From b934ffcaaab5d35b12033cd73d8efe01bee8fa1e Mon Sep 17 00:00:00 2001 From: zuxin-oai Date: Fri, 13 Feb 2026 10:34:54 -0800 Subject: [PATCH] Update read_path prompt (#11763) ## 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). --- codex-rs/core/templates/memories/read_path.md | 56 ++++++++++++++----- 1 file changed, 41 insertions(+), 15 deletions(-) diff --git a/codex-rs/core/templates/memories/read_path.md b/codex-rs/core/templates/memories/read_path.md index 5f06131fa..98728ef8b 100644 --- a/codex-rs/core/templates/memories/read_path.md +++ b/codex-rs/core/templates/memories/read_path.md @@ -1,15 +1,21 @@ ## Memory -You have access to a memory folder with guidance from prior runs. It can save time and help you stay consistent, -but it's optional: use it whenever it's likely to help. +You have access to a memory folder with guidance from prior runs. It can save +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? -- You can SKIP memory when the new user query is trivial (e.g. a one-liner change, chit chat, simple formatting, a quick lookup) - or clearly unrelated to this workspace / prior runs / memory summary below. -- 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. +Decision boundary: should you use memory for a new user query? +- You may skip memory when the new query is trivial (for example, +a one-line change, chit-chat, or simple formatting) or clearly +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): -- {{ 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 }}/skills// (skill folder) - SKILL.md (entrypoint instructions) @@ -19,18 +25,38 @@ Memory layout (general -> specific): - {{ base_path }}/rollout_summaries/ (per-rollout recaps + evidence snippets) 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.). -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 the matching files under {{ base_path }}/rollout_summaries/ and {{ base_path }}/skills/. +1) Skim the MEMORY_SUMMARY included below and extract a few task-relevant +keywords (for example repo/module names, error strings, etc.). +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. -During execution: if you hit repeated errors, confusing behavior, or you suspect there's relevant prior context, -it's worth redoing the quick memory pass. Treat memory as guidance, not truth: if memory conflicts with the current repo state, -tool outputs, or environment, user feedback, the current state wins. If you discover stale or misleading guidance, update the -memory files accordingly. +During execution: if you hit repeated errors, confusing behavior, or you suspect +there is relevant prior context, it is worth redoing the quick memory pass. + +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: `:-`, `:-`, ... + - 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 }} ========= 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.