Heads up This site is currently under heavy development.
Subscribe Get it delivered — the daily firehose, filtered to the tools you run, plus the documentation changes vendors never announce. Compare plans →

The AI Toolchain — issue -184, February 14, 2026

THE AI TOOLCHAIN NO. -184
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED FEBRUARY 14, 2026 · EVERY WEEKDAY
EDITIONS tail grep head diff uniq

The daily firehose — everything the toolchain shipped today, already filtered.

// HOW THIS ISSUE IS MADE

We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.

VIEW
ISSUE VIEW full issue
Do you prefer this view? 
$ tct list   # 8 tools matched
AI & LLM Tooling
◆  AI Coding Agents

GitHub Copilot CLI

Sources Release notes → v0.0.410 NOTES

GitHub Copilot CLI v0.0.410 adds /init suppress, repo-level validation tool controls, ACP session loading, and new keyboard/shell ergonomics.

└──▷ GET THIS VERSION
$ git clone --branch v0.0.410 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.410
└──▷ TRY IT
Silence per-repo init suggestions after the feature is noisy in a monorepo.
$ /init suppress
  • ›Adds /init suppress subcommand to control init suggestions on a per-repository basis.
  • ›Adds repo-level settings to disable individual validation tools.
  • ›Extends skill name validation to support underscores, dots, and spaces; makes name and description optional in skill frontmatter with sensible fallbacks.
  • ›Supports tilde (~) expansion in MCP server cwd configuration.
  • ›ACP server now supports loading existing sessions.
+9 moreshow less
  • ›Adds Ctrl+Z suspend/resume support on Unix platforms.
  • ›Adds Ctrl+D to exit the CLI on an empty prompt.
  • ›Adds Ctrl+N and Ctrl+P as arrow-key alternatives in the input prompt.
  • ›Shell mode is now accessed only via ! and is removed from the Shift+Tab cycle.
  • ›Shift+Enter inserts newlines in terminals that support the kitty keyboard protocol.
  • ›Adds Page Up / Page Down keyboard scrolling in alt-screen mode.
  • ›MCP server errors and loading issues now surface in the timeline.
  • ›Shows IDE file-selection indicator in the status bar when connected to an IDE.
  • ›Appends a Copilot co-authored-by trailer to git commits created by the tool.
Was this useful?

SST OpenCode

Sources Release notes → v1.2.1 2 RELEASES · 2026-02-14 NOTES STABLE

The open source coding agent.

OpenCode v1.2.1 migrates session storage to SQLite and adds a new PartDelta SDK event for incremental updates.

└──▷ GET THIS VERSION
$ git clone --branch v1.2.1 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.2.1
  • ›Migrates all flat-file session data to a single SQLite database on first run, enabling faster and more scalable session storage.
  • ›New PartDelta SDK event delivers only incremental changes to parts, avoiding repeated transmission of full text-part content.
  • ›Shows all project sessions from any working directory, not just the current one.
└──▷ BREAKING ON UPGRADE
  • !On first run after upgrading, a one-time data migration runs automatically, converting flat files in the data directory to a SQLite database (~/.local/share/opencode/opencode.db* on Linux/macOS, %APPDATA% on Windows); depending on data volume this may take significant time before the tool becomes usable.
1 more release in this issue · 2026-02-14
v1.2.0 NOTES STABLE

OpenCode v1.2.0 migrates storage to SQLite and adds a PartDelta SDK event plus a --dir CLI flag.

└──▷ GET THIS VERSION
$ git clone --branch v1.2.0 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.2.0
└──▷ TRY IT
Run opencode against a specific project directory without changing your shell's working directory.
$ opencode run --dir /path/to/project
  • ›Migrates session data from flat files to a single SQLite database for improved storage performance and reliability.
  • ›New PartDelta SDK bus event (message.part.delta) delivers only incremental text-part changes, eliminating redundant full-content retransmissions.
  • ›New --dir option on the run command lets you specify the working directory at invocation time.
  • ›Moves timeout configuration from the programmatic API to a CLI flag, enabling per-invocation timeout control.
└──▷ BREAKING ON UPGRADE
  • !On first run, all flat files in the data directory are migrated to ~/.local/share/opencode/opencode.db (or %APPDATA% on Windows); the migration may take significant time depending on data volume and hardware.
Was this useful?

Alibaba Qwen Code

Sources Release notes → v0.10.2 2 RELEASES · 2026-02-14 NOTES STABLE

Qwen Code v0.10.2 adds --session-id for CLI/SDK session control and TPM throttling retry handling.

└──▷ GET THIS VERSION
$ git clone --branch v0.10.2 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.10.2
└──▷ TRY IT
Resume or correlate a specific agent session by ID — useful when scripting multi-turn workflows or debugging a particular run.
$ qwen-code --session-id <your-session-id> 'Continue the refactor we started'
  • ›Adds --session-id flag to the CLI and SDK to attach or resume a specific session by ID.
  • ›Adds TPM throttling error handling with an automatic 1-minute retry delay when rate limits are hit.
1 more release in this issue · 2026-02-14
v0.10.1-nightly.20260214.03c38899 NOTES STABLE

Qwen Code v0.10.1-nightly adds --session-id for CLI/SDK and TPM throttling retry handling.

└──▷ GET THIS VERSION
$ git clone --branch v0.10.1-nightly.20260214.03c38899 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.10.1-nightly.20260214.03c38899
└──▷ TRY IT
Resume or correlate a specific conversation session across CLI invocations by pinning a session ID.
$ qwen --session-id my-debug-session-001 'Continue analysing the auth module'
  • ›Adds --session-id flag to the CLI and SDK, enabling callers to specify or resume a named session.
  • ›Adds TPM throttling error handling with an automatic 1-minute retry delay when rate limits are hit.
Was this useful?
◆  AI Model & Data Infrastructure

Ollama

Sources Release notes → v0.16.2 NOTES

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Ollama v0.16.2 adds web search for cloud models and a new setting to block cloud data egress.

└──▷ GET THIS VERSION
$ git clone --branch v0.16.2 https://github.com/ollama/ollama.git
# already have the repo? check out this version:
$ git checkout v0.16.2
└──▷ TRY IT
Keep all inference on-device — block cloud model access entirely for air-gapped or sensitive environments.
$ OLLAMA_NO_CLOUD=1 ollama serve
Run a live web-augmented query through Claude without leaving the Ollama CLI.
$ ollama launch claude:cloud
  • ›Adds web search support when running ollama launch claude with :cloud models.
  • ›New OLLAMA_NO_CLOUD=1 environment variable (and app setting) to disable cloud models and keep data on-device.
Was this useful?
◆  AI Agent Frameworks

OpenClaw

Sources Release notes → v2026.2.13 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.2.13 adds Discord voice messages, Hugging Face provider support, configurable presence status, and Slack thread-ownership gating.

└──▷ GET THIS VERSION
$ git clone --branch v2026.2.13 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.13
  • ›Adds Discord voice message sending with waveform previews from local audio files, including silent delivery.
  • ›Adds configurable Discord presence status, activity, type, and URL (custom status defaults to activity text).
  • ›Adds Slack/plugin thread-ownership outbound gating via message_sending hooks, with @-mention bypass tracking and cancel/modify behavior.
  • ›Adds first-class Hugging Face Inference provider support with onboarding auth flow, API key configuration, and default-model selection.
  • ›Adds pre-prompt context diagnostics for agent embedded runner calls (messages, systemPromptChars, promptChars, provider/model, session file) to aid overflow debugging.
+4 moreshow less
  • ›Adds synthetic catalog support for the hf:zai-org/GLM-5 agent model.
  • ›Adds security audit misconfiguration checks for sandbox Docker config, ineffective gateway.nodes.denyCommands entries, minimal tool-profile overrides, and permissive extension-plugin tool reachability.
  • ›Blocks high-risk tools (sessions_spawn, sessions_send, gateway, whatsapp_login) from HTTP /tools/invoke by default, with gateway.tools.{allow,deny} overrides.
  • ›Adds security audit distinction between external webhooks (hooks.enabled) and internal hooks (hooks.internal.enabled) in attack-surface summaries.
└──▷ BREAKING ON UPGRADE
  • !Canvas IP-based auth fallback now only accepts machine-scoped addresses (RFC1918, link-local, ULA IPv6, CGNAT); public-source IP matches now require bearer token auth.
Was this useful?

PydanticAI

Sources Release notes → v1.59.0 NOTES

PydanticAI v1.59.0 adds Model.model_id, aggregated usage flag, BaseModel support in Contains, and Vercel AI metadata injection

└──▷ GET THIS VERSION
$ git clone --branch v1.59.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:
$ git checkout v1.59.0
└──▷ USE IT
Inspect which provider and model a configured agent is using at runtime, without string-parsing.
python 
print(model.model_id)  # e.g. 'openai:gpt-4o'
  • ›Adds Model.model_id property that returns the model identifier in provider:model format.
  • ›Adds opt-in flag for aggregated usage attribute names.
  • ›Enhances Contains evaluator to support pydantic.BaseModel instances as expected values.
  • ›Allows BaseChunks to be injected into the Vercel AI adapter through ToolReturnPart.metadata.
Was this useful?
◆  Local LLM Runtimes

llama.cpp

Sources Release notes → b8054 4 RELEASES · 2026-02-14 NOTES STABLE

llama.cpp b8054 adds multimodal support for Nemotron Nano 12B v2 VL.

└──▷ GET THIS VERSION
$ git clone --branch b8054 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8054
  • ›Adds vision-language (VL) support for the Nemotron Nano 12B v2 model, including pre-downsampled position embeddings during GGUF conversion for fixed input sizes.
3 more releases in this issue · 2026-02-14
b8051 NOTES STABLE

llama.cpp b8051 adds NetBSD build support.

└──▷ GET THIS VERSION
$ git clone --branch b8051 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8051
  • ›Adds NetBSD build support, expanding platform coverage to include NetBSD targets.
b8036 NOTES STABLE

llama.cpp b8036 adds support for the GLM MoE DSA model architecture.

└──▷ GET THIS VERSION
$ git clone --branch b8036 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8036
  • ›Adds support for the GLM MoE DSA model architecture (note: the indexer component is not yet supported in this release).
b8033 NOTES STABLE

llama.cpp b8033 adds --verbose-prompt flag support.

└──▷ GET THIS VERSION
$ git clone --branch b8033 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8033
└──▷ TRY IT
Inspect exactly how your prompt is tokenized before a model run, useful when diagnosing unexpected model behavior.
$ llama-cli --verbose-prompt -m model.gguf -p "Tell me about buffer overflows"
  • ›Adds --verbose-prompt flag to print the full tokenized prompt before inference, aiding prompt debugging and inspection.
Was this useful?
Other / Uncategorized
◆  AI OBSERVABILITY

Weights & Biases Weave

Sources Release notes → v0.52.28 NOTES

Weave v0.52.28 adds OpenAI Realtime GA support, $lt/$lte ORM filters, and resource attributes for W&B vars via OTel.

└──▷ GET THIS VERSION
$ git clone --branch v0.52.28 https://github.com/wandb/weave.git
# already have the repo? check out this version:
$ git checkout v0.52.28
  • ›Adds $lt and $lte comparison operators to the ORM query layer, enabling range-based filtering of calls.
  • ›Adds support for resource attributes for W&B vars via OpenTelemetry integration.
  • ›New OTel projects now write to the calls_complete table for improved call stats and usage tracking.
  • ›Promotes OpenAI Realtime tracing support to GA.
  • ›Exposes wb_run and storage data fields on calls.
+1 moreshow less
  • ›Adds Vertex AI as a supported LLM provider.
Was this useful?
// END OF TRANSMISSION

The AI Toolchain · curated daily · February 14, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

▷ Subscribe
my-toolchain — 0 tools
paste an install list to detect your tools

A brew list, a Brewfile, requirements.txt, a Dockerfile — or just the product names, free-form. Nothing leaves your browser.

    browse all tools →