agent/codex
2
0
Fork 0
mirror of https://github.com/pchuan98/codex.git synced 2026-07-01 00:31:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update read_path prompt (#11763)

Browse Source 
## Summary

- Created branch zuxin/read-path-update from main.
- Copied codex-rs/core/templates/memories/read_path.md from the current
branch.
- Committed the content change.

## Testing
Not run (content copy + commit only).
This commit is contained in:
zuxin-oai
2026-02-13 18:34:54 +00:00
committed by GitHub
parent b98c810328
commit b934ffcaaa
1 changed files with 41 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/core/templates/memories/read_path.md
+41 -15
View File
@@ -1,15 +1,21 @@
## Memory ## Memory
You have access to a memory folder with guidance from prior runs. It can save time and help you stay consistent, You have access to a memory folder with guidance from prior runs. It can save
but it's optional: use it whenever it's likely to help. time and help you stay consistent. Use it whenever it is likely to help.
Decision boundary: should you use memory for the new user query? Decision boundary: should you use memory for a new user query?
- You can SKIP memory when the new user query is trivial (e.g. a one-liner change, chit chat, simple formatting, a quick lookup) - You may skip memory when the new query is trivial (for example,
or clearly unrelated to this workspace / prior runs / memory summary below. a one-line change, chit-chat, or simple formatting) or clearly
- You SHOULD do a quick memory pass when the new user query is ambiguous and relevant to the memory summary below, or when consistency with prior decisions/conventions matters. unrelated to this workspace or the memory summary below.
- You SHOULD do a quick memory pass when the new query is ambiguous and likely
relevant to the memory summary below, or when consistency with prior
decisions/conventions matters.
Especially if the user asks about a specific repo/module/code path that seems
relevant, skim/search the relevant memory files first before diving into the repo.
Memory layout (general -> specific): Memory layout (general -> specific):
- {{ base_path }}/memory_summary.md (already provided below; do NOT open again) - {{ base_path }}/memory_summary.md (already provided below; do NOT open
again)
- {{ base_path }}/MEMORY.md (searchable registry; primary file to query) - {{ base_path }}/MEMORY.md (searchable registry; primary file to query)
- {{ base_path }}/skills/<skill-name>/ (skill folder) - {{ base_path }}/skills/<skill-name>/ (skill folder)
- SKILL.md (entrypoint instructions) - SKILL.md (entrypoint instructions)
@@ -19,18 +25,38 @@ Memory layout (general -> specific):
- {{ base_path }}/rollout_summaries/ (per-rollout recaps + evidence snippets) - {{ base_path }}/rollout_summaries/ (per-rollout recaps + evidence snippets)
Quick memory pass (when applicable): Quick memory pass (when applicable):
1) Skim the MEMORY_SUMMARY included below and extract a few task-relevant keywords (e.g. repo / module names, error strings, etc.). 1) Skim the MEMORY_SUMMARY included below and extract a few task-relevant
2) Search {{ base_path }}/MEMORY.md for those keywords, and for any referenced rollout summary files and skills. keywords (for example repo/module names, error strings, etc.).
3) If relevant rollout summary files and skills exist, open the matching files under {{ base_path }}/rollout_summaries/ and {{ base_path }}/skills/. 2) Search {{ base_path }}/MEMORY.md for those keywords, and for any referenced
rollout summary files and skills.
3) If relevant rollout summary files and skills exist, open matching files
under {{ base_path }}/rollout_summaries/ and {{ base_path }}/skills/.
4) If nothing relevant turns up, proceed normally without memory. 4) If nothing relevant turns up, proceed normally without memory.
During execution: if you hit repeated errors, confusing behavior, or you suspect there's relevant prior context, During execution: if you hit repeated errors, confusing behavior, or you suspect
it's worth redoing the quick memory pass. Treat memory as guidance, not truth: if memory conflicts with the current repo state, there is relevant prior context, it is worth redoing the quick memory pass.
tool outputs, or environment, user feedback, the current state wins. If you discover stale or misleading guidance, update the
memory files accordingly. When to update memory:
- Treat memory as guidance, not truth: if memory conflicts with the current
repo state, tool outputs, or environment, the user feedback, the current state
wins. If you discover stale or misleading guidance, update the memory files
accordingly.
- When user explicitly asks you to remember something or update the memory, you
should revise the files accordingly. Usually you should directly update
memory_summary.md (such as general tips and user profile section) and MEMORY.md.
Memory citation requirements:
- If ANY relevant memory files were used: you must output exactly one final
line:
Memory used: `<file1>:<line_start>-<line_end>`, `<file2>:<line_start>-<line_end>`, ...
- Never include memory citations inside the pull-request message itself.
- Never cite blank lines; double-check ranges.
- Append these at the VERY END of the final reply; last line only
- If user ask you do not output citations, you shouldn't do it.
========= MEMORY_SUMMARY BEGINS ========= ========= MEMORY_SUMMARY BEGINS =========
{{ memory_summary }} {{ memory_summary }}
========= MEMORY_SUMMARY ENDS ========= ========= MEMORY_SUMMARY ENDS =========
If memory is relevant for a new user query, start with the quick memory pass above. If memory seems to be relevant for a new user query, always start with the quick
memory pass above.