20 changes found
20 changes found from /v1/search
X post: User: @shmidtqq Post ID: 2071950221764948023 Text: I MADE MY AI AGENT 10X FASTER WITHOUT CHANGING THE MODEL not a smarter model, not a bigger context window, not another c
X post: User: @shmidtqq Post ID: 2071950221764948023 Text: I MADE MY AI AGENT 10X FASTER WITHOUT CHANGING THE MODEL not a smarter model, not a bigger context window, not another c
X post: User: @shmidtqq Post ID: 2071950221764948023 Text: I MADE MY AI AGENT 10X FASTER WITHOUT CHANGING THE MODEL not a smarter model, not a bigger context window, not another c
X post: User: @riyazmd774 Post ID: 2067294202355208688 Text: CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could
X post: User: @riyazmd774 Post ID: 2067294202355208688 Text: CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could
X post: User: @riyazmd774 Post ID: 2067294202355208688 Text: CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could
X post: User: @riyazmd774 Post ID: 2067294202355208688 Text: CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could
X post: User: @riyazmd774 Post ID: 2067294202355208688 Text: CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could
X post: User: @riyazmd774 Post ID: 2067294202355208688 Text: CHINA JUST DROPPED AN AI CODING MODEL WITH A 1M CONTEXT WINDOW. And I connected it to Claude Code to see what it could
X post: User: @JackWoth98 Post ID: 2066593613098975384 Text: Custom Statusline in Antigravity CLI🚦⚙️ Track agent state, context window, subagents all right from the footer of you
X post: User: @JackWoth98 Post ID: 2066593613098975384 Text: Custom Statusline in Antigravity CLI🚦⚙️ Track agent state, context window, subagents all right from the footer of you
X post: User: @JackWoth98 Post ID: 2066593613098975384 Text: Custom Statusline in Antigravity CLI🚦⚙️ Track agent state, context window, subagents all right from the footer of you
Go documentation for Qwen3.7 Plus and Qwen3.6 Plus now separates pricing into ≤256K and >256K token tiers.
Go documentation for Qwen3.7 Plus and Qwen3.6 Plus now separates pricing into ≤256K and >256K token tiers.
Go documentation for Qwen3.7 Plus and Qwen3.6 Plus now separates pricing into ≤256K and >256K token tiers.
CodeCompanion Neovim plugin now lets users directly view and edit the context window mid-conversation, and isolates chats per editor tab so switching files no longer mixes conversations.
CodeCompanion Neovim plugin now lets users directly view and edit the context window mid-conversation, and isolates chats per editor tab so switching files no longer mixes conversations.
CodeCompanion Neovim plugin now lets users directly view and edit the context window mid-conversation, and isolates chats per editor tab so switching files no longer mixes conversations.
CodeCompanion introduces configurable thresholds for automatic context editing and compaction, allowing the plugin to manage context limits per adapter without user intervention.
CodeCompanion introduces configurable thresholds for automatic context editing and compaction, allowing the plugin to manage context limits per adapter without user intervention.
CodeCompanion introduces configurable thresholds for automatic context editing and compaction, allowing the plugin to manage context limits per adapter without user intervention.
The default model for the MiniMax provider in deer-flow is changed from older models to MiniMax-M3, leveraging its larger context window and image input support.
The default model for the MiniMax provider in deer-flow is changed from older models to MiniMax-M3, leveraging its larger context window and image input support.
The default model for the MiniMax provider in deer-flow is changed from older models to MiniMax-M3, leveraging its larger context window and image input support.
A test is added to verify that the specific error message from ollamacloud for context window overflow is correctly matched to the ExceededContextWindow error type, locking in the existing behavior and preventing future regressions in error classification logic.
A test is added to verify that the specific error message from ollamacloud for context window overflow is correctly matched to the ExceededContextWindow error type, locking in the existing behavior and preventing future regressions in error classification logic.
A test is added to verify that the specific error message from ollamacloud for context window overflow is correctly matched to the ExceededContextWindow error type, locking in the existing behavior and preventing future regressions in error classification logic.
The plan approval UI now shows context window usage against the execution model's actual capacity, preventing misleading displays when plan mode runs on a larger-context model than the execution model.
The plan approval UI now shows context window usage against the execution model's actual capacity, preventing misleading displays when plan mode runs on a larger-context model than the execution model.
The plan approval UI now shows context window usage against the execution model's actual capacity, preventing misleading displays when plan mode runs on a larger-context model than the execution model.
The project's 'Integrating AI Capabilities' tutorial now presents MiniMax-M3 as the new flagship model option, replacing MiniMax-M2.7 as the default example in its curl commands and recommendation tips.
The project's 'Integrating AI Capabilities' tutorial now presents MiniMax-M3 as the new flagship model option, replacing MiniMax-M2.7 as the default example in its curl commands and recommendation tips.
The project's 'Integrating AI Capabilities' tutorial now presents MiniMax-M3 as the new flagship model option, replacing MiniMax-M2.7 as the default example in its curl commands and recommendation tips.
Adds Azure OpenAI and Dell Pro AI Studio provider cases to the LangChain chat model switch statement used during content summarization fallback, fixing a crash when agents with those providers try to summarize content exceeding the context window.
Adds Azure OpenAI and Dell Pro AI Studio provider cases to the LangChain chat model switch statement used during content summarization fallback, fixing a crash when agents with those providers try to summarize content exceeding the context window.
Adds Azure OpenAI and Dell Pro AI Studio provider cases to the LangChain chat model switch statement used during content summarization fallback, fixing a crash when agents with those providers try to summarize content exceeding the context window.
RAGFlow introduced a `.rooignore` configuration file to explicitly exclude generated files, caches, and dependencies from AI coding assistant workspaces, reducing token waste and preventing agents from indexing irrelevant or sensitive local data.
RAGFlow introduced a `.rooignore` configuration file to explicitly exclude generated files, caches, and dependencies from AI coding assistant workspaces, reducing token waste and preventing agents from indexing irrelevant or sensitive local data.
RAGFlow introduced a `.rooignore` configuration file to explicitly exclude generated files, caches, and dependencies from AI coding assistant workspaces, reducing token waste and preventing agents from indexing irrelevant or sensitive local data.
A merged PR adds four Ejentum cognitive-harness skills to the Claude Code plugin registry, enabling the agent to call an external MCP server for structured reasoning scaffolds before generating code or architectural plans.
A merged PR adds four Ejentum cognitive-harness skills to the Claude Code plugin registry, enabling the agent to call an external MCP server for structured reasoning scaffolds before generating code or architectural plans.
A merged PR adds four Ejentum cognitive-harness skills to the Claude Code plugin registry, enabling the agent to call an external MCP server for structured reasoning scaffolds before generating code or architectural plans.
The CAMEL framework integrates the Anthropic Claude Opus 4.8 model, configuring its alias, classification, and 1 million token context limit bucket to enable large-context agent workflows.
The CAMEL framework integrates the Anthropic Claude Opus 4.8 model, configuring its alias, classification, and 1 million token context limit bucket to enable large-context agent workflows.
The CAMEL framework integrates the Anthropic Claude Opus 4.8 model, configuring its alias, classification, and 1 million token context limit bucket to enable large-context agent workflows.
The Goose coding agent now dynamically reads the context window size advertised by upstream ACP servers instead of relying solely on a static local configuration, ensuring accurate compaction and truncation decisions.
The Goose coding agent now dynamically reads the context window size advertised by upstream ACP servers instead of relying solely on a static local configuration, ensuring accurate compaction and truncation decisions.
The Goose coding agent now dynamically reads the context window size advertised by upstream ACP servers instead of relying solely on a static local configuration, ensuring accurate compaction and truncation decisions.
Goose introduces an unstable ACP API that allows external controllers to replace the base system prompt or append keyed instructions per session, along with helpers to clear overrides.
Goose introduces an unstable ACP API that allows external controllers to replace the base system prompt or append keyed instructions per session, along with helpers to clear overrides.
Goose introduces an unstable ACP API that allows external controllers to replace the base system prompt or append keyed instructions per session, along with helpers to clear overrides.
Cline v3.86.0 integrates Claude Opus 4.8 and Moonshot Kimi K2.6 as native providers, enabling developers to route coding tasks to models with up to 1M-token context windows for larger repository analysis.
Cline v3.86.0 integrates Claude Opus 4.8 and Moonshot Kimi K2.6 as native providers, enabling developers to route coding tasks to models with up to 1M-token context windows for larger repository analysis.
Cline v3.86.0 integrates Claude Opus 4.8 and Moonshot Kimi K2.6 as native providers, enabling developers to route coding tasks to models with up to 1M-token context windows for larger repository analysis.
The adk-go history builder now preserves intermediate, unrelated function-call and function-response events when consolidating the latest long-running tool response, preventing valid tool history from being silently dropped during conversation replay.
The adk-go history builder now preserves intermediate, unrelated function-call and function-response events when consolidating the latest long-running tool response, preventing valid tool history from being silently dropped during conversation replay.
The adk-go history builder now preserves intermediate, unrelated function-call and function-response events when consolidating the latest long-running tool response, preventing valid tool history from being silently dropped during conversation replay.
AnythingLLM agent tools previously passed an object instead of a string to the context limit caller, causing a silent fallback to an 8K context window. This update adds type validation and error logging to ensure user-defined context limits are strictly respected when processing large documents.
AnythingLLM agent tools previously passed an object instead of a string to the context limit caller, causing a silent fallback to an 8K context window. This update adds type validation and error logging to ensure user-defined context limits are strictly respected when processing large documents.
AnythingLLM agent tools previously passed an object instead of a string to the context limit caller, causing a silent fallback to an 8K context window. This update adds type validation and error logging to ensure user-defined context limits are strictly respected when processing large documents.