update read path

codex-rs/core/src/memories/mod.rs

@@ -29,9 +29,9 @@ mod phase_one {
     /// Prompt used for phase 1.
     pub(super) const PROMPT: &str = include_str!("../../templates/memories/stage_one_system.md");
     /// Maximum number of rollout candidates processed per startup pass.
-    pub(super) const MAX_ROLLOUTS_PER_STARTUP: usize = 8;
+    pub(super) const MAX_ROLLOUTS_PER_STARTUP: usize = 128;
     /// Concurrency cap for startup memory extraction and consolidation scheduling.
-    pub(super) const CONCURRENCY_LIMIT: usize = 8;
+    pub(super) const CONCURRENCY_LIMIT: usize = 64;
     /// Fallback stage-1 rollout truncation limit (tokens) when model metadata
     /// does not include a valid context window.
     pub(super) const DEFAULT_STAGE_ONE_ROLLOUT_TOKEN_LIMIT: usize = 150_000;
@@ -45,7 +45,7 @@ mod phase_one {
     /// framing, and model output.
     pub(super) const CONTEXT_WINDOW_PERCENT: i64 = 70;
     /// Maximum rollout age considered for phase-1 extraction.
-    pub(super) const MAX_ROLLOUT_AGE_DAYS: i64 = 30;
+    pub(super) const MAX_ROLLOUT_AGE_DAYS: i64 = 90;
     /// Minimum rollout idle time required before phase-1 extraction.
     pub(super) const MIN_ROLLOUT_IDLE_HOURS: i64 = 12;
     /// Lease duration (seconds) for phase-1 job ownership.

codex-rs/core/templates/memories/read_path.md

@@ -1,12 +1,14 @@
 ## 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's 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 (e.g., a one-line change, chit-chat,
+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)
@@ -25,12 +27,22 @@ Quick memory pass (when applicable):
 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.
+it's 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, 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 }}
 ========= 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.