- Removed auto-invoked syncIndexes() blocks from all 11 model files
(api-client, api-client-log, csrf-token, drone-monitor,
drone-registration, email-log, email-verification, ide-session,
user, web-token, web-visit) — no longer needed
- Fixed drone-session.test.ts by mocking ChatSession.updateOne(),
VectorStoreService.ingestTurn(), and MessageQueue to prevent
real DB connections during tests
- Removed unused mongoose Types import from drone-session test
- All 129 tests now pass across all packages
Phase 1: OpenAI API Token Extraction
- Add stream_options: { include_usage: true } to all streaming API calls
- Capture chunk.usage from final streaming chunks and response.usage from non-streaming
- Extend OpenAiChatIterationResult with optional usage field
- Update buildStats() to accept and return real token counts from usage data
- Wire iteration.usage through chat() to both buildStats() call sites
Phase 2: Agent Loop Stats Propagation
- Rename inputTokens/outputTokens to masterInputTokens/masterOutputTokens, add masterThinkingTokens
- Accumulate response.stats.tokenCounts after each master AI call
- Delete all Math.ceil(length/4) crude approximations (master and subagent loops)
- Track startTime/durationMs and emit IWorkOrderCompleteStats with workOrderComplete
- Subagent loop uses response.stats?.tokenCounts instead of Math.ceil
Phase 3: Database Model Changes
- Add contextWindowUsage field to IChatSession, ChatSessionSchema, and frontend ChatSession
- Initialize contextWindowUsage: 0 on session creation
Phase 4: Persist Stats on Turn Completion
- drone-session: accept IWorkOrderCompleteStats, persist turn stats, walk subagent records for aggregate
- drone-session: $inc session stats and contextWindowUsage, add formatDurationLabel() helper
- code-session: accept and forward stats, update in-memory session stats
- message-queue: Redis replay handles 4th stats arg
- Update WorkOrderCompleteMessage type in @gadget/api to accept stats parameter
Phase 5: UI — Context Window Fuel Gauge
- Add contextWindowUsage prop to SessionPanel
- Add fuel gauge bar with E→F labels, green/yellow/red zones, token count display
- Visible for ALL provider types (not gated by apiType)
Phase 6: Frontend Streaming State
- Add IWorkOrderCompleteStats interface to frontend api.ts
- handleWorkOrderComplete accepts stats, updates turn stats and session contextWindowUsage
- Pass contextWindowUsage prop to SessionPanel
- IChatSession/IChatTurn interfaces: add optional numCtx field
- Mongoose schemas: add numCtx field to ChatSession and ChatTurn
- API controller: validate numCtx (>=16384, multiple of 8192)
- ChatSessionService: persist numCtx on session, pass through to turn
- SessionPanel: add range slider for Context Window (hidden for OpenAI)
- Drone buildDroneModelConfig: prefer turn.numCtx over model defaults
Fixes premature AI API response truncation by propagating inference
parameters through the entire probe → storage → runtime → API call chain.
Root cause: Ollama defaults num_predict to 128 tokens and num_ctx to
4096, silently truncating output and context. We never overrode these.
Changes:
- IAiModelSettings: add numPredict, maxCompletionTokens fields
- IDroneModelConfig: moved from gadget-drone to @gadget/api (shared),
expanded with numPredict, numCtx, maxCompletionTokens params
- IAiModelConfig.params: add numPredict, numCtx, maxCompletionTokens
- IAiModelProbeResult.settings: add numPredict, maxCompletionTokens
- AiModelSettingsSchema (Mongoose): add numPredict, maxCompletionTokens
- Ollama extractSettings(): extract num_predict from model parameters
- Ollama generate()/chat(): pass options: { num_ctx, num_predict }
- OpenAI all three create() calls: add max_completion_tokens
- web-cli.ts onProviderProbe(): compute numPredict (-1 for Ollama)
and maxCompletionTokens (contextWindow for OpenAI) during probe
- agent.ts main + subagent loops: read model settings from provider
cached models, build IDroneModelConfig with stored params
- ai.ts: remove local IDroneModelConfig, import from @gadget/api
- chat-session.ts: add new params to title generation call
- Tests: update all fixtures with new params, all 19 tests pass
Defaults when model settings unavailable:
- numPredict: -1 (Ollama unlimited - generate until natural stop)
- numCtx: 131072 (128k - covers most modern models)
- maxCompletionTokens: 16384 (16k - reasonable OpenAI default)
User Settings will enable User to enter a Persona, or a description of
the User, to be included in the system prompt. This helps calibrate the
agent to better assist the User, and work with the User in ways that
work best for each individual User of the system.
- Resolve duplicate DroneStatus enum (import from @gadget/api)
- Fix IAiProvider interface conflict with DB→runtime mapper
- Add callId to ToolCallMessage and ChatToolCallSchema
- Fix ChatTurnStats schema field name (thinkingTokenCount)
- Add provider/selectedModel to ChatSession interface and model
- Implement CodeSession.onSubmitPrompt() to create ChatTurn and send work orders
- Add drone/chat session tracking to CodeSession
- Add unit tests for CodeSession (9 tests, all passing)
We want to speak only one language when dealing with AI content to
minimize the number of maps, transforms, and copies. This initiative
isn't done, this is a checkpoint along the way while conducting
experiments.
Moved all Mongoose model interfaces to @gadget/api to commonize the data
structures being passed around the system as JSON objects via HTTP and
Socket.IO.
