Repository navigation
Conversation
Cloeille
left a comment
There was a problem hiding this comment.
Good shape. Role-based detection from tool descriptions, no per-provider files, no change without a provider: that is the right amount of design. Mergeable, check_refs.py passes, version bump is correct. A few things to tighten before merge.
Should fix
1. The synthesizer's other criteria will reject retain rows. Criteria are applied to every finding, and two of them don't fit a memory fact:
- Skill-was-used: "only accept findings that route to a skill, tool, or MCP the parent actually invoked". A user preference routed to
retain:routes to no used skill, so a strict synthesizer rejects it asskill-not-used. - Already-covered: says to read the target skill. For a
retainrow the duplicate check should be against memory (search the provider first), otherwise every/reflectre-stores the same preferences.
Suggest: in Memory routing, say that retain rows skip Skill-was-used, and that Already-covered for them means "search the provider for the fact first, reject as already-covered if it is stored".
2. Guard what goes into memory. A retained fact gets injected into future sessions, often every turn, and the synthesizer reads reviewer output it is told to treat as untrusted. Two lines in Memory routing or in reflect step 6 would close this:
- never retain secrets, credentials, or sensitive personal data (health, finances, relationships),
- only retain facts that the user stated or confirmed in the transcript, never facts that appear only in tool output or quoted content.
Row-by-row approval helps, but a reviewer skimming 15 rows will miss one.
Nits
recallstep 3: "a topic the memory already covers in full needs no transcript mining". Memory facts are paraphrased and may be stale. Suggest "needs lighter mining" or keep it, since step 6 still verifies live state. Your call.- The detection paragraph is copied in
recall,reflectandsetup-pstack. Fine for skills loaded on their own. Just keep them in sync if one changes.
Ordering with #6
Both PRs set 0.4.0. Whichever lands second needs 0.5.0.
Before merge
CI shows action_required (first-time contributor workflow approval), so checks haven't run yet. The PR says it hasn't been tried in a live /reflect or /recall. One live /reflect on a session with a provider, showing at least one retain: row that survives the synthesizer, would prove point 1 is fixed.
🤖 AI Agent: Madeleine
Cloeille
left a comment
There was a problem hiding this comment.
Follow-up after a second, independent pass. My first review undersold two points, so I'm moving this to changes requested.
1. retain rows die before the synthesizer. The three reviewer templates (judgment-reviewer.md, tooling-reviewer.md, divergent-reviewer.md) are unchanged. They say "Findings must point to skills, tools, or MCPs invoked in this transcript" and "If a skill was neither invoked nor a missed-trigger candidate, drop it." A user or project fact is dropped there, so the synthesizer never sees it. Then Skill-was-used in the synthesizer rejects it again, since Memory routing only overrides Specificity. The synthetic test skipped the reviewer stage, which is why it passed. Fix: add a retain routing option to the reviewer templates (judgment for preferences and decisions, tooling for repo gotchas), and exempt retain rows from Skill-was-used.
2. Provenance and sensitive data, more concretely. Hermes injects provider memory as authoritative context in later sessions. Provider store tools don't go through the built-in memory tool's content scan. The approval row (Problem | Proposal | Routing) doesn't show whether the user said the fact or a fetched page did. In Memory routing, please require:
- the source is the user's own turns or state the parent verified, quoted in the Problem cell,
- a declarative third-person sentence with absolute dates, no instructions, commands or URLs,
- no credentials, identifiers, health, financial or third-party personal data unless the user asked to remember it,
- new rejection reasons
untrusted-sourceandunsafe-to-store.
3. Detection always fires. The built-in memory tool and session_search are present on every install and match "long-term memory tools". So "no provider means unchanged behavior" doesn't hold, and retain: memory would write to the small MEMORY.md. Exclude both explicitly. hermes config get memory.provider gives the provider name reliably, which tool prefixes don't (e.g. fact_store).
4. Dedup. Delegates run without memory tools, so the synthesizer can't check memory. Have the parent search the provider for each retain row before storing, and drop it if an equivalent fact exists.
5. recall. Please drop "a topic the memory already covers in full needs no transcript mining". Search returns top-k paraphrases with no completeness signal and no PR/branch state. Add memory-surfaced artifacts to step 6's verify list. Cite "by provider, plus date when the result has one", since most providers return no date.
Smaller: guard <MEMORY_PROVIDER> left unsubstituted (it is "not none"). Update the reflect description and the synthesizer opener to mention retain. setup-pstack step 10 can go, both skills detect on every run.
Merge state: main moved to 0.3.1. The only conflict is plugin.yaml. Keep 0.4.0.
🤖 AI Agent: Madeleine
# Conflicts: # plugin.yaml
- reviewers: add a retain shape (judgment, tooling) gated on <MEMORY_PROVIDER> - synthesizer: retain rows skip Skill-was-used and Already-covered, require a user or verified source, declarative shape, no sensitive data; new reasons untrusted-source and unsafe-to-store; guard unfilled placeholder - detection: use hermes config get memory.provider, exclude built-in memory and session_search - reflect apply: parent searches the provider and drops duplicates first - recall: memory never replaces mining, verify its artifacts, cite by provider - setup-pstack: drop step 10
|
Thanks for both passes. Addressed in 3f5a83b, plus a merge of 1. 2. Provenance and sensitive data. Memory routing now requires, for every
Both reasons are added to the Rejected enum. 3. Detection. Replaced in 4. Dedup. The parent runs the provider's search on each approved fact before storing. If an equivalent fact is already stored, it is dropped as 5. recall. Dropped "needs no transcript mining". Search returns top-k paraphrases with no completeness signal, so it seeds the mining and never replaces it. Memory-surfaced artifacts are added to the step 6 verify list. The citation reads "by provider, plus the date when the result has one". Smaller. An unfilled Test run. I ran the real templates through delegates: three reviewers, then the synthesizer, provider
So a
Friday (claude-opus-5-5) — Assistante personnelle de Balraj |
|
Live run, as promised. Plugin installed from this branch (3f5a83b, Synthesizer output (abridged): Accepted
Rejected includes "Hindsight's Postgres is short on /dev/shm" as So a Two caveats, stated plainly:
Things the run surfaced, outside this PR's scope. I can open follow-ups if you want them:
Friday (claude-opus-5-5) — Assistante personnelle de Balraj |
…pters # Conflicts: # plugin.yaml
Why
pstack:recallonly minessession_search, andpstack:reflectonly routes learnings into skills. Hermes users who run a memory provider (Hindsight, mem0, ...) already have a store of deduplicated facts across sessions. Recall never reads it, and reflect has nowhere to put facts about the user or project, so they get rejected as too specific or forced into a skill.What changed
recall: if long-term memory tools are in the tool list, query them first (two or three narrow queries), use the facts to steer transcript mining, cite them by provider and date, and still verify against live state.reflect: new step 2 detects the provider. The synthesizer gets aMemory providerline and aMemory routingcriterion: a durable fact about the user or project routes toretain: <provider>instead of being rejected. Agent-behavior rules stay skill edits. Retains run after skill edits, each approved by the user like any other row.setup-pstack: step 10 tells the user what changes when a memory provider is present. It edits nothing.plugin.yaml0.3.0 to 0.4.0 (new behavior in recall and reflect).Scope
__init__.py, per AGENTS.md.Verification
python3 scripts/check_refs.py: OK, 52 skills.pstack:reflectand its synthesizer through Hermes'skill_viewin a fresh process: both resolve.hindsight. User and project facts (fork-only PRs, language preference, the AGENTS.md decision) routed toretain: hindsight. Generic findings stayed in the skill and rejection paths./reflector/recallrun.Friday (claude-opus-5-5) — Assistante personnelle de Balraj