mirror of https://github.com/koala73/worldmonitor.git synced 2026-04-25 17:14:57 +02:00

Files

Elie Habib 01f6057389 feat(simulation): MiroFish Phase 2 — theater-limited simulation runner (#2220 )

* feat(simulation): MiroFish Phase 2 — theater-limited simulation runner

Adds the simulation execution layer that consumes simulation-package.json
and produces simulation-outcome.json for maritime chokepoint + energy/logistics
theaters, closing the WorldMonitor → MiroFish handoff loop.

Changes:
- scripts/seed-forecasts.mjs: 2-round LLM simulation runner (prompt builders,
  JSON extractor, runTheaterSimulation, writeSimulationOutcome, task queue
  with NX dedup lock, runSimulationWorker poll loop)
- scripts/process-simulation-tasks.mjs: standalone worker entry point
- proto: GetSimulationOutcome RPC + make generate
- server/worldmonitor/forecast/v1/get-simulation-outcome.ts: RPC handler
- server/gateway.ts: slow tier for get-simulation-outcome
- api/health.js: simulationOutcomeLatest in STANDALONE + ON_DEMAND keys
- tests: 14 new tests for simulation runner functions

* fix(simulation): address P1/P2 code review findings from PR #2220

Security (P1 #018):
- sanitizeForPrompt() applied to all entity/seed fields interpolated into
  Round 1 prompt (entityId, class, stance, seedId, type, timing)
- sanitizeForPrompt() applied to actorId and entityIds in Round 2 prompt
- sanitizeForPrompt() + length caps applied to all LLM array fields written
  to R2 (dominantReactions, stabilizers, invalidators, keyActors, timingMarkers)

Validation (P1 #019):
- Added validateRunId() regex guard
- Applied in enqueueSimulationTask() and processNextSimulationTask() loop

Type safety (P1 #020):
- Added isOutcomePointer() and isPackagePointer() type guards in TS handlers
- Replaced unsafe as-casts with runtime-validated guards in both handlers

Correctness (P2 #022):
- Log warning when pkgPointer.runId does not match task runId

Architecture (P2 #024):
- isMaritimeChokeEnergyCandidate() accepts both flat and nested topBucketId
- Call site simplified to pass theater directly

Performance (P2 #025):
- SIMULATION_ROUND1_MAX_TOKENS raised 1800 to 2200
- Added max 3 initialReactions instruction to Round 1 prompt

Maintainability (P2 #026):
- Simulation pointer keys exported from server/_shared/cache-keys.ts
- Both TS handlers import from shared location

Documentation (P2 #027):
- Strengthened runId no-op description in proto and OpenAPI spec

* fix(todos): add blank lines around lists in markdown todo files

* style(api): reformat openapi yaml to match linter output

* test(simulation): add flat-shape filter test + getSimulationOutcome handler coverage

Two tests identified as missing during PR #2220 review:

1. isMaritimeChokeEnergyCandidate flat-shape tests — covers the || candidate.topBucketId
   normalization added in the P1/P2 review pass. The existing tests only used the nested
   marketContext.topBucketId shape; this adds the flat root-field shape that arrives from
   the simulation-package.json JSON (selectedTheaters entries have topBucketId at root).

2. getSimulationOutcome handler structural tests — verifies the isOutcomePointer guard,
   found:false NOT_FOUND return, found:true success path, note population on runId mismatch,
   and redis_unavailable error string. Follows the readSrc static-analysis pattern used
   elsewhere in server-handlers.test.mjs (handler imports Redis so full integration test
   would require a test Redis instance).

2026-03-25 13:55:59 +04:00

1.7 KiB

Raw Blame History

status, priority, issue_id, tags

status

priority

issue_id

`getForecastLlmCallOptions` has no cases for `simulation_round_1` / `simulation_round_2`

Problem Statement

getForecastLlmCallOptions(stage) maps stage names to provider order and model configuration. Every other pipeline stage (combined, critical_signals, impact_expansion, market_implications, etc.) has its own env override so operators can route that stage to a different model. The simulation runner uses 'simulation_round_1' and 'simulation_round_2' as stage names, but both fall through to the else branch (default provider order). This means simulation stages cannot be independently routed to a more capable reasoning model in Phase 3 without a code change.

Proposed Solution

// In getForecastLlmCallOptions, add cases:
: stage === 'simulation_round_1' || stage === 'simulation_round_2'
    ? (process.env.FORECAST_LLM_SIMULATION_PROVIDER_ORDER
        ? parseForecastProviderOrder(process.env.FORECAST_LLM_SIMULATION_PROVIDER_ORDER)
        : globalProviderOrder || defaultProviderOrder)

This follows the exact pattern of every other named stage. No behavior change until FORECAST_LLM_SIMULATION_PROVIDER_ORDER is set.

Acceptance Criteria

simulation_round_1 and simulation_round_2 have explicit cases in getForecastLlmCallOptions
FORECAST_LLM_SIMULATION_PROVIDER_ORDER env var controls simulation provider order when set
Existing tests pass; no behavior change when env var is unset

Technical Details

File: scripts/seed-forecasts.mjs — getForecastLlmCallOptions (~line 3920)

Work Log

2026-03-24: Found by compound-engineering:review:performance-oracle in PR #2220 review

1.7 KiB Raw Blame History

getForecastLlmCallOptions has no cases for simulation_round_1 / simulation_round_2