fix+feat: agent core fixes (Bucket P — 4 PRs) - #7541
Merged
Conversation
Add delegation.reasoning_effort config key so subagents can run at a different thinking level than the parent agent. When set, overrides the parent's reasoning_config; when empty, inherits as before. Valid values: xhigh, high, medium, low, minimal, none (disables thinking). Config path: delegation.reasoning_effort in config.yaml Files changed: - tools/delegate_tool.py: resolve override in _build_child_agent - hermes_cli/config.py: add reasoning_effort to DEFAULT_CONFIG - tests/tools/test_delegate.py: 4 new tests covering all cases
…xiliary tasks
GPT-5+ models (except gpt-5-mini) are only accessible via the Responses
API on Copilot. When these models were configured as the compression
summary_model (or any auxiliary task), the plain OpenAI client sent them
to /chat/completions which returned a 400 error:
model "gpt-5.4-mini" is not accessible via the /chat/completions endpoint
resolve_provider_client() now checks _should_use_copilot_responses_api()
for the copilot provider and wraps the client in CodexAuxiliaryClient
when needed, routing calls through responses.stream() transparently.
Adds tests for both the wrapping (gpt-5.4-mini) and non-wrapping
(gpt-4.1-mini) paths.
…int against brace paths
- Remove unreachable `if not content_sample` branch inside the truthy
`if content_sample` block in `_is_likely_binary()` (dead code that
could never execute).
- Replace `linter_cmd.format(file=...)` with `linter_cmd.replace("{file}", ...)`
in `_check_lint()` so file paths containing curly braces (e.g.
`src/{test}.py`) no longer raise KeyError/ValueError.
- Add 16 unit tests covering both fixes and edge cases.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Contributor
|
This was referenced Apr 11, 2026
Closed
1 task
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Four agent core fixes salvaged from #6951, #6953, #6950, #6944. All contributor authorship preserved.
1. feat(delegation): configurable reasoning_effort for subagents (#6951, @hermes-agent-dhabibi)
New
delegation.reasoning_effortconfig key. Subagents can run at different thinking levels. 4 tests.2. fix: copilot Responses-API wrapping for auxiliary tasks (#6953, @hermes-agent-dhabibi)
GPT-5+ on Copilot needs Responses API but aux client created plain OpenAI client. Now wraps in CodexAuxiliaryClient when needed. 3 tests.
3. fix(tools): dead code removal + brace path hardening (#6950, @luyao618)
Unreachable code in
_is_likely_binary(),.format()→.replace()in_check_lint()to handle{curly brace}file paths. 16 tests.4. fix(compression): truthful manual compression feedback (#6944, @aquaright1)
/compressno longer shows "✅ Compressed" when nothing changed. Sharedsummarize_manual_compression()helper detects no-ops and explains token estimate increases. Both CLI and gateway updated. 2 test files.Test results
26 targeted tests passing. All 6 modified files compile clean.