Daemon: a changed default model overrides the saved state (0.6.3)

In managed mode the extension switches models by rewriting the daemon config's
defaultModel and restarting it, but loadState() preferred the persisted model, so the
daemon came back on the old one every time. State now records the default it was saved
under; a different default wins.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J39imRDT8L7xYbWzsVWd8A

CHANGELOG.md

@@ -2,6 +2,19 @@
 
 Extension versions are released as `vscode-v<version>` on the [Releases](https://git.harvmaster.com/Harvmaster/autocomplete-model/releases) page. Models are versioned by their name in [`models/manifest.json`](models/manifest.json).
 
+## vscode 0.6.3
+
+- **Fix: model choice didn't stick in managed mode.** The daemon's saved state (last model used) overrode both the
+  model picked in the menu and a new default from a release, so it kept restarting on the old model (e.g.
+  `stage-c`). A changed default now wins; switching through the daemon API still persists as before.
+
+## vscode 0.6.2
+
+- **Next-edit is ~3–5× faster:** the next-edit server uses n-gram speculative decoding (the rewritten region is mostly
+  a copy of the current one, so drafted tokens are verified in batches). Same output, since decoding is greedy.
+  Rewriting a 13-line region on a laptop CPU: ~2.1 s → ~0.7 s (~0.4 s when the prompt is cached).
+- Next-edit timings in "Show Last Prompt" now split TS errors / prompt / generation time.
+
 ## vscode 0.6.1
 
 - **New default model `stage-d`**, with **`stage-e` for next-edit**. Both download automatically (~530 MB each); the

daemon/src/config.ts

@@ -32,6 +32,9 @@ export interface DaemonConfig {
     ctx: number
     /** Extra flags, e.g. ["-ngl", "99"] on Apple Silicon, ["-t", "16"] on the laptop CPU. */
     args: string[]
+    /** Extra flags for the next-edit companion server only. Default: n-gram speculative decoding (the output is
+     *  mostly a copy of the region, so drafts from the prompt are accepted; exact with greedy sampling). */
+    nextEditArgs?: string[]
   }
   models: Record<string, ModelProfile>
   defaultModel: string
@@ -73,6 +76,8 @@ export interface RuntimeState {
   enabled: boolean
   model: string
   mode: ContextMode
+  /** config.defaultModel when this state was saved: a changed default (editor model setting, new release) wins. */
+  defaultModel?: string
 }
 
 export function loadConfig(configPath: string): DaemonConfig {
@@ -94,12 +99,13 @@ export function loadConfig(configPath: string): DaemonConfig {
 }
 
 export function loadState(config: DaemonConfig): RuntimeState {
-  const fallback: RuntimeState = { enabled: true, model: config.defaultModel, mode: config.models[config.defaultModel].defaultMode }
+  const fallback: RuntimeState = { enabled: true, model: config.defaultModel, mode: config.models[config.defaultModel].defaultMode, defaultModel: config.defaultModel }
   try {
     const s = JSON.parse(fs.readFileSync(config.stateFile, 'utf8')) as Partial<RuntimeState>
-    const model = s.model && config.models[s.model] ? s.model : fallback.model
+    const keepModel = s.defaultModel === config.defaultModel && s.model && config.models[s.model]
+    const model = keepModel ? s.model! : fallback.model
     const mode = s.mode && config.models[model].modes.includes(s.mode) ? s.mode : config.models[model].defaultMode
-    return { enabled: s.enabled ?? true, model, mode }
+    return { enabled: s.enabled ?? true, model, mode, defaultModel: config.defaultModel }
   } catch {
     return fallback
   }

daemon/src/main.ts

@@ -52,7 +52,8 @@ function loadModel(name: string) {
 }
 
 // Next-edit companion model (profile.nextEditModel): a second llama-server, started on first use.
-const neLlama = new LlamaServer({ ...config.llamaServer, port: config.llamaServer.port + 1 })
+const NEXT_EDIT_SPECULATION = ['--spec-type', 'ngram-simple', '--spec-draft-n-max', '64', '--spec-ngram-simple-size-n', '3']
+const neLlama = new LlamaServer({ ...config.llamaServer, port: config.llamaServer.port + 1, args: [...config.llamaServer.args, ...(config.llamaServer.nextEditArgs ?? NEXT_EDIT_SPECULATION)] })
 let neLoading: Promise<void> | null = null
 /** The server that answers next-edit for the active model, or an error message. */
 async function nextEditServer(): Promise<LlamaServer | string> {
@@ -273,9 +274,11 @@ async function handleNextEdit(body: NextEditRequest, res: http.ServerResponse, c
   const endLine = Math.min(lines.length, cursorLine + o.regionAfter + 1)
   const recentEdits = edits.observe(`${body.workspaceRoot ?? body.repo}/${body.path}`, body.path, body.text, cursorLine)
   const lang = symbolLang(body.languageId ?? '')
+  const tErrors = performance.now()
   const errors = body.workspaceRoot && lang
     ? await symbols.errors({ root: body.workspaceRoot, filePath: path.join(body.workspaceRoot, body.path), lang, text: body.text, cursor: body.cursor, waitMs: 300 })
     : undefined
+  const errorsMs = performance.now() - tErrors
   const ids = builder.buildNextEdit({ repo: body.repo, path: body.path, file: body.text, regionStartLine: startLine, regionEndLine: endLine, cursor: body.cursor, recentEdits: recentEdits || undefined, errors },
     { beforeTokens: o.beforeTokens, afterTokens: o.afterTokens })
 
@@ -294,7 +297,7 @@ async function handleNextEdit(body: NextEditRequest, res: http.ServerResponse, c
   const response = {
     requestId: body.requestId, noEdit, startLine, endLine, oldText, newText: noEdit ? null : newText,
     recentEdits, errors: errors ?? null, model: profile.nextEditModel ?? state.model,
-    timings: { promptTokens: ids.length, processedTokens: result.timings?.prompt_n ?? null, genTokens: result.timings?.predicted_n ?? null, totalMs: round(performance.now() - t0) },
+    timings: { promptTokens: ids.length, processedTokens: result.timings?.prompt_n ?? null, genTokens: result.timings?.predicted_n ?? null, errorsMs: round(errorsMs), promptMs: round(result.timings?.prompt_ms ?? 0), genMs: round(result.timings?.predicted_ms ?? 0), totalMs: round(performance.now() - t0) },
   }
   remember({ kind: 'next-edit', requestId: body.requestId, path: body.path, model: state.model, prompt: builder.decode(ids), raw, noEdit, timings: response.timings })
   json(res, 200, response)

extensions/vscode/package.json

@@ -3,7 +3,7 @@
   "displayName": "Local Autocomplete",
   "description": "Inline code completion from a local fine-tuned model via the acd daemon",
   "publisher": "harvmaster",
-  "version": "0.6.1",
+  "version": "0.6.3",
   "license": "MIT",
   "engines": {
     "vscode": "^1.90.0"