# NousResearch/hermes-agent · Preserve reasoning_effort during switch_model calls

## Open now

- 1 issue, 4 PRs open on GitHub.
- #72856: fix(agent): switch_model resets session-level reasoning_effort to config default
- PR #72857: fix(agent): preserve session reasoning_config when switch_model resolves to None
- PR #72861: fix: preserve reasoning_effort on switch_model (#72856)
- PR #73588: fix(agent): preserve session-level reasoning_effort on switch_model
- PR #117247: fix(reasoning): preserve explicit session overrides across model switches

These members address a bug where switching models resets or loses the session-level reasoning_effort or reasoning_config. The fixes aim to preserve those session-level settings across model switches.

## TL;DR

- 5 member(s): 1 open issue(s), 0 closed issue(s), 4 open PR(s), 0 merged PR(s), 0 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.40`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Open related issues

- #72856: fix(agent): switch_model resets session-level reasoning_effort to config default

## Prior & competing PRs

- **#72857: fix(agent): preserve session reasoning_config when switch_model resolves to None**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/agent_runtime_helpers.py`, `tests/run_agent/test_switch_model_reasoning_override.py`, `tui_gateway/server.py`
- **#72861: fix: preserve reasoning_effort on switch_model (#72856)**. open
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#72857`, `#72857`
  - files: `agent/agent_runtime_helpers.py`
- **#73588: fix(agent): preserve session-level reasoning_effort on switch_model**. open
  - maintainer direction: category `partial_fix`; implication `needs_llm`; refs `5044698939f3`, `#72856`, `#72857`, `#72861`, `#72873`, `#73588`, `#72857`, `#72861`, `#72857`, `#72857`, `#72857`, `#72873`, `#72857`, `#72857`, `#73588`, `#72861`, `#72873`, `#72857`, `#73588`, `#72857`, `#72861`, `#72873`, `#72857`, `#73588`, `#374151`, `#72856`, `#73588`
  - files: `agent/agent_runtime_helpers.py`, `agent/tool_executor.py`, `skills/email/himalaya/SKILL.md`, `skills/email/himalaya/references/configuration.md`, `tests/run_agent/test_switch_model_reasoning_override.py`
- **#117247: fix(reasoning): preserve explicit session overrides across model switches**. open
  - maintainer direction: category `silent_close`; implication `active`
  - files: `agent/agent_runtime_helpers.py`, `agent/nous_wire.py`, `apps/desktop/src/app/shell/model-catalog-menu.test.tsx`, `apps/desktop/src/app/shell/model-catalog-menu.tsx`, `cli.py`, `gateway/slash_commands_model.py`, `hermes_cli/cli_commands_mixin.py`, `hermes_cli/cli_model_switch_mixin.py`, `hermes_cli/cli_session_mixin.py`, `tests/agent/test_nous_wire_auto.py`, `tests/agent/test_switch_model_reasoning_override.py`, `tests/gateway/test_model_command_reasoning_flag.py`, `tests/hermes_cli/test_cli_model_once.py`, `tests/hermes_cli/test_model_switch_reasoning_reresolve.py`, `tests/hermes_cli/test_reasoning_command.py`, `tests/tui_gateway/test_model_switch_reasoning_flag.py`, `tests/tui_gateway/test_reasoning_session_scope.py`, `tests/tui_gateway/test_tui_gateway_server.py`, `tui_gateway/model_switch.py`, `tui_gateway/server.py` (+1 more)

## Fix status

- No merged fix on record.
- Subsystem: `agent`