Sergey Kozyrenko b8b90f8349 refactor(providers): use native adaptive thinking from the langchaingo fork ...

Adaptive thinking (Claude Opus 4.7+) is now implemented natively in the
vxcontrol/langchaingo fork (v0.1.14-update.6): the anthropic and bedrock clients
emit thinking.type=adaptive + output_config.effort and omit the sampling params
adaptive models reject. PentAGI no longer patches the serialized request body.

- pconfig.PrepareAdaptiveCallOptions appends llms.WithAdaptiveReasoning; the
  ctx-effort plumbing (WithAdaptiveEffort/AdaptiveEffortFromContext) is removed.
- Delete the bedrock smithy Build middleware and anthropic http RoundTripper
  (adaptive_thinking.go + tests in both packages) that rewrote the request body.
- Bump the langchaingo require to v0.1.14-update.6; refresh llms_how_to.md.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-22 00:47:32 +07:00

..

installer

docs: tighten macOS installer warning guidance

2026-06-19 04:45:28 +07:00

analytics_api.md

…

chain_ast.md

…

chain_summary.md

…

charm.md

…

config.md

docs: propagate MiniMax + Claude 4.7/4.8 across deploy files and guides (refs #288, #328)

2026-06-21 18:04:43 +07:00

controller.md

…

database.md

docs: propagate MiniMax + Claude 4.7/4.8 across deploy files and guides (refs #288, #328)

2026-06-21 18:04:43 +07:00

docker.md

feat: enhance Docker client with container file operations and API integration

2026-04-27 13:19:39 +03:00

flow_execution.md

docs: add qwen long-flow troubleshooting

2026-06-19 04:45:05 +07:00

gemini.md

…

installer.md

…

langfuse.md

…

llms_how_to.md

refactor(providers): use native adaptive thinking from the langchaingo fork

2026-06-22 00:47:32 +07:00

observability.md

…

ollama.md

…

prompt_engineering_openai.md

…

prompt_engineering_pentagi.md

Merge pull request #276 from mason5052/codex/issue-71-scope-of-work-template

2026-04-29 01:08:29 +04:00