Repository navigation
Description
Destination
Every candidate row in docs/upstream-issue-triage.yaml and docs/upstream-pr-triage.yaml, and each of fork issues #435–#447, has a tested verdict. It is either apply, backed by a reproduction that fails on penguin and passes with a prototype fix, plus the measurement its class needs, and handed to /ship as a ready-for-agent issue. Or it is reject, backed by evidence that it does not reproduce here or does not benefit the Operator, and recorded wont-fix in the YAML. No upstream patch is applied on trust: the fork has diverged too far.
Notes
- Domain: agentmemory-sqlite, the Operator's fork. Read root
CLAUDE.md(Goal, Evidence, Testing) andCONTEXT.mdfor vocabulary. - Execution override: a ticket may write a reproduction test and a prototype fix on a throwaway branch
verify/<slug>(pushed, never merged), and run evals. It never lands code onmain. Landing is/ship's job after the verdict. - The evidence bar every verdict must meet is the first decision on this map. Read it before working any verification ticket.
- An upstream PR diff is read for the diagnosis, never copied as the fix. Write the fix for this tree.
- A measurement that ends (kept, rejected or inconclusive) adds a row to
docs/experiments.mdwith its scorecard underdocs/benchmarks/, on the verify branch. - Each verdict updates its YAML rows (
status,disposition) and its fork issue (labelready-for-agent, or close as not reproducing), on the verify branch. - Skills to consult:
diagnosing-bugsfor reproductions;grilling+domain-modelingfor grilling tickets. - Working material from the triage:
tmp/upstream-review/(verdict notes, repro probeprobe/redact.ts, issue bodies).
Decisions so far
- What evidence clears an upstream candidate to apply?: failing repro on
penguinplus a prototype fix onverify/<slug>; correctness fixes need no regression on the gates, tuning changes need a measured gain, rejects need a passing probe or a code trace. - Verify: replace import empties the store before validating: apply. It reproduces, and validate-first plus dropping keyless rows holds on
verify/436-import-validate-first. Correctness only, so noeval:suite(no eval calls import). - Verify: auto-forget supersedes Memories across projects: apply. Cross-scope supersession, early image-ref release and the interval parse all reproduce; fixed on
verify/437-auto-forget-scope. Latent: nothing in the Operator's store is hit yet. - Verify: capture redaction corrupts data and misses JSON secrets: apply. Structured redaction, JSON-shaped secret keys and unclosed
<private>blocks fixed onverify/435-capture-redaction;eval:suiteunchanged. Surrogate truncation rejected (3 of 105,699 records, none from a hook cut). - Verify: lesson recall cuts candidates before the project filter: apply. Filtering before the cut fixed on
verify/438-lesson-recall-starvation;eval:suiteflat; on the Operator's Lessons the top pick is unchanged and recall lists gain better-scoring same-project Lessons. - Verify: observe dedup hashes only the first 500 chars: apply. Full-payload hash on
verify/439-dedup-full-hash; 224 of 16,796 of the Operator's prompts would have been dropped;eval:suiteflat. - Verify: Reflect Insight identity, source attribution and concept bloat: partial. Project-scoped Insight id and failure reporting apply on
verify/440-reflect-insight; cited-only sources and concept trimming not applied, sincemem:insightsis 2.3% of the store here. - Which upstream feature requests earn a test?: one of 52 does (synthetic-Observation age limit, now its own ticket); 50 rejected for empty record kinds, levers already rejected, wont-fix classes or no measurable cost.
- Verify: four write paths skip the search index: apply, latent. Consolidate, auto-page, heal and mesh now index or de-index on
verify/442-index-writes; none has written a Memory on the Operator's store. - Verify: age-out synthetic Observations (upstream #1566): not applied. A 60-day rule frees ~28 MB of a 598 MB store, and 1,111 of those Observations are still read as search hits; the 30-day replay corpus cannot reach the rule.
- Verify: export and snapshot drop data a restore needs: partial. Memory relations now go through export and snapshot, with content-keyed rows, on
verify/443-relations;eval:suiteflat; latent (0 relations stored). The consolidate crash, the import cap, audit export and image refs are rejected or not applied. - Verify: whole-scope reloads cost the Operator latency: partial. Session-cap eviction counts the Session's rows before listing them, on
verify/469-scope-reloads. Under the cap,observep50 drops from 255 to 24 ms and/livezmax from 328 to 51 ms (5 interleaved rounds). The count and list endpoints are rejected: none lists a whole scope on a hot path. - Should unscoped Memories pass a project filter?: apply. Exclude a non-Global Memory with no project from a project filter, no migration (Operator's call), on
verify/441-unscoped-memory; eval:suite flat. - Verify: project-scoped smart-search returns a short page: apply. A scoped page short of
limitfrom a full window re-searches at 4x, up to 1,600, onverify/444-scoped-short-page; eval:suite flat. - Verify: consolidation writes reworded near-duplicate facts: partial apply. An unkeyed reworded fact reinforces its same-project live twin (Jaccard >= 0.5) on
verify/445-reworded-dup-facts; 42% of live facts have such a twin; existing rows stay; eval:suite flat. - Verify: agent-sdk child sessions load host plugins: apply, latent. Child
query()setssettingSources: [],strictMcpConfig,persistSession: falseonverify/446-agent-sdk-isolation; the Operator's.envkeeps agent-sdk off. - Verify: MCP memory_save reports saved from the fallback: partial. The local fallback reply adds
localOnly: trueonverify/447-save-fallback-queue; queue-and-replay not applied, since the plugin'sAGENTMEMORY_URLalready makes a down daemon fail loudly. - Verify: MCP shim drops write args and dies silently: partial. Array
concepts/fileskept on the daemon REST MCP path (sharednormalizeList) and a clean exit on stdout EPIPE, onverify/463-mcp-shim; LessonsourceIdsand memory_savettlDaysnot applied (nothing reads them); crash-log PRs rejected, since Node already prints the stack to stderr. - Verify: facets outlive the records they tag: apply. Every Observation, Memory and Lesson delete path also deletes the facets tagging it (
deleteFacetsForTargets), onverify/465-facets; latent, since the live store has 0 facet rows. The heal sweep and remove-by-targetId are not applied. - Verify: Recall scoring defects: partial. Applied on
verify/467-recall-scoring: search results keep a saved Memory's own type, graph scoring keeps each Observation's best path, and mem::consolidate is locked, writes before it demotes, and counts failed calls. The prefix-bonus lever was measured and is inconclusive (pmb +0.021 with an interval touching 0, gate prompt-submit precision −0.033), so it was not applied. The procedural tier is left for an Operator decision. - Verify: config and doctor disagreements: apply most. A placeholder API key no longer picks a provider, doctor honours
OPENAI_API_KEY_FOR_LLM=falseand the agent SDK and stays quiet without a TTY, the fallback chain describes images, and amodel:variantname finds its embedding dimensions, onverify/468-config-doctor; all latent. The MAX_TOKENS default and the status label are rejected (the Operator sets MAX_TOKENS; status already reads the right field). - Verify: lock gaps in delete, relate and RMW paths: apply most. Every Memory delete path, relate and evolve now take the Memory write lock, so a delete or relate is no longer undone by a concurrent remember; a half-open circuit breaker lets one probe through, not every caller; on
verify/464-locks; latent. Session and graph RMW locks are rejected (already covered byobs:and the graph write lock). - Verify: hook capture loses or merges Observations: partial. import-jsonl no longer stamps a timestampless line with the import time, on
verify/466-hooks; latent. Hook early exit, repeated-prompt dedup and the durable hook spool are rejected: the request is sent before exit, the dedup is deliberate, and the storeless Sessions trace to hosts that never loaded the plugin or to audited eviction, not to lost Observations. - Verify: Session Summaries store stray XML tags: apply. A child item closed with the wrong tag no longer fuses with the next item or keeps the stray tag, on
verify/472-xml-children; re-parsing the live store's leaked items clears 59 of 59 Summaries and 784 of 792 Observations. Stored records are not repaired; that would be a separate migration.
Not yet specified
- Nothing. Every question is decided or handed off (see Handoff).
Handoff
Every fix is verified and uncommitted on its verify/<slug> branch. Each is a ready-for-agent issue for /ship, one PR per issue:
#435, #436, #437, #438, #439, #440, #441, #442, #443, #444, #445, #446, #447, #472, #473 (MCP shim), #474 (locks), #475 (facets), #476 (import-jsonl), #477 (Recall scoring), #478 (config and doctor), #479 (session-cap eviction).
- No broker A/B arm before shipping. Every class-2 fix ran eval:suite fast against base-fdc3d459 with no metric moved, and most are latent on the Operator's store. Run
eval:arm/eval:compareonly for a fix whose suite numbers move once it is rebased. - One PR per issue. Overlaps to rebase in order: Auto-forget's contradiction pass supersedes Memories across projects #437 and Memory deletes, relate and evolve race remember, and a half-open breaker admits every caller #474 both touch
auto-forget.tsandretention.ts; Consolidate, auto-page, heal and mesh sync write Memories without updating the search index #442 and Search drops a saved Memory's type, graph scoring keeps a worse path, and mem::consolidate runs unlocked #477 both touchconsolidate.ts. - Triage YAML:
statusandfixed_bynaming the issue are enough; no evidence field. - Operator decision open: Procedural memory tier never writes a procedure.
Out of scope
- Landing fixes on
main: that is/ship's job, starting from eachready-for-agentissue this map produces. - Reporting findings back upstream.
Activity