Open
Conversation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
benfrank241
force-pushed
the
blog/adding-memory-to-codex-with-hindsight
branch
from
040bc43 to
ee69347
Compare
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
cdbartholomew
requested changes
Apr 1, 2026
|
|
||
| **Full-session upsert.** The transcript is stored using the session ID as the document key. If a session is retained multiple times (in chunked mode), the content is upserted rather than duplicated. No accumulation of near-identical entries. | ||
|
|
||
| **Zero dependencies.** The plugin is three Python stdlib scripts. No pip install, no virtualenv, no version conflicts. |
|
|
||
| **Recall adds latency.** Every prompt triggers a Hindsight query before Codex sees it. In practice this is 100–300ms with Hindsight Cloud on a fast connection. For interactive sessions it's imperceptible; for automated scripts it may matter. Use `"recallBudget": "low"` or `"autoRecall": false` if you need to skip it. | ||
|
|
||
| **Retention is asynchronous.** The `retain.py` hook fires asynchronously so it doesn't block your session from exiting. Facts extracted from a session won't appear in recall until the next session. |
Contributor
There was a problem hiding this comment.
The fact may not appear until later, not necessarily the next session. It depends on how fast the async processing goes.
- Clarify "zero dependencies" — hook scripts are stdlib-only but local daemon mode requires uvx; Cloud mode has no local prerequisites - Fix retention timing — facts may appear sooner or later than the next session depending on async processing speed Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Contributor
|
Could we add one short troubleshooting note to the post? Something like: “Nothing happening? Check |
Documents the persistent log files added by the upcoming Codex integration PR: error.log for hook failures, debug.log when debug mode is enabled. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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
2 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
Notes
/img/blog/adding-memory-to-codex-with-hindsight.pngneeded before merge🤖 Generated with Claude Code