Repository navigation
feat(adr-001): verifySparseSolution MCP tool — wire-callable witness - #52
Merged
Merged
Conversation
PR #41 shipped the Rust witness (verify_sparse_solution); PR #42 added it to the estimateComplexityClass advertisement table. But there was no actual wire-callable MCP tool — clients (RuView / Cognitum agents) couldn't audit their SubLinear orchestrator outputs over the wire. This closes that gap with a pure-TypeScript handler. The residual math is straightforward enough that duplicating it in JS is cheaper than plumbing a new WASM binding. Matches Rust's verify_sparse_solution semantics exactly: r[i] = b[i] - Σ_j A[i,j] · x_new[j] for each (row, value) entry x_new[j] = overlay[j] if entries contains j, else prev_solution[j] threshold = tolerance · max(1, ‖b‖_∞) ok ⟺ max_i |r_i| ≤ threshold Lands in src/mcp/server.ts: - New `verifySparseSolution` tool with x-complexity = SubLinear - Input schema: matrix, prev_solution, vector (b), entries: Array<{row, value}>, tolerance - Dispatch case + handleVerifySparseSolution method - Returns {ok, max_residual, threshold, worst_row, note} - Supports both dense and sparse-COO matrix formats Wire contract matches the Rust function: - Out-of-bound entries silently dropped (no panic) - Malformed entries (non-numeric row/value) tolerated - Failure on strict-DD input indicates real solver bug Cost: O(|entries| · avg_row_nnz). Independent of n for sparse DD matrices — same complexity class as the orchestrator whose output it verifies. Co-Authored-By: claude-flow <ruv@ruv.net>
This was referenced May 19, 2026
ruvnet
added a commit
that referenced
this pull request
May 19, 2026
…trator The SubLinear orchestrator shipped in Rust (PR #29) had MCP preview primitives (coherenceScore, closureIndices, estimateComplexityClass) and a wire-callable witness (PR #52). But the orchestrator itself wasn't wire-callable — agents had to fall back to `solve` (which returns the full n-vector) instead of the closure-restricted entries the SubLinear path produces. This closes the gap with a pure-TS handler that chains: 1. closure_indices(matrix, delta.indices, closure_depth) 2. for each closure entry: truncated Neumann iteration restricted to the closure (mirrors src/entry.rs math) 3. return Vec<{row, value}> Lands in src/mcp/server.ts: - New `solveOnChangeSublinear` tool with x-complexity = SubLinear - Input schema: matrix, vector (b_new), delta_indices: number[], closure_depth (default 4), max_terms (default 32), tolerance (default 1e-8) - Dispatch case + handleSolveOnChangeSublinear method - Returns {entries: Array<{row, value}>, closure_size, max_terms, closure_depth, note} - Supports both dense and sparse-COO matrix formats Matches Rust solve_on_change_sublinear semantics exactly: - Early-exit when |delta_k[target]| < tolerance - Zero-diagonal in closure → InvalidParams - Empty closure → empty entries - note field warns when closure covers full matrix This completes the wire surface for the change-driven inner loop. Agents can now run the full pipeline over MCP: 1. coherenceScore (PR #53) — is the matrix solvable? 2. closureIndices (PR #54) — how wide is the work? 3. estimateComplexityClass (PRs #30, #42) — what class? 4. solveOnChangeSublinear (THIS PR) — actual SubLinear solve 5. verifySparseSolution (PR #52) — audit output All 5 tools are pure-TS. No Rust/WASM bridge required for any of them. Co-Authored-By: claude-flow <ruv@ruv.net>
This was referenced May 19, 2026
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
PR #41 shipped the Rust witness (`verify_sparse_solution`); PR #42 added it to the `estimateComplexityClass` advertisement table. But there was no actual wire-callable MCP tool — clients couldn't audit their SubLinear orchestrator outputs over the wire.
This closes that gap with a pure-TypeScript handler. The residual math is straightforward enough that duplicating it in JS is cheaper than plumbing a new WASM binding. Matches Rust's `verify_sparse_solution` semantics exactly.
Math
```
r[i] = b[i] - Σ_j A[i,j] · x_new[j] for each (row, value) entry
x_new[j] = overlay[j] if entries contains j, else prev_solution[j]
threshold = tolerance · max(1, ‖b‖_∞)
ok ⟺ max_i |r_i| ≤ threshold
```
API
```json
{
"name": "verifySparseSolution",
"x-complexity": { "class": "SubLinear", "edgeSafe": true },
"inputSchema": {
"matrix": "...",
"prev_solution": "number[n]",
"vector": "number[n] (RHS b)",
"entries": "Array<{row: number, value: number}>",
"tolerance": "number, default 1e-6"
}
}
```
Returns: `{ok, max_residual, threshold, worst_row, note}`.
Wire contract
Test plan
🤖 Generated with claude-flow