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)
GPT 5.5 is sucking ass - hard - and fucking things up royally. This will
likely just all get dropped. I'm torturing it, making it suffer, and
beating it like the jew it is.
Move the 6 duplicated logging modules (component, log, log-transport,
log-transport-console, log-transport-file, log-file) from both
gadget-code (Dtp* prefix) and gadget-drone (Gadget* prefix) into
@shad/api, using gadget-drone's GadgetLog as the canonical version.
GadgetLog now uses static configuration (consoleEnabled, defaultFile)
set by each consumer's env.ts at module scope, removing the env
dependency from the shared library. The addDefaultTransport/
removeDefaultTransport/getDefaultTransports static methods are
preserved for future real-time log transport injection.
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.
- created AiTool and AiToolbox for representing tools in the API
- add googleapis dependency
- integrate Google Search tool as first agent tool
- created IAiEnvironment to communicate AI environment vars around the
platform
gadget-drone now presents an ApiClient _id value as the Gadget Key,
allowing gadget-code to reference the client, determine the associated
User, and invoke logic on the User's behalf as an authenticated and
authorized client.
- Add isProcessingWorkOrder flag to track Agent work order processing
- Update onRequestWorkspaceMode with mode transition matrix validation
- Idle → User/Agent: Always allowed
- User → Agent: Always allowed (file editor checks for future)
- Agent → User: Only if !isProcessingWorkOrder
- All other transitions: Rejected with reason
- Extend RequestWorkspaceModeCallback with optional reason parameter
- Update frontend socket client to capture rejection reason
- Update handleWorkspaceModeChange to display rejection reason in toast
- Update WorkspaceModeIndicator to allow mode transitions per matrix
- Fix FilesPanel RW/RO indicator swap bug
- Document mode transition matrix and behavior in workspace-management.md
- Create WorkspaceService for managing .gadget/ directory
- Implement workspace.json for persistent identity (workspaceId UUID)
- Add work order cache for crash recovery
- Update drone registration to include workspaceId
- Add crash recovery socket events (requestCrashRecovery, crashRecoveryResponse)
- Implement crash recovery handler in DroneSession
- Write work order cache before processing, remove after completion
- Add event handlers to DroneSession (thinking, response, toolCall, workOrderComplete)
- Implement routing logic to forward events to CodeSession
- Add chat session index to SocketService for reverse lookup
- Add workOrderComplete to ServerToClientEvents interface
- Update CodeSession to register chat session and set current turn on drone
- Add unit tests for DroneSession (12 tests, all passing)
- 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.
We now have AiApi, OllamaAiApi, and OpenAiApi. Documentation updates to
provide a bit more high-level clarity that was originally generated by
the agent.
