fix(core): M1 validated against real DeepSeek API + V4 model alias map#9
Merged
Conversation
…models
End-to-end validation 2026-05-28 with a real API key (since rotated):
· /v1/models, /v1/chat/completions all reach
· Text streaming + tool_calls increments + reasoning_content all match our
mocked unit test fixtures exactly
· Agent loop (provider → tool → result → finalize) runs against real model
· deepseek-reasoner reasoning chunks flow into thinking ContentBlocks
Change
------
- types.ts — DeepSeekModel union now includes deepseek-v4-flash /
deepseek-v4-pro (the actual current backing models
per /v1/models). The classic deepseek-chat /
deepseek-reasoner names remain as stable API
aliases.
- providers/deepseek.ts — DEEPSEEK_MODELS table extended with the V4 entries
(all 4 share ctx 128k / maxOutput 8192).
- providers/deepseek.live.test.ts (new) — three live-API integration tests
(text streaming / tool_calls / reasoning_content),
opt-in via DEEPCODE_LIVE_TESTS=1. All three pass.
- docs/m1-validation.md — formal validation report
Result: 217 default tests still pass (+ 3 live tests when DEEPCODE_LIVE_TESTS=1).
Verified
--------
pnpm typecheck → green
pnpm test → 217 passed / 1 skipped file / 7 skipped tests
(live tests deferred unless opted in)
DEEPCODE_LIVE_TESTS=1 \
pnpm --filter @deepcode/core test deepseek.live.test
→ 3 passed (~6s, costs a few ¥0.001 of real tokens)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
oratis
added a commit
that referenced
this pull request
Jun 1, 2026
…137) The collapsed inspector rail now matches design spec screen #3 exactly: ‹ expand · ▤ Plan (pending badge) · ◐ Context · 📁 Recent files · ⓘ Session info · ⚙ Settings. The four middle icons are inspector hints — clicking one expands the 320px panel and scrolls to that section (new `focusSection` prop on InspectorPanel + `data-section` anchors). The rail previously doubled as the *only* navigation to Permissions / MCP / Plugins / Skills / About. Per spec screen #9 those live behind the ⚙ cog in a shared Settings shell, so this adds <SettingsLayout> (a `.set-nav` left column + pane) and folds the settings-family screens into it — nothing is stranded. Sessions stay in the left sidebar where the spec puts them. - InspectorRail: trimmed to the 6 spec elements; onExpand(section) / onSettings / settingsActive replace the old screen-routing props. - SettingsLayout + SETTINGS_FAMILY: unified nav for settings-family screens. - App: expandInspector(section), settings-shell wrapping in renderScreen. - index.css: `.settings-shell` / `.set-nav` / `.set-pane` per spec lines 754-768; sticky `.inspector-head` so focused sections land below it. Verified in a browser harness: rail = 48px with exactly ‹/▤(badge)/◐/📁/ⓘ/⚙, panel = 320px, set-nav switches active screen, ⌘\ unchanged. Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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.
Summary
User provided a real DeepSeek API key. Used it to validate that M1's mock-based test fixtures actually match the real wire behavior of api.deepseek.com.
Result: everything works. The provider, agent loop, sessions, tool dispatch all run end-to-end against real DeepSeek. The biggest
unknownfrom MORNING_REPORT.md is now closed.Findings
mockFetchfixtures exactlydeepseek-reasonerreasoning_contentsurfaces asthinkingblocks + reasoning_tokens captured/v1/modelsreturnsdeepseek-v4-flashanddeepseek-v4-pro. The classic namesdeepseek-chat/deepseek-reasonerremain as stable API aliases (still accepted), but we now also expose the V4 names in ourDeepSeekModeltype.Changes
types.ts— expandDeepSeekModelunion to 4 names with alias mapping commentproviders/deepseek.ts—DEEPSEEK_MODELStable extendedproviders/deepseek.live.test.ts— new live-API integration tests, opt-in viaDEEPCODE_LIVE_TESTS=1docs/m1-validation.md— formal validation reportTest plan
pnpm test— 217 passed, live tests properly skipped by defaultDEEPCODE_LIVE_TESTS=1 pnpm --filter @deepcode/core test deepseek.live.test— 3 passed against real APIRelease notes
release-notes:fix— corrects model names to match current API + adds validated invariantsCo-Authored-By: Claude Opus 4.7 (1M context) noreply@anthropic.com