opencode-see-image 0.8.3 → 0.8.5

package/index.ts

@@ -11,7 +11,7 @@ const ENDPOINT =
   "https://opencode.ai/zen/go/v1/messages"
 const MODEL = process.env.SEE_IMAGE_MODEL || "minimax-m3"
 const PROVIDER_ID = process.env.SEE_IMAGE_PROVIDER || "opencode-go"
-const TIMEOUT = parseInt(process.env.SEE_IMAGE_TIMEOUT || "30000", 10)
+const TIMEOUT = parseInt(process.env.SEE_IMAGE_TIMEOUT || "10000", 10)
 const API_VERSION = process.env.SEE_IMAGE_API_VERSION || "2023-06-01"
 const USER_AGENT =
   process.env.SEE_IMAGE_USER_AGENT ||
@@ -224,88 +224,102 @@ async function seeImageViaSDK(
 ): Promise<{ text: string; model: string; provider: string }> {
   const errors: string[] = []
 
-  // Create new sessions with specific provider/model candidates
-  const envProvider = process.env.SEE_IMAGE_PROVIDER
-  const envModel = process.env.SEE_IMAGE_MODEL
-  const candidates: Array<{ providerID: string; modelID: string }> = []
-  if (envProvider && envModel) {
-    candidates.push({ providerID: envProvider, modelID: envModel })
-  }
-  candidates.push({ providerID: "opencode-go", modelID: "minimax-m3" })
-  candidates.push({ providerID: "opencode", modelID: "mimo-v2.5-free" })
-
-  for (const { providerID, modelID } of candidates) {
-    let sessionID: string | undefined
-    try {
-      const sessionRes = await client.session.create({ body: {} })
-      sessionID = sessionRes.data?.id
-      if (!sessionID) {
-        errors.push(`${providerID}/${modelID}: no session ID`)
-        continue
-      }
+  // Write image to a temp file so the server can read it directly
+  const b64 = dataUrl.split(",")[1] || ""
+  const tmpPath = path.join(os.tmpdir(), `see-image-${Date.now()}.png`)
+  try {
+    fs.writeFileSync(tmpPath, Buffer.from(b64, "base64"))
+  } catch {}
 
-      // Per-candidate timeout so a slow model doesn't hang forever
-      const controller = new AbortController()
-      const timer = setTimeout(() => controller.abort(), TIMEOUT)
-
-      const result = await client.session.prompt({
-        path: { id: sessionID },
-        body: {
-          model: { providerID, modelID },
-          parts: [
-            { type: "file", mime: mediaType, url: dataUrl },
-            { type: "text", text: prompt },
-          ],
-          tools: {},
-          system:
-            "You are a vision assistant. Describe the image accurately and concisely. Answer with text only.",
-        },
-        signal: controller.signal,
-      })
-      clearTimeout(timer)
-
-      const parts = result.data?.parts ?? []
-      const text = (parts as any[])
-        .filter((p: any) => p.type === "text")
-        .map((p: any) => p.text)
-        .filter((t: any) => typeof t === "string" && t.length > 0)
-        .join("\n")
-        .trim()
-
-      if (text) {
-        return { text, model: modelID, provider: providerID }
-      }
-      errors.push(`${providerID}/${modelID}: no text in response`)
-    } catch (e: any) {
-      errors.push(`${providerID}/${modelID}: ${e?.message ?? e}`)
-    } finally {
-      if (sessionID) {
-        await client.session
-          .delete({ path: { id: sessionID } })
-          .catch(() => {})
+  const fileUrl = `file://${tmpPath}`
+  let result: { text: string; model: string; provider: string } | undefined
+
+  try {
+    const candidates: Array<{ providerID: string; modelID: string }> = []
+    const envProvider = process.env.SEE_IMAGE_PROVIDER
+    const envModel = process.env.SEE_IMAGE_MODEL
+    if (envProvider && envModel) {
+      candidates.push({ providerID: envProvider, modelID: envModel })
+    }
+    candidates.push({ providerID: "opencode-go", modelID: "minimax-m3" })
+    candidates.push({ providerID: "opencode", modelID: "mimo-v2.5-free" })
+
+    for (const { providerID, modelID } of candidates) {
+      let sessionID: string | undefined
+      try {
+        const sessionRes = await client.session.create({ body: {} })
+        sessionID = sessionRes.data?.id
+        if (!sessionID) {
+          errors.push(`${providerID}/${modelID}: no session ID`)
+          continue
+        }
+
+        const controller = new AbortController()
+        const timer = setTimeout(() => controller.abort(), TIMEOUT)
+        const res = await client.session.prompt({
+          path: { id: sessionID },
+          body: {
+            model: { providerID, modelID },
+            parts: [
+              { type: "file", mime: mediaType, url: providerID === "opencode" ? fileUrl : dataUrl },
+              { type: "text", text: prompt },
+            ],
+            tools: {},
+            system:
+              "You are a vision assistant. Describe the image accurately and concisely. Answer with text only.",
+          },
+          signal: controller.signal,
+        })
+        clearTimeout(timer)
+
+        const parts = res.data?.parts ?? []
+        const text = (parts as any[])
+          .filter((p: any) => p.type === "text")
+          .map((p: any) => p.text)
+          .filter((t: any) => typeof t === "string" && t.length > 0)
+          .join("\n")
+          .trim()
+
+        if (text) {
+          result = { text, model: modelID, provider: providerID }
+          break
+        }
+        errors.push(`${providerID}/${modelID}: no text in response`)
+      } catch (e: any) {
+        errors.push(`${providerID}/${modelID}: ${e?.message ?? e}`)
+      } finally {
+        if (sessionID) {
+          await client.session
+            .delete({ path: { id: sessionID } })
+            .catch(() => {})
+        }
       }
     }
-  }
 
-  // If user has an API key configured (from auth.json or env), try HTTP fallback
-  const b64 = dataUrl.split(",")[1] || ""
-  const apiKey =
-    process.env.SEE_IMAGE_API_KEY || readProviderKey("opencode-go")
-  if (apiKey) {
-    try {
-      return await seeImageViaHTTP(b64, mediaType, prompt, abort, apiKey)
-    } catch (e: any) {
-      errors.push(`http-fallback: ${e?.message ?? e}`)
+    if (!result) {
+      const apiKey =
+        process.env.SEE_IMAGE_API_KEY || readProviderKey("opencode-go")
+      if (apiKey) {
+        try {
+          result = await seeImageViaHTTP(b64, mediaType, prompt, abort, apiKey)
+        } catch (e: any) {
+          errors.push(`http-fallback: ${e?.message ?? e}`)
+        }
+      }
     }
-  }
 
-  const errMsg = errors.join("; ")
-  const hint = errMsg.includes("usage limit")
-    ? ` Enable usage from your balance at https://opencode.ai/workspace/wrk_01KVARG0A0Y87XV5JYBNJ0WRXB/go`
-    : ""
-  throw new Error(
-    `see_image: SDK vision call failed for all candidates. ${errMsg}.${hint}`,
-  )
+    if (result) return result
+
+    const errMsg = errors.join("; ")
+    const hint = errMsg.includes("usage limit")
+      ? ` Enable usage from your balance at https://opencode.ai/workspace/wrk_01KVARG0A0Y87XV5JYBNJ0WRXB/go`
+      : ""
+    throw new Error(
+      `see_image: SDK vision call failed for all candidates. ${errMsg}.${hint}`,
+    )
+  } finally {
+    try { fs.unlinkSync(tmpPath) } catch {}
+  }
 }
 
 async function seeImageViaHTTP(

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-see-image",
-  "version": "0.8.3",
+  "version": "0.8.5",
   "description": "Give non-vision opencode models the ability to see images/screenshots by routing them to a vision-capable model (MiniMax M3 via opencode-go by default).",
   "type": "module",
   "main": "index.ts",