- Add `fetchAbacusModels()` to dynamically retrieve models from Abacus RouteLLM API
- Fall back to static model list when Abacus API fetch fails
- Add GPT-5 Codex variants (5, 5.1, 5.1-max, 5.2) to static models
- Add GPT-5.2 and GPT-5.2-chat-latest to static model list
- Add claude-opus-4-6 and gemini-3-flash-preview to static models
- Add kimi-k2.5, glm-4.7, and glm-5 to static model list
- Rename `qwen/qwen3-Max` to lowercase `qwen3-max`
- Handle `static:abacus` as special case in `ListModels` routing
# CHANGES
- Update Anthropic SDK to version 1.22.0 for improved functionality
- Bump AWS SDK and Bedrock runtime to improve cloud integration
- Upgrade Ollama dependency to version 0.15.6 for model support
- Refresh Google API and GenAI libraries to current stable releases
- Update Go Git and Billy modules to enhance repository handling
- Synchronize various golang.org x-library versions for better system compatibility
- Patch minor dependencies including SQLite, i18n, and Perplexity SDK
## CHANGES
- Add `check_falsifiability` pattern for evaluating testability of claims
- Add `detect_mind_virus` pattern for identifying manipulative belief systems
- Add `extract_ethical_framework` pattern for analyzing implicit ethics in text
- Add `ultimate_law_safety` pattern for evaluating actions against minimal ethics
- Register new patterns in `suggest_pattern` category mappings (ANALYSIS, CR THINKING, EXTRACT)
- Update `pattern_explanations.md` numbering to accommodate 4 new entries
- Add pattern descriptions and extracts to JSON metadata files
## CHANGES
- Add `explain_terms_and_conditions` pattern for legal agreement analysis
- Rename `suggest_moltbot_command` to `suggest_openclaw_pattern` with updated branding
- Register both new patterns in pattern descriptions and extracts JSON
- Update `suggest_pattern` category indexes with new pattern entries
- Add pattern summaries to `suggest_pattern/user.md` documentation
- Renumber all pattern explanations to accommodate new entries
- Remove deprecated `suggest_moltbot_command` pattern entirely
Add four patterns implementing minimal, falsifiable ethical constraints
for AGI safety evaluation:
- ultimate_law_safety: Evaluate actions against "no unwilling victims" principle
- detect_mind_virus: Identify manipulative reasoning that resists correction
- check_falsifiability: Verify claims can be tested and proven wrong
- extract_ethical_framework: Surface implicit ethics in documents/policies
These patterns derive from the Ultimate Law framework (github.com/ghrom/ultimatelaw),
which takes a different approach to AI alignment: instead of encoding contested
"human values," define the minimal boundary no agent may cross.
The core insight: Not "align AI with human values" but "constrain any agent
from creating unwilling victims."
Framework characteristics:
- Minimal: smallest possible constraint set
- Logically derivable: not arbitrary cultural preferences
- Falsifiable: can be challenged and improved
- Agent-agnostic: works for humans, AI, corporations, governments
- Computable: precise enough for algorithmic implementation
Each pattern includes system.md (prompt) and README.md (documentation).
See https://www.anthropic.com/news/claude-opus-4-6
## CHANGES
- Upgrade anthropic-sdk-go from v1.20.0 to v1.21.0
- Add `ClaudeOpus4_6` to supported Anthropic model list
- Remove unused indirect dependencies from go.mod and go.sum
- Clean up legacy protobuf and gRPC version references
- Remove stale tensor, math, and image processing libraries
- Drop unused table writer and console dependencies
- Prune obsolete cloud.google.com version pins
Bumps the npm_and_yarn group with 1 update in the /web directory: @isaacs/brace-expansion.
Updates `@isaacs/brace-expansion` from 5.0.0 to 5.0.1
---
updated-dependencies:
- dependency-name: "@isaacs/brace-expansion"
dependency-version: 5.0.1
dependency-type: indirect
dependency-group: npm_and_yarn
...
Signed-off-by: dependabot[bot] <support@github.com>
- Update default API version from 2024-05-01-preview to 2025-04-01-preview
(required for o-series and GPT-5 models)
- Remove NeedsRawMode override that always returned false, inheriting parent
logic that correctly skips temperature/top_p for reasoning models
- Add /responses route to deployment middleware for future v1 API support
Tested against Azure OpenAI gpt-5.2-chat deployment.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
## CHANGES
- Bump `anthropic-sdk-go` dependency from v1.19.0 to v1.20.0
- Add deprecation notice for pre-February 2026 legacy models
- Add new Claude Sonnet 4.0 and Opus 4.0 model aliases
- Extend 1M context beta support to all Sonnet 4 variants
- Reorganize model list to separate deprecated from current models
- Add `neturl` to VS Code spell-check dictionary
- Remove OAuth support from Anthropic client
- Delete `oauth.go` and related test files
- Simplify `IsConfigured` to check only API key
- Update configuration handling to remove OAuth references
- Clean up imports and unused variables in `anthropic.go`
- Adjust `GetConfig` and `UpdateConfig` methods in server configuration
- Remove OAuth-related environment variables from configuration
## CHANGES
- Rename `suggest_clawdbot_command` pattern to `suggest_moltbot_command`
- Replace all `clawdbot` CLI references with `moltbot` in pattern docs
- Update command examples to use new `moltbot` binary name
- Add new dictionary words for VSCode spellcheck (Moltbot, schtasks, etc.)
- Fix markdown formatting with proper table alignment
Address Copilot review: clarify that multiple commands should be
combined on a single line with && to preserve head -1 behavior,
with follow-up steps described in the explanation section.
Add a new pattern for suggesting Clawdbot CLI commands based on
natural language intent. Clawdbot is an open-source AI agent framework
(github.com/clawdbot/clawdbot) that connects LLMs to messaging
platforms, devices, and developer tools.
This follows the same structure as suggest_gt_command: command
reference tables, intent mapping, and a pipe-friendly output format
where the first line is the executable command.
All commands verified against clawdbot help and subcommand --help
output (v2026.1.23).
