|
2 | 2 |
|
3 | 3 | ## Unreleased |
4 | 4 |
|
| 5 | +## [2.1.0](https://github.com/PatrickSys/codebase-context/compare/v1.9.0...v2.1.0) (2026-04-13) |
| 6 | + |
5 | 7 | ### Features |
6 | 8 |
|
| 9 | +- **search:** surface chunk intelligence directly in `search_codebase` results, including symbol identity, scope, signature preview, and compact/full response budgeting |
| 10 | +- **map:** upgrade the conventions map with structural skeleton sections and add `map --export` so the compact map can be written to `CODEBASE_MAP.md` |
7 | 11 | - **mcp:** rework multi-project routing so one MCP server can serve multiple projects instead of one hardcoded server entry per repo |
8 | 12 | - **mcp:** keep explicit `project` as the fallback when the client does not provide enough project context |
9 | 13 | - **mcp:** accept repo paths, subproject paths, and file paths as `project` selectors when routing is ambiguous |
10 | 14 |
|
11 | 15 | ### Bug Fixes |
12 | 16 |
|
| 17 | +- **metadata:** require real dependency evidence plus multiple framework indicators before labeling a repo as Next.js or another specialized framework |
| 18 | +- **reranker:** auto-heal corrupted cross-encoder cache entries and surface degraded reranker state in `searchQuality.rerankerStatus` |
| 19 | +- **benchmarks:** harden comparator lanes for cross-platform execution and keep setup failures explicit instead of silently turning them into claims |
13 | 20 | - **search:** auto-heal on corrupted index now triggers a background rebuild instead of blocking the search response |
14 | 21 |
|
15 | 22 | ### Documentation |
16 | 23 |
|
| 24 | +- publish the v2.1.0 discovery benchmark rerun with the current gate output: `pending_evidence`, `claimAllowed: false`, `24` frozen tasks, `0.75` average usefulness, and `1822.25` average estimated tokens |
| 25 | +- document the current comparator truth instead of stale assumptions: the public proof still has setup failures plus near-empty comparator outputs on this host, so benchmark win claims remain blocked |
| 26 | +- note the new `searchQuality.tokenEstimate` advisory contract: estimates are based on the final serialized response payload and warnings only appear above the 4K-token threshold |
17 | 27 | - simplify the setup story around a roots-first contract: roots-capable multi-project sessions, single-project fallback, and explicit `project` retries |
18 | 28 | - clarify that issue #63 fixed the architecture and workspace-aware workflow, but issue #2 is still only partially solved when the client does not provide roots or active-project context |
19 | 29 | - remove the repo-local `init` / marker-file story from the public setup guidance |
|
0 commit comments