fix(commandcode): preserve images and reasoning_effort on /alpha/generate
Command Code dropped vision and ignored client effort through the router:
image blocks became "[image omitted]", HTTP image URLs were never inlined,
and reasoning_effort landed on the envelope wrapper instead of params (so the
DeepSeek family mapping remapped low -> high). The catalog also treated
deepseek/deepseek-v4.1-flash as text-only, so the vision adapter stole those
requests to another provider.
- Map OpenAI image_url / Claude image blocks (base64 or data-URI) to the
native {type:"image", image:"data:...;base64,...", mimeType} generate block.
- Add FORMATS.COMMANDCODE to TARGETS_NEED_BASE64 so remote http(s) images are
inlined by the existing SSRF-safe fetcher before translation.
- Write reasoning_effort inside params for targetFormat commandcode and pass
low|medium|high|xhigh|max through unmapped; allow it in thinkingLevels.
- Provider-scoped capabilities for commandcode/cmc: vision except the CLI
text-only denylist, thinkingFormat commandcode, so family patterns
(deepseek-v4 -> thinkingFormat deepseek, vision false) no longer win.
- Quota Tracker: whoami + billing credits/subscriptions (credits vs plan cap,
5h and weekly windows), labels from AI_PROVIDERS[].name.
This commit is contained in:
@@ -8,6 +8,7 @@ import { fetchImageAsBase64, parseDataUri } from "./image.js";
|
||||
const TARGETS_NEED_BASE64 = new Set([
|
||||
FORMATS.GEMINI, FORMATS.GEMINI_CLI, FORMATS.VERTEX,
|
||||
FORMATS.ANTIGRAVITY, FORMATS.OLLAMA, FORMATS.KIRO,
|
||||
FORMATS.COMMANDCODE,
|
||||
]);
|
||||
|
||||
function isRemoteUrl(url) {
|
||||
|
||||
@@ -19,6 +19,7 @@ const FORMAT_TO_NATIVE = {
|
||||
vertex: "gemini-budget",
|
||||
antigravity: "gemini-budget",
|
||||
kiro: "kiro",
|
||||
commandcode: "commandcode",
|
||||
};
|
||||
|
||||
// Strip a trailing thinking suffix "model(value)" → "model" (no-op when absent).
|
||||
@@ -108,6 +109,7 @@ export const captureThinking = extractThinking;
|
||||
const NATIVE_ONLY_FORMATS = new Set(["gemini-level", "gemini-budget", "claude-budget", "claude-adaptive", "kiro"]);
|
||||
|
||||
function resolveFormat(targetFormat, model, provider) {
|
||||
if (targetFormat === "commandcode") return "commandcode";
|
||||
const providerFmt = provider ? PROVIDERS[provider]?.thinkingFormat : null;
|
||||
if (providerFmt) return providerFmt;
|
||||
const caps = getCapabilitiesForModel(provider, model);
|
||||
@@ -223,6 +225,10 @@ function stripAll(body) {
|
||||
delete body.output_config;
|
||||
if (body.generationConfig) delete body.generationConfig.thinkingConfig;
|
||||
if (body.request?.generationConfig) delete body.request.generationConfig.thinkingConfig;
|
||||
if (body.params && typeof body.params === "object") {
|
||||
delete body.params.reasoning_effort;
|
||||
delete body.params.thinking;
|
||||
}
|
||||
}
|
||||
|
||||
// Apply unified thinking config to body in the resolved provider-native format.
|
||||
@@ -336,6 +342,17 @@ function applyFormat(fmt, body, cfg, caps, supportedLevels) {
|
||||
case "kiro":
|
||||
// Kiro thinking handled via system-tag injection in openai-to-kiro.js; no body field here.
|
||||
break;
|
||||
case "commandcode": {
|
||||
// Native CLI sends reasoning_effort inside params of the /alpha/generate envelope.
|
||||
if (!body.params || typeof body.params !== "object") body.params = {};
|
||||
if (none && canDisable) {
|
||||
delete body.params.reasoning_effort;
|
||||
break;
|
||||
}
|
||||
const level = toLevel(eff);
|
||||
if (level) body.params.reasoning_effort = level;
|
||||
break;
|
||||
}
|
||||
default:
|
||||
break;
|
||||
}
|
||||
|
||||
@@ -5,6 +5,7 @@
|
||||
* - params.system: STRING at top level (Anthropic-style; system messages NOT allowed in messages[])
|
||||
* - params.messages[*].role ∈ {"user","assistant","tool"}
|
||||
* - params.messages[*].content: Array of content blocks (NEVER a string)
|
||||
* - image_url / image source → {type:"image", image:"data:...;base64,...", mimeType}
|
||||
* - tool_use blocks (assistant): {type:"tool-call", toolCallId, toolName, input}
|
||||
* - tool_result blocks (role=user): {type:"tool-result", toolCallId, toolName, output}
|
||||
* - tools[*]: Anthropic plain {name, description, input_schema}
|
||||
@@ -12,8 +13,9 @@
|
||||
import { register } from "../index.js";
|
||||
import { FORMATS } from "../formats.js";
|
||||
import { randomUUID } from "crypto";
|
||||
import { ROLE, OPENAI_BLOCK } from "../schema/index.js";
|
||||
import { ROLE, OPENAI_BLOCK, CLAUDE_BLOCK } from "../schema/index.js";
|
||||
import { DEFAULT_MAX_TOKENS } from "../../config/runtimeConfig.js";
|
||||
import { parseDataUri, encodeDataUri } from "../concerns/image.js";
|
||||
|
||||
function flattenText(content) {
|
||||
if (content == null) return "";
|
||||
@@ -29,6 +31,43 @@ function flattenText(content) {
|
||||
return String(content);
|
||||
}
|
||||
|
||||
function toNativeImageBlock(part) {
|
||||
if (!part || typeof part !== "object") return null;
|
||||
|
||||
if (part.type === OPENAI_BLOCK.IMAGE_URL) {
|
||||
const url = typeof part.image_url === "string" ? part.image_url : part.image_url?.url;
|
||||
const parsed = parseDataUri(url);
|
||||
if (!parsed) return null;
|
||||
return {
|
||||
type: OPENAI_BLOCK.IMAGE,
|
||||
image: encodeDataUri(parsed.mimeType, parsed.base64),
|
||||
mimeType: parsed.mimeType,
|
||||
};
|
||||
}
|
||||
|
||||
if (part.type === OPENAI_BLOCK.IMAGE || part.type === CLAUDE_BLOCK.IMAGE) {
|
||||
if (typeof part.image === "string" && part.image.startsWith("data:")) {
|
||||
const parsed = parseDataUri(part.image);
|
||||
return {
|
||||
type: OPENAI_BLOCK.IMAGE,
|
||||
image: part.image,
|
||||
mimeType: part.mimeType || parsed?.mimeType || "image/png",
|
||||
};
|
||||
}
|
||||
const source = part.source;
|
||||
if (source?.type === "base64" && typeof source.data === "string") {
|
||||
const mime = source.media_type || "image/png";
|
||||
return {
|
||||
type: OPENAI_BLOCK.IMAGE,
|
||||
image: encodeDataUri(mime, source.data),
|
||||
mimeType: mime,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
|
||||
function toContentBlocks(content) {
|
||||
if (content == null) return [{ type: OPENAI_BLOCK.TEXT, text: "" }];
|
||||
if (typeof content === "string") return [{ type: OPENAI_BLOCK.TEXT, text: content }];
|
||||
@@ -40,10 +79,12 @@ function toContentBlocks(content) {
|
||||
} else if (part && typeof part === "object") {
|
||||
if (part.type === OPENAI_BLOCK.TEXT && typeof part.text === "string") {
|
||||
blocks.push({ type: OPENAI_BLOCK.TEXT, text: part.text });
|
||||
} else if (part.type === OPENAI_BLOCK.IMAGE_URL || part.type === OPENAI_BLOCK.IMAGE) {
|
||||
blocks.push({ type: OPENAI_BLOCK.TEXT, text: "[image omitted]" });
|
||||
} else if (typeof part.text === "string") {
|
||||
blocks.push({ type: OPENAI_BLOCK.TEXT, text: part.text });
|
||||
} else {
|
||||
const image = toNativeImageBlock(part);
|
||||
if (image) blocks.push(image);
|
||||
else if (typeof part.text === "string") {
|
||||
blocks.push({ type: OPENAI_BLOCK.TEXT, text: part.text });
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user