- CLI/models: keep route-first `models status --json` stdout reserved for the JSON payload by routing auth-profile and startup diagnostics to stderr. Fixes #72962. Thanks @vishutdhar.

- Sessions: ignore future-dated session activity timestamps during reset freshness checks and cap future `updatedAt` values at the merge boundary so clock-skewed messages cannot keep stale sessions alive forever. Fixes #72989. Thanks @martingarramon.

- Plugins/CLI: allow managed plugin installs when the active extensions root is a symlink to a real state directory, while keeping nested target symlinks blocked and suppressing misleading hook-pack fallback errors for install-boundary failures. Fixes #72946. Thanks @mayank6136.

- Providers/Ollama: mark discovered Ollama catalog models as supporting streaming usage metadata so token accounting stays enabled for local models. (#72976) Thanks @sdeyang.

- Gateway/startup: keep hot Gateway boot paths on leaf config imports and add max-RSS reporting to the gateway startup bench so low-memory startup regressions are visible before release. Thanks @vincentkoc.

- WebChat: read `chat.history` from active transcript branches, drop stale streamed assistant tails once final history catches up, and coalesce duplicate in-flight Control UI submits, so rewritten prompts, completed replies, and rapid send events no longer render or process twice. Fixes #72975, #72963, and #72974. Thanks @dmagdici, @lhtpluto, and @Benjamin5281999.

- WebChat/TTS: persist automatic final-mode TTS audio as a supplemental audio-only transcript update instead of adding a second assistant message with the same visible text. Fixes #72830. Thanks @lhtpluto.

expect(visionModel.input).toEqual(["text", "image"]);

expect(visionModel.reasoning).toBe(true);

expect(visionModel.compat?.supportsTools).toBe(true);

expect(visionModel.compat?.supportsUsageInStreaming).toBe(true);

const textModel = buildOllamaModelDefinition("glm-5.1:cloud", 202752, ["completion", "tools"]);

expect(textModel.input).toEqual(["text"]);

expect(textModel.reasoning).toBe(false);

expect(textModel.compat?.supportsTools).toBe(true);

expect(textModel.compat?.supportsUsageInStreaming).toBe(true);

const noCapabilities = buildOllamaModelDefinition("unknown-model", 65536);

expect(noCapabilities.input).toEqual(["text"]);

expect(noCapabilities.compat).toBeUndefined();

expect(noCapabilities.compat?.supportsUsageInStreaming).toBe(true);

});

it("disables tool support when Ollama capabilities omit tools", () => {

const model = buildOllamaModelDefinition("embeddinggemma:latest", 2048, ["embedding"]);

expect(model.reasoning).toBe(false);

expect(model.compat?.supportsTools).toBe(false);

expect(model.compat?.supportsUsageInStreaming).toBe(true);

});

it("parses the last positive Modelfile num_ctx value", () => {

: capabilities.includes("thinking");

const compat =

capabilities === undefined

? undefined

? { supportsUsageInStreaming: true }

: {

supportsTools: capabilities.includes("tools"),

supportsUsageInStreaming: true,

};

return {

id: modelId,

cost: OLLAMA_DEFAULT_COST,

contextWindow: contextWindow ?? OLLAMA_DEFAULT_CONTEXT_WINDOW,

maxTokens: OLLAMA_DEFAULT_MAX_TOKENS,

...(compat ? { compat } : {}),

compat,

};

}