mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-01 01:51:44 +00:00
585855d2ca
Anthropic extended thinking blocks include an opaque 'signature' field required for thinking chain continuity across multi-turn tool-use conversations. Previously, normalize_anthropic_response() extracted only the thinking text and set reasoning_details=None, discarding the signature. On subsequent turns the API could not verify the chain. Changes: - _to_plain_data(): new recursive SDK-to-dict converter with depth cap (20 levels) and path-based cycle detection for safety - _extract_preserved_thinking_blocks(): rehydrates preserved thinking blocks (including signature) from reasoning_details on assistant messages, placing them before tool_use blocks as Anthropic requires - normalize_anthropic_response(): stores full thinking blocks in reasoning_details via _to_plain_data() - _extract_reasoning(): adds 'thinking' key to the detail lookup chain so Anthropic-format details are found alongside OpenRouter format Salvaged from PR #4503 by @priveperfumes — focused on the thinking block continuity fix only (cache strategy and other changes excluded). |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| anthropic_adapter.py | ||
| auxiliary_client.py | ||
| context_compressor.py | ||
| context_references.py | ||
| copilot_acp_client.py | ||
| credential_pool.py | ||
| display.py | ||
| insights.py | ||
| model_metadata.py | ||
| models_dev.py | ||
| prompt_builder.py | ||
| prompt_caching.py | ||
| redact.py | ||
| skill_commands.py | ||
| skill_utils.py | ||
| smart_model_routing.py | ||
| title_generator.py | ||
| trajectory.py | ||
| usage_pricing.py | ||