feat(presets): drop auto + /pro — flash/pro are the only knobs now#1630
Merged
Conversation
Auto-escalation (flash → pro via the `<<<NEEDS_PRO>>>` marker) and the one-shot `/pro` arming were both surfaces that could spend money behind the user's back: a turn that ran on flash could silently re-bill on pro, and `/pro` plus an idle session compounded the same risk. Both are gone. PresetName is now exactly `"flash" | "pro"`. Old configs holding `auto` / `smart` / `fast` / `max` keep loading: `loadPreset` and the loose-input `resolvePreset` / `canonicalPresetName` silently coerce anything that isn't `flash`/`pro` to `flash`. No legacy migration notice — the user just gets the new safe default. Surface dropped: - `CacheFirstLoopOptions.autoEscalate`, `loop.autoEscalate`, the streaming-time NEEDS_PRO buffer/flush, the post-call NEEDS_PRO retry, `src/loop/escalation.ts`, the `loop.flashEscalation` i18n string. - `loop.armProForNextTurn`, `loop.disarmPro`, `loop.proArmed`, `loop.escalatedThisTurn`, `loop.currentCallModel`, the `_escalateThisTurn` / `_proArmedForNextTurn` state, the `loop.proArmed` warning yield. - `/pro` slash command + handler + i18n. - Dashboard `proNext` field on `POST /api/settings` + ctx.setProNextLive + the proNext / proArm / proArmed / proNextNote i18n bundle. - StatsPanel's pro pill (escalated / proArmed props + rendering). - ModelPicker's `currentAutoEscalate` prop and detect. - usePresetMode's proArmed / turnOnPro state. - ResolvedDefaults.autoEscalate, handleWarningEvent's setTurnOnPro hook, AppProps.autoEscalate / ChatOptions.autoEscalate. - "auto" preset card in both desktop and dashboard Settings → Models. Tests updated: - tests/presets.test.ts: legacy + unknown values coerce to flash. - tests/resolve.test.ts: legacy auto/smart/fast/max coerce silently. - tests/slash.test.ts: `/preset auto` returns usage; `/preset flash` / `/preset pro` keep working; arg-picker enum is `["flash", "pro"]`. - tests/loop.test.ts: NEEDS_PRO describe block and the proArm/disarm tests are gone with the features. - tests/server-dashboard.test.ts: proNext field is gone from the live callback test. - tests/preset-effort-isolation.test.ts: only flash/pro iterated. - tests/ui-slash-suggestions.test.tsx: advanced-group count 11 → 10. Verify: tsc clean (root + dashboard), biome clean (only pre-existing welcome-banner warning), 3576 tests pass. Net -669 lines.
0753078 to
3b62591
Compare
esengine
pushed a commit
that referenced
this pull request
May 24, 2026
…moved, persisted usage stats, plan dispatch gate Headline themes: - Desktop: bundle the CLI-hosted React dashboard, retire Tauri+Preact duplicate (#1418) - Config: drop preset abstraction; flash/pro are direct model selections (#1657, #1630) - Stats: persist cumulative usage to session meta + auto-restore on startup (#1667, #1680, #1643, #1628) - Plans: editMode="plan" enforced at the ToolRegistry dispatch gate (#1681); step advance fix (#1629) - Context: fold once at turn start, drop pre-flight + byte-ceiling (#1642, #1646); collapsible compacted card (#1649) - Subagents: per-skill flash/pro override + Settings UI (#1632) - Desktop polish: sidebar drag-resize (#1688), responsive collapse (#1585), copy/edit overlay + msg-history nav (#1645), Esc closes modal not turn (#1685), QQ tab isolation (#1672), DiffCard for edits (#1662), theme-aware highlighting (#1655), system events toggle (#1654/#1650), macOS TCC inheritance (#1614), dashboard.enabled (#1612) - Dashboard polish: persistent session URL (#1586, #1589, #1599), theme-aware highlighting (#1664), IME confirm-enter guard (#1689), code-fence lang fix (#1677), vendor chunk split (#1587), markdown table h-scroll (#1562) - TUI: Alt+S input stash/recall; static history isolated from input rerenders (#1635); legacy mouse drop (#1637, #1648); multi-edit gated in review (#1647) - Diff: SplitDiff column border holds under CJK (#1686) - MCP: workspace roots passed to servers (#1625); codeCommand honors mcpServers (#1603) - Config plumbing: (baseUrl, apiKey) resolved as a tuple (#1658); stale model id self-heal (#1663) See CHANGELOG for the full list.
esengine
pushed a commit
that referenced
this pull request
May 25, 2026
Three stale-doc fixes: - ARCHITECTURE.md §4.3 — replace removed /pro single-turn arming with the current /model flash|pro + settings.json model selection. Note the removal in 0.50.0 (#1657, #1630). - ARCHITECTURE.md §4.4 — replace the never-existed FAILURE_ESCALATION_THRESHOLD counter with the actual <<<NEEDS_PRO>>> model self-report mechanism. No failure-counter; purely LLM-initiated, no-op on pro tier. - benchmarks/real-world-cache/README.md — fix 10× pricing error in v4-flash cache-hit ($0.028 → $0.0028) and entirely wrong v4-pro pricing ($0.139/1.667/3.333 → $0.003625/0.435/0.87). Recalculated cost tables; headline 99.82% hit ratio unchanged, savings now correctly show ~97.7% (flash) / ~98.9% (pro). Thanks @FriendsHL for catching this — the benchmark pricing in particular is the public cache-first defense link, the old numbers would have been embarrassing.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
Two surfaces in the loop could spend money behind the user's back:
autopreset — flash would self-escalate to pro mid-turn via the<<<NEEDS_PRO>>>marker. The decision was opaque, the cost delta wasn't surfaced clearly, and a stuck loop on auto could quietly bill at pro pricing for many iters./proone-shot — armed for the next turn and disarmed after, but combined with/loop, a steer queue, or an AFK session it could fire multiple pro turns on prompts the user never saw run.Both are gone. From this PR forward the model knob is flash or pro, picked explicitly. The user always knows which model is on.
What
PresetNameis now exactly"flash" | "pro"— noauto, nosmart/fast/maxlegacy aliases in the type. Old configs holding any of those values keep loading:loadPresetand the loose-inputresolvePreset/canonicalPresetNamesilently coerce anything that isn'tflash/protoflash. No legacy migration notice — oldpreset: "auto"just opens as flash.Removed
CacheFirstLoopOptions.autoEscalate,loop.autoEscalate, the streaming-time NEEDS_PRO buffer/flush, the post-call NEEDS_PRO retry,src/loop/escalation.ts, theloop.flashEscalationi18n string.loop.armProForNextTurn,loop.disarmPro,loop.proArmed,loop.escalatedThisTurn,loop.currentCallModel, the_escalateThisTurn/_proArmedForNextTurnstate, theloop.proArmedwarning yield./proslash command + handler + i18n.proNextfield onPOST /api/settings+ ctx.setProNextLive + the proNext / proArm / proArmed / proNextNote i18n bundle.currentAutoEscalateprop and matching detector.Kept
/preset flashand/preset prowork as before./preset auto(andautoas a--presetflag) accept the value but route to usage error / flash respectively — no surprise upgrade.Verify
npm run typecheck(root + dashboard)npm run lint(only pre-existing welcome-banner warning)npm run test— 3576 passnpm run verify— build + lint + typecheck + tests all green~/.reasonix/config.jsonwith"preset": "auto"loads as flash, no warning row, model id readsdeepseek-v4-flash/preset autoshows the usage hint;/preset flashand/preset proswitch live/proreturns "unknown slash command"47 files, net -669 lines.