Commit graph

10 commits

Author SHA1 Message Date
Kjell Tore Guttormsen
b95b075dd0 feat(config-audit): MCP tool-count detection with manifest fallback (v5 M1) [skip-docs]
readActiveMcpServers now resolves tool count via:
  1. In-config tools array
  2. Cached tools/list at \$HOME/.claude/config-audit/mcp-cache/<name>.json
  3. node_modules/<pkg>/package.json (resolved from npx <pkg>)
  4. Fallback: { toolCount: null, toolCountUnknown: true }

estimateTokens uses detected toolCount (heavy server > light server).

New fixture: mcp-tool-heavy/ with mocked node_modules/mcp-heavy/package.json (20 tools).

576 → 580 tests, all green.
2026-05-01 07:02:08 +02:00
Kjell Tore Guttormsen
3dfa32609c feat(config-audit): TOK flags skill description > 500 chars (v5 M2) [skip-docs]
- New Pattern F in TOK: low-severity finding when SKILL.md description > 500 chars
- Scoped to discovery.files (project-local) — activeConfig.skills walk would
  pull in user/plugin skills out of project scope
- New fixtures: skill-bloated (594-char desc) + skill-tight (46-char baseline)

574 → 576 tests, all green.
2026-05-01 06:58:42 +02:00
Kjell Tore Guttormsen
65297faeb1 feat(config-audit): TOK flags CLAUDE.md cascade > 10k tokens (v5 M4) [skip-docs]
- New Pattern E in TOK: emits medium finding when activeConfig.claudeMd.estimatedTokens > 10_000
- Uses cascade tokens, file count, and calibration note as evidence
- New fixtures: large-cascade (37k bytes / 14475 cascade tokens) + small-cascade (5k baseline)

572 → 574 tests, all green.
2026-05-01 06:53:12 +02:00
Kjell Tore Guttormsen
24856baf6b feat(config-audit): flag additionalDirectories > 2 (v5 M6) [skip-docs]
- Add 'additionalDirectories' to KNOWN_KEYS
- Emit low severity finding when length > 2
- New fixtures: additional-dirs-many (3 entries) + additional-dirs-ok (2)

569 → 572 tests, all green.
2026-05-01 06:50:24 +02:00
Kjell Tore Guttormsen
b1fc9996b9 feat(config-audit): TOK consumes readActiveConfig (v5 F1)
Removes the v4 'void readActiveConfig' placeholder and wires the
active-config snapshot into the TOK scanner.

Per-turn behavior changes:
- Each enabled MCP server becomes its own hotspot entry (richer than
  the parent .mcp.json file alone)
- total_estimated_tokens now includes MCP server cost
- result.activeConfig exposes a small summary
  (claudeMdEstimatedTokens, mcpServerCount, pluginCount, skillCount)

Failures of readActiveConfig are non-fatal — the scanner falls back
to the discovery-only path used in v4.

Tests: +3 cases on the new tok-active-config fixture
(.mcp.json with 2 servers, CLAUDE.md, plugin skeleton).
2026-05-01 06:27:34 +02:00
Kjell Tore Guttormsen
0c2aa0f0c2 test(config-audit): add marketplace-small/medium/large scanner fixtures 2026-04-19 22:36:33 +02:00
Kjell Tore Guttormsen
2a8dc8655f test(config-audit): add Opus 4.7 pattern fixtures (cache, redundant, imports, sonnet-era) 2026-04-19 22:34:41 +02:00
Kjell Tore Guttormsen
87b5078c91 test(config-audit): add baseline-all-a fixture + grade-stability regression test 2026-04-19 22:32:40 +02:00
Kjell Tore Guttormsen
d120fae509 fix(config-audit): complete conflict-project fixture for CNF cross-scope tests 2026-04-19 22:29:46 +02:00
Kjell Tore Guttormsen
caee558e79 feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.

New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.

Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.

Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-08 08:58:35 +02:00