Repository navigation
feat: add GPT/Codex execution discipline guidance - #5414
Merged
Merged
Conversation
Adds OPENAI_MODEL_EXECUTION_GUIDANCE — XML-tagged behavioral guidance injected for GPT and Codex models alongside the existing tool-use enforcement. Targets four specific failure modes: - <tool_persistence>: retry on empty/partial results instead of giving up - <prerequisite_checks>: do discovery/lookup before jumping to final action - <verification>: check correctness/grounding/formatting before finalizing - <missing_context>: use lookup tools instead of hallucinating Follows the same injection pattern as GOOGLE_MODEL_OPERATIONAL_GUIDANCE for Gemini/Gemma models. Inspired by OpenClaw PR #38953 and OpenAI's GPT-5.4 prompting guide patterns.
Tommyeds
pushed a commit
to Tommyeds/hermes-agent
that referenced
this pull request
Apr 12, 2026
NousResearch#5414) Adds OPENAI_MODEL_EXECUTION_GUIDANCE — XML-tagged behavioral guidance injected for GPT and Codex models alongside the existing tool-use enforcement. Targets four specific failure modes: - <tool_persistence>: retry on empty/partial results instead of giving up - <prerequisite_checks>: do discovery/lookup before jumping to final action - <verification>: check correctness/grounding/formatting before finalizing - <missing_context>: use lookup tools instead of hallucinating Follows the same injection pattern as GOOGLE_MODEL_OPERATIONAL_GUIDANCE for Gemini/Gemma models. Inspired by OpenClaw PR NousResearch#38953 and OpenAI's GPT-5.4 prompting guide patterns.
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 27, 2026
NousResearch#5414) Adds OPENAI_MODEL_EXECUTION_GUIDANCE — XML-tagged behavioral guidance injected for GPT and Codex models alongside the existing tool-use enforcement. Targets four specific failure modes: - <tool_persistence>: retry on empty/partial results instead of giving up - <prerequisite_checks>: do discovery/lookup before jumping to final action - <verification>: check correctness/grounding/formatting before finalizing - <missing_context>: use lookup tools instead of hallucinating Follows the same injection pattern as GOOGLE_MODEL_OPERATIONAL_GUIDANCE for Gemini/Gemma models. Inspired by OpenClaw PR NousResearch#38953 and OpenAI's GPT-5.4 prompting guide patterns.
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
NousResearch#5414) Adds OPENAI_MODEL_EXECUTION_GUIDANCE — XML-tagged behavioral guidance injected for GPT and Codex models alongside the existing tool-use enforcement. Targets four specific failure modes: - <tool_persistence>: retry on empty/partial results instead of giving up - <prerequisite_checks>: do discovery/lookup before jumping to final action - <verification>: check correctness/grounding/formatting before finalizing - <missing_context>: use lookup tools instead of hallucinating Follows the same injection pattern as GOOGLE_MODEL_OPERATIONAL_GUIDANCE for Gemini/Gemma models. Inspired by OpenClaw PR NousResearch#38953 and OpenAI's GPT-5.4 prompting guide patterns.
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
NousResearch#5414) Adds OPENAI_MODEL_EXECUTION_GUIDANCE — XML-tagged behavioral guidance injected for GPT and Codex models alongside the existing tool-use enforcement. Targets four specific failure modes: - <tool_persistence>: retry on empty/partial results instead of giving up - <prerequisite_checks>: do discovery/lookup before jumping to final action - <verification>: check correctness/grounding/formatting before finalizing - <missing_context>: use lookup tools instead of hallucinating Follows the same injection pattern as GOOGLE_MODEL_OPERATIONAL_GUIDANCE for Gemini/Gemma models. Inspired by OpenClaw PR NousResearch#38953 and OpenAI's GPT-5.4 prompting guide patterns.
waefrebeorn
pushed a commit
to waefrebeorn/slermes
that referenced
this pull request
Jul 2, 2026
NousResearch#5414) Adds OPENAI_MODEL_EXECUTION_GUIDANCE — XML-tagged behavioral guidance injected for GPT and Codex models alongside the existing tool-use enforcement. Targets four specific failure modes: - <tool_persistence>: retry on empty/partial results instead of giving up - <prerequisite_checks>: do discovery/lookup before jumping to final action - <verification>: check correctness/grounding/formatting before finalizing - <missing_context>: use lookup tools instead of hallucinating Follows the same injection pattern as GOOGLE_MODEL_OPERATIONAL_GUIDANCE for Gemini/Gemma models. Inspired by OpenClaw PR NousResearch#38953 and OpenAI's GPT-5.4 prompting guide patterns.
melon-xf
added a commit
to melon-xf/hermes-agent
that referenced
this pull request
Sep 3, 2026
NousResearch#5414) Adds OPENAI_MODEL_EXECUTION_GUIDANCE — XML-tagged behavioral guidance injected for GPT and Codex models alongside the existing tool-use enforcement. Targets four specific failure modes: - <tool_persistence>: retry on empty/partial results instead of giving up - <prerequisite_checks>: do discovery/lookup before jumping to final action - <verification>: check correctness/grounding/formatting before finalizing - <missing_context>: use lookup tools instead of hallucinating Follows the same injection pattern as GOOGLE_MODEL_OPERATIONAL_GUIDANCE for Gemini/Gemma models. Inspired by OpenClaw PR NousResearch#38953 and OpenAI's GPT-5.4 prompting guide patterns.
fsca8
pushed a commit
to fsca8/hermes-agent
that referenced
this pull request
Oct 6, 2026
NousResearch#5414) Adds OPENAI_MODEL_EXECUTION_GUIDANCE — XML-tagged behavioral guidance injected for GPT and Codex models alongside the existing tool-use enforcement. Targets four specific failure modes: - <tool_persistence>: retry on empty/partial results instead of giving up - <prerequisite_checks>: do discovery/lookup before jumping to final action - <verification>: check correctness/grounding/formatting before finalizing - <missing_context>: use lookup tools instead of hallucinating Follows the same injection pattern as GOOGLE_MODEL_OPERATIONAL_GUIDANCE for Gemini/Gemma models. Inspired by OpenClaw PR NousResearch#38953 and OpenAI's GPT-5.4 prompting guide patterns.
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
1 participant
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
Adds
OPENAI_MODEL_EXECUTION_GUIDANCE— XML-tagged behavioral guidance injected for GPT and Codex models alongside the existing tool-use enforcement. Addresses known GPT failure modes where the model abandons work on partial results, skips prerequisite lookups, halluccinates instead of using tools, and declares done without verification.Four guidance sections
<tool_persistence>— Retry on empty/partial results instead of giving up<prerequisite_checks>— Do discovery/lookup before jumping to final action<verification>— Check correctness/grounding/formatting before finalizing<missing_context>— Use lookup tools instead of hallucinatingDesign
Follows the same injection pattern as
GOOGLE_MODEL_OPERATIONAL_GUIDANCEfor Gemini/Gemma. Only injected when model name contains 'gpt' or 'codex'. ~1500 chars / ~370 tokens overhead.Inspired by patterns from OpenAI's GPT-5.4 prompting guide & OpenClaw PR #38953.
Files changed
agent/prompt_builder.py— New constantrun_agent.py— Injection logic in_build_system_prompt()tests/agent/test_prompt_builder.py— 6 new testsTest plan