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)
The Chat View area of the view was growing in width (unbounded), and has
been fixed. From the agent:
> The root cause was a flexbox sizing rule: in ChatSessionView.tsx:768
the parent row flex-1 flex bg-bg-primary overflow-hidden relative has
two children — the content area and the sidebar. The content area (line
777) was flex-1 flex flex-col relative, which as a flex child defaults
to min-width: auto. This means its intrinsic content width (driven by
the wide <pre>) is used as a minimum, forcing the flex item to expand
the whole row beyond the viewport.
>
> Adding min-w-0 overrides min-width: auto to min-width: 0, letting the
flex item shrink below its content's natural width. Now the
overflow-x-auto on the markdown wrapper actually has somewhere to scroll
into.
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.
Replace the broken provider/model <select> elements (which sent empty model
on provider change, rejected by backend) with a cog-icon-driven edit flow:
- Default view shows current provider/model as text labels with a cog icon
- Clicking cog enters edit mode with <select> elements + checkmark/cancel
- Save atomically sends both provider and model; Save disabled until both set
- Cancel restores original values; whole view grays out during edit
Apply the same cog metaphor to the session Name field — inline text edit
with save/cancel, Enter to confirm, Escape to cancel. No global gray-out.
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.
- JWT refresh logic to prevent dead sessions
- drone status messages now arrive in IDE for display
- WorkspaceService.deployProject method added to clone into a repo or
create the directory (new project not yet in git)
- 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
