fix(providers): carry Gemini, MiMo, DeepSeek, Mistral, opencode-go and audio adapter fixes for 2.90

docs-site/src/content/docs/guides/pi.md

@@ -147,12 +147,14 @@ An explicit reasoning effort of `none` survives Chat conversion. Output limits a
 controls are preserved for generic API-key Responses targets; the canonical ChatGPT target
 still applies its own restrictions. This does not make all providers' controls equivalent.
 
-**Audio and most file attachments need a native input wire that supports them.** A document
-that carries its own base64 bytes in a user message is the exception: it survives translation
-and reaches the Anthropic, OpenAI Chat and Google wires as a native document, file part and
-inline data part. Everything else still returns an explicit error rather than succeeding
-without the attachment — audio, a file-ID or remote reference the proxy cannot dereference, an
-attachment in a tool output or a system message, and a document routed to a wire with no byte
+Inline WAV/MP3 audio in a user message or tool result survives translation to OpenAI Chat as an
+`input_audio` content part; tool-result audio is promoted into a follow-up user message after
+the paired tool results because Chat tool messages are text-only. A document that carries its
+own base64 bytes in a user message is also carried: it reaches the Anthropic, OpenAI Chat and
+Google wires as a native document, file part and inline data part. Everything else still
+returns an explicit error rather than succeeding without the attachment — remote or
+unsupported audio, a file-ID or remote reference the proxy cannot dereference, an attachment
+in a system message, a document in a tool result, and a document routed to a wire with no byte
 carrier. File-ID-only images have the same restriction because translated adapters cannot
 resolve those IDs. Convert the attachment to text first, or use a native wire and model that
 support it. Native Chat and raw Responses (including Azure) retain their existing behavior;

docs-site/src/content/docs/guides/providers.md

@@ -857,10 +857,12 @@ when a stable upstream session is required.
 
 **MiMo tool-call echoes.** On OpenCode Go and other Chat Completions routes, a bare
 `<tool_call>` block is hidden when it duplicates one structured call to the same tool
-with the same effective input. If the input differs or several calls could explain
+with the same effective input. This includes MiMo wrappers such as
+`<tool_call_deadbeef>` with matching closing IDs, including echoes appended to ordinary prose.
+Code examples remain visible. If the input differs or several calls could explain
 the block, the markup remains visible. For `mimo-v2` and dotted MiMo V2 model IDs such as
 `mimo-v2.6-pro`, if the gateway instead sends exactly one empty `{}` call for a declared
-freeform tool and puts its input in a standalone bare block, opencodex restores that
+freeform tool and puts its input in a standalone bare or identified block, opencodex restores that
 input to the call and hides the block. Hyphenated IDs such as `mimo-v2-pro` and
 `mimo-v2-omni` are outside this recovery rule. Prose, quoted
 examples, ordinary functions, and ambiguous responses remain unchanged. This also handles

docs-site/src/content/docs/guides/sidecars.md

@@ -138,6 +138,19 @@ failures after response headers have started are delivered as `response.failed`
 
 ## Vision sidecar
 
+Mistral's `zai-glm-5-3` is enrolled by the provider preset as text-only. With the
+vision sidecar enabled and available, OpenCodex describes attached images and
+sends their text descriptions to GLM. The Codex catalog advertises image
+attachments for this route. After an update, run `ocx sync`, then fully quit and
+relaunch the Codex desktop app or reload the VS Code window. Sync without a
+restart flag does not restart an existing Codex app-server, which can retain
+the old model list. Alternatively, use `ocx sync --restart-codex` to sync and
+restart matching Codex processes and the desktop app. Finish active work first:
+this restart ends live conversations. See the [sync and restart reference](/reference/cli/lifecycle/#ocx-sync---restart-codex---restart-app-server-only).
+After relaunch, select `mistral/zai-glm-5-3` and verify that image attachments
+are available. No model modality override is needed. Mistral documents native input in its
+[GLM 5.3 reference](https://docs.mistral.ai/models/zai-glm-5-3).
+
 Image routing is capability-aware. Before an image-bearing upstream send, opencodex resolves the selected model's effective input modalities from runtime provider evidence, explicit operator declarations, backend/registry metadata, and generated vendor metadata. A target positively known to be text-only goes through the Vision Sidecar first; the image is described **before** the main call and replaced inline with text. A target positively known to support images receives the image directly. Unknown custom models keep the existing compatibility behavior rather than being guessed text-only.
 
 For the canonical ChatGPT Codex route, opencodex uses the `openai-codex` metadata bundle rather than public OpenAI API metadata, so backend-specific modality differences are respected. The native Chat fast path uses the same gate and cannot bypass a known text-only verdict. Without an available sidecar plan, raw images are stripped before a proven text-only backend.

docs-site/src/content/docs/reference/configuration/providers.md

@@ -8,6 +8,29 @@ description: Provider entries, authentication, endpoints, model catalogs, quotas
 A provider tells opencodex where a model lives, which wire adapter it speaks, and how requests are
 authenticated.
 
+## DeepSeek: tokens versus image bytes
+
+DeepSeek documents a separate [48 MiB request-body limit](https://api-docs.deepseek.com/guides/files_api/).
+A screenshot-heavy session can reach that limit before its token context fills; increasing
+`model_auto_compact_token_limit` cannot prevent it.
+
+Uploads are **off by default**. Set `modelCapabilities: { "deepseek-flash": { deepseekImageFiles: true } }`
+on your provider if you accept separately persisted images on DeepSeek's servers for one hour.
+PATCH `null` on the axis or model entry clears the opt-in.
+
+For opted-in models on first-party Responses URLs, bodies above 40 MiB replace older inline images
+with [Files API references](https://api-docs.deepseek.com/guides/files_api/), aiming for 32 MiB.
+Image bytes, history and token usage stay unchanged. Files request one-hour expiry; successful
+partial uploads remain until expiry even if generation fails. The bounded reference cache is
+credential-isolated and lasts at most 50 minutes (less if the provider reports earlier expiry).
+A retry can reuse successful uploads; another credential uploads its own copy.
+
+Foreign gateways and Chat Completions are unchanged. Explicit `detail: low` stays inline because
+file references ignore it. Failures stop without discarding images or retrying generation. Repairs
+have a 60-second upload deadline, a 128 MiB input cap and at most two simultaneous preparations;
+provider pacing/concurrency still applies. Oversized text or unconvertible images still need
+compaction; this transport repair does not extend the model's context window.
+
 ## Context windows on custom providers
 
 When a custom provider omits a model's context window, OpenCodex can infer it from the bundled
@@ -360,7 +383,7 @@ Providers can expose a built-in shorthand, such as `agy` for `google-antigravity
 | `inlineThinkTagModels?` | `string[]` | Opt-in recovery for `openai-chat` gateways without a server-side reasoning parser. A leading `<think>` / `<thinking>` / `<reasoning>` block (optionally after whitespace) activates splitting in streamed and buffered replies. All answer whitespace is preserved. Subsequent tags are delimiters anywhere, including same-line interleaving and code fences; this mode does not interpret Markdown. Ordinary text or a code fence before the first tag keeps the whole reply untouched. Off by default; prefer structured upstream reasoning or `reasoningSplitModels` where supported. |
 | `reasoningDetailsModels?` | `string[]` | Models whose endpoint returns thinking as a structured `reasoning_details` array (MiniMax M-series with `reasoning_split`); stream deltas are cumulative snapshots that are prefix-diffed, and preserved reasoning replays as a `reasoning_details` array instead of a `reasoning_content` string. |
 | `requiresReasoningPlaceholderModels?` | `string[]` | Models whose upstream rejects a tool_call continuation missing `reasoning_content` (DeepSeek thinking mode); a minimal placeholder is injected when the replay cache misses. Defaults to `preserveReasoningContentModels`; set `[]` to opt out. A provider save that keeps the destination keeps the stored list, including `[]`; see [What a provider save keeps](#what-a-provider-save-keeps). `PATCH /api/providers?name=<provider>` accepts an array or `null` to clear it. |
-| `showThinkingSummary?` | `boolean` | Display provider-authored summaries when a Responses client omits `reasoning.summary`. Explicit wire `"none"` wins; a client that serializes its preference as omission cannot be distinguished. Raw reasoning remains content and is never relabeled as a summary. The `google-antigravity` preset defaults to `true`; explicit `false` disables that default. CCA Gemini requests also opt into `generationConfig.thinkingConfig.includeThoughts` when display is enabled; image, Claude and gpt-oss requests do not. This does not change client configuration or global catalog summary defaults. |
+| `showThinkingSummary?` | `boolean` | Display provider-authored summaries when a Responses client omits `reasoning.summary`. Explicit wire `"none"` wins; a client that serializes its preference as omission cannot be distinguished. Raw reasoning remains content and is never relabeled as a summary. The `google-antigravity` preset defaults to `true`; explicit `false` disables that default. Eligible CCA, Vertex and direct Gemini requests also opt into `generationConfig.thinkingConfig.includeThoughts` when display is enabled; image, Claude, gpt-oss and unladdered Vertex requests do not. This does not change client configuration or global catalog summary defaults. |
 | `hideRawReasoning?` | `boolean` | Keep a routed provider's raw chain of thought off the client-facing content channel (openai-chat `reasoning_content`, kiro tags, `response.reasoning_text.*`) while provider-authored summaries still stream on the summary channel. Explicit wire `reasoning.summary: "none"` keeps hiding both. This controls what a client displays; it does not keep the text from the client. A Responses bridge route still sends it inside the `ocxr1` replay envelope in the reasoning item's `encrypted_content`, which is base64 JSON rather than encryption, so the client can echo it back on the next turn. The direct Chat and Messages encoders have no envelope on their wire, so those clients receive no copy and replay comes from the server-side reasoning replay cache. `preserveReasoningContentModels` replay and DeepSeek-style continuations are unaffected either way. Off by default; a native passthrough route relays the upstream's own frames and ignores this option. A save of the same provider name keeps an omitted value even after a destination move; `PATCH` accepts a boolean or `null` to clear it. |
 | `thinkingToggleModels?` | `string[]` | Chat models using `thinking.enabled` rather than an effort ladder. |
 | `thinkingBudgetModels?` | `string[]` | Chat models using integer `thinking_budget`; effort maps to a budget fraction. |
@@ -1788,7 +1811,7 @@ contracts.
 
 ### Per-model capability declarations
 
-`modelCapabilities` stores explicit declarations keyed by exact upstream model ID. IDs preserve case and must not contain surrounding whitespace. Each entry may contain `inputModalities` (`text`, `image`, `audio`, `video`), `contextTier` (`default`, `long_context`) and `video.processing` (`static`, `agentic`). These are operator declarations, not proof of provider support. Context-tier and video fields currently record intent only and do not activate upstream behavior or increase catalog windows.
+`modelCapabilities` stores explicit declarations keyed by exact upstream model ID. IDs preserve case and must not contain surrounding whitespace. Each entry may contain `inputModalities` (`text`, `image`, `audio`, `video`), `contextTier` (`default`, `long_context`), `video.processing` (`static`, `agentic`) and `deepseekImageFiles` (`boolean`; see [DeepSeek image bytes](#deepseek-tokens-versus-image-bytes)). These are operator declarations, not proof of provider support. Context-tier and video fields currently record intent only and do not activate upstream behavior or increase catalog windows.
 
 The raw provider editor and provider API expose this map. POST/PUT replace an explicitly supplied map and reject null entries. PATCH merges individual axes; null clears a map, model, axis or video processing value, while `{}` makes no change. Omitted provider overwrites preserve the existing map. Malformed hand-edited files retain valid independent axes and treat malformed explicit input modalities as text-only, with a diagnostic.
 

docs-site/src/content/docs/reference/proxy-formats.md

@@ -20,6 +20,15 @@ response safety still happen at the proxy boundary. Configure the listener and a
 [Configuration](/reference/configuration/); use [Combos](/guides/combos/) when one public model id
 should select among several targets.
 
+## MiMo bare tool-call recovery
+
+On translated OpenAI Chat routes, `mimo-v2` and dotted `mimo-v2.*` model IDs can recover a
+complete bare `<tool_call>` block as a call to an exact declared freeform tool when the response
+contains no structured tool calls. Prose around the block is preserved; fenced and inline-code
+examples, nested headers, undeclared tools and identified wrappers remain literal. Recovery is
+bounded to 128 calls, 4 MiB total and 2 MiB per candidate. Long streamed prose may release the
+original markup before terminal recovery; errors never dispatch recovered calls.
+
 ## Upstream redirects
 
 Credential-bearing model, image, video, and search requests do not automatically follow HTTP redirects, including same-origin redirects. Configure the final upstream API URL instead of a redirecting alias. A redirect does not cause the server to resend credentials or the request body to its destination. The response owner retains its existing error or relay behavior; native Responses and compact routes can return the original 3xx and `Location` to the client. Client redirect behavior is separate from this server transport policy.

scripts/model-metadata.source.json

@@ -61584,6 +61584,45 @@
 		}
 	},
 	"opencode-go": {
+		"beam-free": {
+			"id": "beam-free",
+			"name": "Beam Free",
+			"api": "openai-completions",
+			"provider": "opencode-go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"contextWindow": 1000000,
+			"maxTokens": 131072
+		},
+		"claude-haiku-5-5": {
+			"id": "claude-haiku-5-5",
+			"name": "Anthropic Haiku 5.5",
+			"api": "openai-completions",
+			"provider": "opencode-go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.1,
+				"output": 0.5,
+				"cacheRead": 0.01,
+				"cacheWrite": 0.125
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 128000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "high"
+			}
+		},
 		"deepseek-v4-flash": {
 			"id": "deepseek-v4-flash",
 			"name": "DeepSeek V4 Flash",
@@ -61642,6 +61681,48 @@
 				"requiresReasoningContentForToolCalls": true
 			}
 		},
+		"deepseek-v4.1-flash": {
+			"id": "deepseek-v4.1-flash",
+			"name": "DeepSeek V4.1 Flash",
+			"api": "openai-completions",
+			"provider": "opencode-go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"contextWindow": 1048576,
+			"maxTokens": 384000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "minimal",
+				"maxLevel": "xhigh"
+			},
+			"compat": {
+				"supportsToolChoice": false,
+				"reasoningContentField": "reasoning_content",
+				"requiresReasoningContentForToolCalls": true
+			}
+		},
+		"gemini-4-argon-contributor": {
+			"id": "gemini-4-argon-contributor",
+			"name": "Gemini 4 Argon Contributor",
+			"api": "openai-responses",
+			"provider": "opencode-go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"contextWindow": 1048576,
+			"maxTokens": 65536,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "low",
+				"maxLevel": "high"
+			}
+		},
 		"glm-5": {
 			"id": "glm-5",
 			"name": "GLM-5",
@@ -61766,6 +61847,25 @@
 			"contextWindow": 1050000,
 			"maxTokens": 128000
 		},
+		"gpt-6-luna": {
+			"id": "gpt-6-luna",
+			"name": "GPT-6 Luna",
+			"api": "openai-responses",
+			"provider": "opencode-go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"contextWindow": 1050000,
+			"maxTokens": 128000,
+			"thinking": {
+				"mode": "effort",
+				"minLevel": "low",
+				"maxLevel": "max"
+			}
+		},
 		"grok-4.5": {
 			"id": "grok-4.5",
 			"name": "Grok 4.5",
@@ -62015,6 +62115,20 @@
 			"contextWindow": 1000000,
 			"maxTokens": 131072
 		},
+		"longcat-2.5-preview-free": {
+			"id": "longcat-2.5-preview-free",
+			"name": "LongCat 2.5 Preview Free",
+			"api": "openai-completions",
+			"provider": "opencode-go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"contextWindow": 1000000,
+			"maxTokens": 131072
+		},
 		"mimo-v2-omni": {
 			"id": "mimo-v2-omni",
 			"name": "MiMo-V2-Omni",
@@ -62417,9 +62531,9 @@
 			"contextWindow": 1000000,
 			"maxTokens": 131072
 		},
-		"union-alpha": {
-			"id": "union-alpha",
-			"name": "Union Alpha Free",
+		"space-bunny": {
+			"id": "space-bunny",
+			"name": "Space Bunny",
 			"api": "openai-completions",
 			"provider": "opencode-go",
 			"baseUrl": "https://opencode.ai/zen/go/v1",
@@ -62428,12 +62542,12 @@
 				"text",
 				"image"
 			],
-			"contextWindow": 262144,
+			"contextWindow": 1000000,
 			"maxTokens": 131072
 		},
-		"claude-haiku-5-5": {
-			"id": "claude-haiku-5-5",
-			"name": "Anthropic Haiku 5.5",
+		"step-5-preview": {
+			"id": "step-5-preview",
+			"name": "Step 5 Preview",
 			"api": "openai-completions",
 			"provider": "opencode-go",
 			"baseUrl": "https://opencode.ai/zen/go/v1",
@@ -62442,19 +62556,27 @@
 				"text",
 				"image"
 			],
-			"cost": {
-				"input": 0.1,
-				"output": 0.5,
-				"cacheRead": 0.01,
-				"cacheWrite": 0.125
-			},
-			"contextWindow": 1000000,
-			"maxTokens": 128000,
+			"contextWindow": 256000,
+			"maxTokens": 64000,
 			"thinking": {
 				"mode": "effort",
 				"minLevel": "minimal",
-				"maxLevel": "high"
+				"maxLevel": "xhigh"
 			}
+		},
+		"union-alpha": {
+			"id": "union-alpha",
+			"name": "Union Alpha Free",
+			"api": "openai-completions",
+			"provider": "opencode-go",
+			"baseUrl": "https://opencode.ai/zen/go/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"contextWindow": 262144,
+			"maxTokens": 131072
 		}
 	},
 	"opencode-zen": {