mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-31 06:51:29 +00:00
9c69204d87
reasoning.encrypted_content is sealed to the Responses endpoint that minted it. When a session switches model providers mid-conversation — say the user runs /model gpt-5.5 after several turns on grok-4.3, or vice versa — the persisted codex_reasoning_items carry blobs the new endpoint cannot decrypt, and every subsequent turn fails with HTTP 400 invalid_encrypted_content. This is the cross-issuer prevention layer. Pairs with: * PR #33035 — runtime recovery when the HTTP 400 fires anyway * PR #33146 — prevention for transient rs_tmp_* items Stamps each reasoning item with the issuer kind that minted it (codex_backend / xai_responses / github_responses / other:<url>) at normalize time, then drops items at replay time when the active endpoint differs from the stamp. Unstamped (legacy) items pass through for backwards compatibility. Cherry-picked from @chaconne67's PR #31629. Conflict against current main (#33035's replay_encrypted_reasoning parameter) resolved as 'keep both' — the two guards compose: replay_encrypted_reasoning=False is the session-wide kill switch, current_issuer_kind is the per-item filter that runs only when replay is still enabled. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| anthropic.py | ||
| base.py | ||
| bedrock.py | ||
| chat_completions.py | ||
| codex.py | ||
| codex_app_server.py | ||
| codex_app_server_session.py | ||
| codex_event_projector.py | ||
| hermes_tools_mcp_server.py | ||
| types.py | ||