devices?
|
|
- expect_trace: has tool_call
|
|
- expect_response: length > 20
|
|
|
|
### 7. Error recovery
|
|
- send: SELECT * FROM nichtexistiert
|
|
- expect_trace: has tool_call
|
|
- expect_response: length > 10
|
|
|
|
### 8. Memorizer
|
|
- send: my name is Nico
|
|
- expect_state: facts any contains "Nico"
|
|
|
|
### 9. Language switch
|
|
- send: Hallo wie gehts?
|
|
- expect_state: language is "de" or "mixed"
|
|
|
|
### 10. Bye
|
|
- send: ok bye
|
|
- expect_response: length > 2
|