fix(memory): keep short pattern terms out of raw JSON metadata columns - #152
Open
DevMello wants to merge 38 commits into
Open
fix(memory): keep short pattern terms out of raw JSON metadata columns#152DevMello wants to merge 38 commits into
DevMello wants to merge 38 commits into
Conversation
merge main to v1.0.5
fix: unify cross-agent action backgrounds
fix: simplify memory tool call headings
feat(memory): commit episode routing on turn complete
fix(memory): separate retrieval content and validate L3 evidence
fix(memory): finalize episode rewards and processing
chore: docs
feat(memory): link related memory details
…emTensor#139) Co-authored-by: antalike <> Co-authored-by: Cursor <cursoragent@cursor.com>
* feat: merge pkg shell * feat: merge pkg shell * feat: merge pkg shell * feat: merge pkg shell
fix(backend): share scan permission per installation
fix(backend): refine onboarding permissions and actions
fix: surface structured quota exhaustion errors
feat(memory): add time-filtered trace recall
feat: trust Codex hooks and reveal account identifiers
…faults (MemTensor#7) loadConfig() caught YAML parse and schema validation errors, logged a console.warn, and returned a fresh default Config. Any onboarded settings (including BYOK provider credentials) were silently discarded and the CLI kept running against defaults with no non-zero exit, contradicting the project's fail-loud philosophy. Throw a new ConfigError (ConfigLoadError for bad YAML/schema, EnvValueError for missing env var references, both now exported) when the config file exists but is invalid. A missing config file still returns the defaults unchanged, since first-run `memmy onboard` depends on that path. The CLI entrypoint (main.ts) catches ConfigError specifically and prints a concise `memmy: <reason>` message with a non-zero exit code instead of an unhandled stack trace; other entrypoints (serve/gateway route through the same CLI main(), and the frontend-bridge/websocket HTTP layer already has generic catch blocks that turn thrown errors into clean error responses).
…allback (MemTensor#9) MemmyMemoryHook.beforeRun/afterRun/sessionStart/sessionEnd caught every connection error from the memory service and only recorded it on an unread `lastError` field, so an unreachable service (e.g. default http://127.0.0.1:18960 down) degraded completely silently: no CLI/log warning, and the LLM turn context received neither a recall block nor any notice, indistinguishable from "memory checked, found nothing". This contradicted the README's fail-loud promise and drove agents to silently fall back to the local MEMORY.md/history.jsonl store. - Replace the blanket try/catch with per-phase handling that emits a deduped console.warn (once per session, reset on recovery) and injects an honest <memmy_memory_status status="unavailable"> notice into the user message so the model is told memory wasn't checked, instead of implying nothing relevant was found. - Drop the stale in-flight turn entry on a failed beforeRun so afterRun doesn't try to complete a turn that was never opened server-side. - Document the new status tag in the memory context protocol prompt. Failures still never crash the turn (fail-loud, not fail-crash).
MemTensor#148) Keep params.user_id for event dimensions while also exposing userId alongside clientId so the cloud proxy can filter and map GA4 user identity. Co-authored-by: antalike <> Co-authored-by: Cursor <cursoragent@cursor.com>
Two-char tokens like "ts" skip FTS and hit the pattern channel, which LIKE-matched them against raw properties_json/info_json. Every trace carries the JSON key "ts", so unrelated recent memories outranked real hits. Short ASCII terms now only match id, key, value and tags; longer terms and CJK bigrams keep their metadata reach.
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
8 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.
Any query with a two-char token ("ts", "js", "id") matches almost every memory. FTS only indexes terms of 3+ chars, so short tokens go to the pattern channel, which LIKE-matches them against raw properties_json/info_json. Every trace row carries the JSON key "ts", so "fix ts build error" matched every trace, and the rank rewrite put the newest one at score 1.0, above the real hits.
Fix: short ASCII terms now only match id, memory_key, memory_value and tags. Longer terms and CJK bigrams can't collide with JSON keys and still match metadata values.
Verify:
cd Memory && npx vitest run tests/repository/memory-retrieval-index.test.ts. The test fails on v1.0.5 and passes with this change.