Auto-discover Morpho Blue positions via event-log scan - #12
Merged
Conversation
Morpho Blue has no on-chain enumeration of a user's markets, so get_morpho_positions and get_portfolio_summary previously skipped Morpho unless the caller supplied marketIds — meaning any agent asking "what are my DeFi positions?" silently missed Morpho exposure. Adds discoverMorphoMarketIds: paginated eth_getLogs scan of Supply, Borrow, and SupplyCollateral events filtered by the indexed onBehalf topic, from the chain's deploy block to head in 10k-block chunks (override via MORPHO_DISCOVERY_CHUNK for premium RPC endpoints). - get_morpho_positions: marketIds is now optional; falls back to discovery. Explicit marketIds remain a fast path. - Portfolio aggregator: fans out Morpho per-chain, merges positions into the lending bucket, and contributes to lendingNetUsd / perChain / totalUsd. Coverage flips from hardcoded covered:false to live errored/covered status. - MorphoLendingPosition added to LendingPositionUnion. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This was referenced Apr 27, 2026
szhygulin
added a commit
that referenced
this pull request
Apr 27, 2026
Two updates to SECURITY.md tied to recent integrity-check work: 1. Preflight-skill row's "Honest limits" column now narrates the silent-skip-on-mismatch failure mode that was open prior to skill v0.4.1: the skill's prose instructed comparison but didn't mandate it, the agent could skip silently, and we observed exactly that in production during the v4-typo pin bump. skill PR #12 (closes skill #10) added Step 0 — mandatory integrity self-check — that halts the flow on divergence with explicit alarm prose. 2. Updated the parallel paragraph (~line 107) that mentioned `PreToolUse` hook as the only roadmap option: now also references vaultpilot-mcp #379 (server-side enforcement) as the equally-valid parallel path, plus calls out skill v0.4.1's Step 0 as the agent-side fix that's already shipped. Cross-references the now-merged skill PR #12, the closed skill #10, and the open vaultpilot-mcp #379 server-side companion. Pure docs.
This was referenced Apr 27, 2026
Closed
szhygulin
added a commit
that referenced
this pull request
Apr 28, 2026
…501) Inv #12.5 (skill-side, issue #501) marks a curated list of op classes where the second-LLM check is a precondition of `confirmed: true`, not opt-in. The skill-side rule lives in vaultpilot-skill v9+; this PR is the MCP-side scaffold so future hard-trigger op producers can flip a flag at build time and have the existing verification block surface a mandatory ⚠ line. What ships: - New `secondLlmRequired?: boolean` on `UnsignedTx`. Default absent / false. Documentation comment lists today's hard-trigger op classes (all currently deferred or not built): - EIP-7702 setCode (#481) - Permit2 batch grants (#453) - Opaque-facet bridges (#451) - Approval-management N-candidate selection (Inv #13) - Safe enableModule / setGuard / threshold changes - `renderVerificationBlock` reads the flag and emits a single ⚠ line below the hash: ⚠ SECOND-LLM CHECK REQUIRED — call get_verification_artifact(handle) and relay the pasteableBlock to the user BEFORE 'send' (Inv #12.5 hard-trigger op). - 3 tests pinning the behavior: omitted when absent/false, emitted when true, composes cleanly with recipient + tokenClass warnings. What does NOT ship: - No producer wires the flag yet (every hard-trigger op class is itself deferred). The flag is dormant scaffold. - No enforcement layer below the rendered ⚠. The MCP can't tell whether the agent actually ran the second-LLM check — same self- attestation gap as `userDecision: "send"`. Trust note (in the field doc): The flag is a workflow signal, not a cryptographic primitive. Closing the agent-side honesty gap requires infrastructure that doesn't exist today (provider-signed LLM responses, TEE attestation, or zkML proofs of NN inference). Discussed in the PR thread for this issue. Coordinated with skill v9 release (lifts §16 unconditional 7702 refusal + adds Inv #12.5 hard-trigger language); MCP-side `EXPECTED_SKILL_SHA256` bump happens in the skill-coordination PR, not this one. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This was referenced Apr 28, 2026
This was referenced Aug 6, 2026
szhygulin
added a commit
that referenced
this pull request
Aug 6, 2026
Deletes the Inv #12.5 hard-trigger flag `secondLlmRequired` on `UnsignedTx` and the `⚠ SECOND-LLM CHECK REQUIRED` line the verification renderer emitted for it. No op class makes the check a precondition of 'send'; docs restate Inv #12.5 as a recommendation. The check needs the user to physically paste into a second provider's session, so a rule that blocks 'send' until it happens blocks the user, not an attacker — a rogue agent self-attests the verdict either way (the `userDecision: "send"` self-attestation gap). The flag also never had a producer: no `prepare_*` path set it, so nothing on this server changes behavior. The load-bearing gate lives in the skill, filed at szhygulin/vaultpilot-security-skill#51. Co-authored-by: Claude Opus 5 (1M context) <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
1 participant
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
get_morpho_positionsandget_portfolio_summarypreviously skipped Morpho unless the caller suppliedmarketIds— meaning any agent asking "what are my DeFi positions?" silently missed Morpho exposure.discoverMorphoMarketIds: paginatedeth_getLogsscan ofSupply/Borrow/SupplyCollateralevents filtered by the indexedonBehalftopic, from the chain's deploy block to head in 10k-block chunks (override viaMORPHO_DISCOVERY_CHUNKfor premium RPCs).get_morpho_positions:marketIdsis now optional; falls back to discovery. ExplicitmarketIdsremain a fast path.lendingNetUsd/perChain/totalUsd. Coverage flips from hardcodedcovered: falseto live errored/covered status.MorphoLendingPositionadded toLendingPositionUnion.Tradeoffs
get_portfolio_summarycalls get slower: ~40 sequential 10k-block chunks × 3 parallel event calls on Ethereum mainnet. Each chunk is capped so it works on Alchemy/Infura free tier. A TTL cache is the natural next step if this becomes painful in practice.Test plan
npm run build— cleannpm test— 209 tests pass (no new tests added; discovery relies on live RPC and isn't covered by the existing unit-test fixtures)get_morpho_positionswith a wallet known to have Morpho exposure and nomarketIds— confirm positions are returnedget_portfolio_summaryfor the same wallet — confirm Morpho appears inbreakdown.lendingand contributes tototalUsdcoverage.morpho = { covered: true }🤖 Generated with Claude Code