shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(ai): avoid duplicate OpenCode DeepSeek reasoning controls

Browse Source 
closes #5818
This commit is contained in:
Armin Ronacher
2026-06-16 18:59:28 +02:00
parent 2d597f0212
commit 2431491c92
3 changed files with 28 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
packages/ai/CHANGELOG.md
View File

@@ -9,6 +9,7 @@
### Fixed
- Fixed OpenAI Responses streaming to tolerate null message content from OpenAI-compatible servers before tool calls ([#5819](https://github.com/earendil-works/pi/issues/5819)).
- Fixed OpenCode DeepSeek V4 thinking requests to avoid sending both `thinking` and `reasoning_effort` ([#5818](https://github.com/earendil-works/pi/issues/5818)).
- Fixed Z.AI GLM-5.2 thinking requests to send `reasoning_effort` with the provider's `high`/`max` effort mapping ([#5770](https://github.com/earendil-works/pi/issues/5770)).
- Fixed Google and `google-vertex` Gemini model metadata to map `latest` aliases to the current models, add Gemini 3.5 Flash for Vertex, correct Gemini 2.5 Flash Vertex cache pricing, and remove shut-down Vertex preview models ([#5761](https://github.com/earendil-works/pi/issues/5761)).
- Fixed Moonshot AI China model metadata to include Kimi K2.7 Code, and omitted unsupported thinking-off payloads for Kimi K2.7 Code models ([#5760](https://github.com/earendil-works/pi/issues/5760)).

6
packages/ai/scripts/generate-models.ts
View File

@@ -1852,9 +1852,13 @@ async function generateModels() {
for (const candidate of allModels) {
if (candidate.api === "openai-completions" && candidate.id.includes("deepseek-v4")) {
const preservesNativeReasoningEffort =
candidate.provider === "openrouter" ||
candidate.provider === "opencode" ||
candidate.provider === "opencode-go";
candidate.compat = {
...candidate.compat,
...(candidate.provider === "openrouter"
...(preservesNativeReasoningEffort
? {
requiresReasoningContentOnAssistantMessages:
deepseekCompat.requiresReasoningContentOnAssistantMessages,

27
packages/ai/src/models.generated.ts
View File

@@ -7938,7 +7938,7 @@ export const MODELS = {
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
@@ -7957,7 +7957,7 @@ export const MODELS = {
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
@@ -7976,7 +7976,7 @@ export const MODELS = {
api: "openai-completions",
provider: "opencode",
baseUrl: "https://opencode.ai/zen/v1",
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
compat: {"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
@@ -8554,7 +8554,7 @@ export const MODELS = {
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
@@ -8573,7 +8573,7 @@ export const MODELS = {
api: "openai-completions",
provider: "opencode-go",
baseUrl: "https://opencode.ai/zen/go/v1",
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
compat: {"maxTokensField":"max_tokens","requiresReasoningContentOnAssistantMessages":true},
reasoning: true,
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"max"},
input: ["text"],
@@ -16310,6 +16310,23 @@ export const MODELS = {
contextWindow: 202800,
maxTokens: 64000,
} satisfies Model<"anthropic-messages">,
"zai/glm-5.2": {
id: "zai/glm-5.2",
name: "GLM 5.2",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text"],
cost: {
input: 1.4,
output: 4.4,
cacheRead: 0.26,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 128000,
} satisfies Model<"anthropic-messages">,
"zai/glm-5v-turbo": {
id: "zai/glm-5v-turbo",
name: "GLM 5V Turbo",