Commit Graph

16 Commits

Author SHA1 Message Date
leubeem
d6df3a3ce3 Wire /pm to Python backend for stateful ATC training sessions
Replace the LLM-per-request flow in /pm with a stateful Python backend
(OpenSquawk-LiveATC-api). The backend owns session state, does regex-first
routing with readback evaluation, and returns the next state + ATC speech.
The frontend keeps its local cursor (communicationsEngine) for TTS and
monitoring UI, but no longer calls /api/llm/decide.

Changes:

app/composables/useRadioBackend.ts (new)
  Typed Nuxt composable wrapping the Python REST API:
  createSession, transmit, deleteSession, fetchFlows.
  Base URL read from NUXT_PUBLIC_RADIO_BACKEND_URL (default 127.0.0.1:8000).

nuxt.config.ts
  Expose radioBackendUrl as a public runtime config key so the composable
  and communicationsEngine can both reach the Python backend.

shared/utils/communicationsEngine.ts
  - fetchRuntimeTree now accepts an optional baseUrl so it fetches from the
    Python backend instead of the Nuxt server when a URL is provided.
  - renderTpl handles both {var} (old MongoDB schema) and {{var}} (new YAML
    schema) — double-brace matched first to avoid partial matches.
  - stateSayTpl / stateUtteranceTpl helpers unify say_tpl|say_template and
    utterance_tpl|expected_pilot_template across both schema versions.
  - auto_transitions from the new YAML schema are included when collecting
    eligible transitions in collectAtcStatesUntilPilotTurn.

shared/types/decision.ts
  RuntimeDecisionState extended with say_template and expected_pilot_template
  fields (new YAML schema field names alongside the existing legacy names).

app/pages/pm.vue
  - startMonitoring: loads tree from Python backend, then creates a backend
    session (backendSessionId). Cursor synced to session.current_state.
  - handlePilotTransmission: calls radioBackend.transmit instead of
    /api/llm/decide. Applies auto_advanced_states via moveToSilent, then
    the final state. Speaks controller_say_template via TTS.
  - Both fetchRuntimeTree calls now pass radioBackendUrl so they hit the
    Python backend, not the Nuxt flow-from-MongoDB path.

AGENTS.md (new)
  Project guide updated to document the new two-backend architecture,
  the Python backend session lifecycle, and the dual template schema.

docs/plans/2026-05-06-pm-python-runtime-contract.md (new)
  Implementation plan and API contract written before the work started.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-09 17:49:28 +02:00
itsrubberduck
54c1b47dc2 fix typescript errors and update dependencies 2026-02-17 18:13:04 +01:00
itsrubberduck
6f060d0ddd fix pm 2026-02-13 08:50:02 +01:00
Remi
d9ca19404a Add simple auto flow evaluation for communication engine 2025-10-14 12:02:49 +02:00
Remi
fbec5c4830 Add session timeline logging and admin sessions view 2025-09-21 23:08:10 +02:00
Remi
6c9f467b94 Enable flow-aware decision routing 2025-09-21 21:16:33 +02:00
Remi
526f74c3b1 Build decision flow editor and runtime integration 2025-09-20 18:33:32 +02:00
Remi
df68719374 refactor: centralize radio speech normalization 2025-09-19 09:20:04 +02:00
Remi
d4521c87c6 Translate pilot monitoring and learn pages 2025-09-19 08:54:57 +02:00
Remi
03b86ae637 Add ATIS quick actions and airport frequency data 2025-09-18 18:16:40 +02:00
Remi
80ccaaf297 Add automated flight simulation trace for pilot monitoring 2025-09-17 15:56:09 +02:00
Remi
19f253f53e Implement authentication, waitlist, and logging upgrades 2025-09-16 17:28:34 +02:00
itsrubberduck
a7eebf0baf refactor: update OpenAI TTS integration and cleanup imports
- index.vue: comment out cockpit simulator image
- learn.vue: remove unused imports (useRadioTTS, learnModules)
- atc/say.post.ts & utils/normalize.ts: rename openaiOld → normalize, adjust TTS calls, skip ensureDir/writeFile
- communicationsEngine.ts: fix atcDecisionTree import path
2025-09-16 16:14:12 +02:00
Remi
8abd011514 Refine pilot monitoring communication flow 2025-09-16 15:48:00 +02:00
itsrubberduck
1e3994f3ce The system now intelligently handles edge cases while maintaining the core decision tree structure. The LLM will follow the schema when possible but can respond naturally when the pilot says something unexpected, making it much more realistic and flexible for training scenarios 2025-09-16 12:38:15 +02:00
itsrubberduck
f72d5b22b8 new version of pm using decision tree 2025-09-16 12:23:32 +02:00