CodeNib v0.1.0

What's Changed

• add readme by @fishmingyu in #1
• [Debug] add module attributes and nested import by @fishmingyu in #2
• Add support for C++ by @fishmingyu in #3
• Syntax debug by @fishmingyu in #4
• [Debug] add support for nested function by @fishmingyu in #5
• Nested type inference by @fishmingyu in #6
• Update igraph as backbone by @fishmingyu in #7
• Codegraph update by @fishmingyu in #8
• Stz dev by @fishmingyu in #9
• search API update by @fishmingyu in #10
• [Update] refactor SimilarityAPI with start() and query() by @stzoozz in #11
• Update Roi Subgraph by @fishmingyu in #12
• add modular BaseAPI framework & SimilarityAPI by @stzoozz in #13
• [Update] add roi subgraph filtering by @fishmingyu in #14
• [Update] add Similarity API with model & device switching by @stzoozz in #15
• [Code Chunk] Support by @fishmingyu in #16
• Agent + tool by @fishmingyu in #17
• transgraph tool by @fishmingyu in #19
• [Agent] Initialize search code snippets by @stzoozz in #18
• [Update] Add BM25-transgraph compatibility by @stzoozz in #20
• Transgraph debug for nested function and hierarchy by @fishmingyu in #21
• Graph file dependency rebase by @fishmingyu in #22
• Agent part utils update by @fishmingyu in #23
• [Framework] refactor from llama-index to langchain by @fishmingyu in #25
• [Update] Add node_id for dense chunk to align with code graph by @stzoozz in #24
• [VecDB] refactor framework from llama_index to langchain by @fishmingyu in #26
• Split chunks with max_lines_per_chunk by @stzoozz in #27
• Agent VLLM support by @fishmingyu in #28
• Build bm25 index from chunk by @fishmingyu in #29
• [Chunk] Add class name in node_id for method by @stzoozz in #30
• Fishming.dev by @fishmingyu in #31
• [Env] add locbench, adjust swebench env path by @fishmingyu in #32
• Add Search + Rerank (S+R) baseline to examples by @stzoozz in #33
• [S+R] Support LocBench in test by @stzoozz in #34
• Exclude config for using scip python index by @fishmingyu in #35
• [SCIP] add third party and update readme by @fishmingyu in #36
• [Examples] Update S+R pipeline & Add Agentless pipeline by @stzoozz in #37
• [Commit] add test repo chunker by @fishmingyu in #38
• SWEBench verified update by @fishmingyu in #39
• [CI/CD] add PR template by @fishmingyu in #40
• Extract agent update and SCIP doc by @fishmingyu in #41
• [Core] update c++ version graph builder by @fishmingyu in #43
• profiler + graph index preprocess by @fishmingyu in #44
• Add Regex node indexing and enhance example outputs by @stzoozz in #42
• Swebench-verified location ground-truth generator with its test (for manually checking) by @siriuxyu in #45
• Ops and Plans initiative, rerank model revise by @fishmingyu in #46
• Rerank refactor and change llm config by @fishmingyu in #48
• Add build_embeddings script and fix with pre-commit by @stzoozz in #47
• [VectorDB] optimize index by @fishmingyu in #49
• Refactor langchain and retrieve ops by @fishmingyu in #50
• [swebench-verified] FIX - set work directory to ~/.codeminer/tmp/ by @siriuxyu in #51
• Update retrieve and rerank the model by @fishmingyu in #52
• Align the node metadata between eval and index by @stzoozz in #53
• [VectorDB] Support index metrics (l2, ip) in the FAISS vector store by @stzoozz in #54
• Align python and cpp scip_decoder with tests by @siriuxyu in #55
• [core] 2 Optimization Attempts by @siriuxyu in #56
• Align the chunker and eval for retrieval rerank pipeline by @stzoozz in #57
• Code Chunking update with new lang and structure by @fishmingyu in #58
• Refactor code chunking and improve retrieval evaluation by @stzoozz in #59
• Fishming.dev by @fishmingyu in #61
• Fishming.dev by @fishmingyu in #62
• Fix CI/CD and tests by @fishmingyu in #63
• fix bug for ci that affect original env and profile by @fishmingyu in #64
• [CI] fix bug that affect original home env by @fishmingyu in #65
• [CI] fix bug that affect original home env by @fishmingyu in #66
• Add skeleton mode; fix CI env by @fishmingyu in #67
• chore: add default flake8, git attributes, clang-format; align with p… by @fishmingyu in #69
• [VectorDB] Implement hierarchical vector store (l0 skeleton + l2) by @stzoozz in #68
• [Examples] Update retrieval rerank pipeline to support hierarchical vector store by @stzoozz in #70
• Added parallel cpp scip decoder & Clean gt-script's test by @siriuxyu in #60
• Fishming.dev by @fishmingyu in #71
• [Emmbedding] fixretrieve rerank pipeline with L0 by @fishmingyu in #72
• New JS/TS chunker, hybrid retrieval by @fishmingyu in #74
• [Rerank] Add embedding-based rerank and SWE-bench dev eval scripts by @fishmingyu in #75
• refactor dataset usage and logic by @fishmingyu in #76
• fix issues for dataset loading by @fishmingyu in #78
• Multilingual CodeGraph with SCIP by @siriuxyu in #77
• Introduce SWE-bench Multilingual support and a query synthesis pipeline for code search QA datasets, including utilities for sampling instances and generating multi-level natural language queries. by @fishmingyu in #79
• Fix shallow-clone checkout for SWE-bench + split collect/synthesize pipeline scripts by @fishmingyu in #80
• [CI/CD] Stabilize SCIP multilingual CI: centralize non-Python deps + migrate test to pytest by @fishmingyu in #81
• SCIP multi-lang robustness + deterministic/consensus SWE-bench synthesis by @fishmingyu in #82
• debug query synthesizer for swebench by @boqiny in #83
• [SCIP] Debug and refactor the SCIP indexing pipeline for multilingual codegraph by @siriuxyu in #84
• Improve retrieval/rerank profiler outputs and add tagged profiling to eval scripts by @fishmingyu in #85
• [Refactor] Unified LS-router for both SCIP and Clangd by @siriuxyu in #87
• Add Go chunker support and stabilize test fixtures by @fishmingyu in #88
• Add BM25, Embedding, and Graph Retrieval Pipelines with Baselines by @imaryandokania in #86
• Dataset pipeline: sampling, GT locator, and HF dataset builder by @fishmingyu in #89
• Add agent compiler infrastructure and migrate LLM layer to LiteLLM by @fishmingyu in #90
• Add agent runner, graph expand skill and ops by @fishmingyu in #93
• Add test for skill/embedding_search by @Turquoise-T in #91
• [Test] Add BM25 search skill tests and Vertex AI ADC credentials by @Yizhao111 in #92
• ci: parallelize CI into 3 jobs (~40min → ~18min) by @fishmingyu in #95
• [SCIP] add Go language support : Indexer/Decoder by @siriuxyu in #94
• Add Incremental Graph Update Module (incremental_graph) by @siriuxyu in #96
• [docs] update docs for scip-index, added docs for incremental-graph & GTLocator by @siriuxyu in #97
• CI, dataset fixes, and documentation updates by @fishmingyu in #98
• docs: add mkdocs-material for project wiki by @fishmingyu in #99
• [docs] intergrate interactivate demo of incremental graph by @siriuxyu in #102
• Improve behavioral query synthesis quality and correctness by @boqiny in #101
• [refactor] decompose query synthesizer & move incremental_graph to graph/incremental by @siriuxyu in #103
• Improve CI: DRY config, local caching, composite action, CLAUDE.md by @fishmingyu in #104
• Rewrite README with project overview by @fishmingyu in #106
• Add e2e SWE-bench evaluation with BM25 by @Yizhao111 in #105
• Add embedding_search evaluation on SWE-bench by @Turquoise-T in #108
• [dataset] add CodeMinerBaseDataset wrapper by @fishmingyu in #112
• Fix embedding language mapping and CUDA OOM for codeminer-base by @fishmingyu in #115
• [agent] Phase 1: token usage tracking + allow_skills filter (refs #109, closes #110) by @fishmingyu in #111
• feat: enhance core block picking algo in data synthesis pipeline by @boqiny in #116
• [embedding] Drop LangChain, add minified-file skip and Qwen3 support by @fishmingyu in #117
• feat(incremental): production-ready incremental embedding pipeline by @tfan10031 in #114
• chore: overhaul label taxonomy — prefix-based, orthogonal, YAML-managed by @fishmingyu in #124
• [core][SCIP] add multi-language C++ (parallel) decoder backend with pybind bindings by @siriuxyu in #120
• feat(embedding): prompt registry + cross-encoder rerank matrix by @fishmingyu in #128
• fix(test): make test_scip_swebench loud on run_pipeline failure by @fishmingyu in #132
• fix(bm25) + feat(compiler): unified_name indexing + skill-aware contexts (#109) by @fishmingyu in #137
• MCP: add BM25 + Regex search server by @Yizhao111 in #126
• MCP: add zoekt trigram (n-gram) search by @Yizhao111 in #136
• Add search_embedding MCP by @Turquoise-T in #123
• diag(eval): query-leak diagnostic tools + short-paraphrase generator (refs #130) by @fishmingyu in #138
• chore: relicense MIT → Apache 2.0 (refs #121) by @fishmingyu in #139
• fix(packaging): drop legacy License classifier superseded by SPDX expression by @tfan10031 in #140
• fix(rerank): graceful OOM recovery in QwenRerankerWrapper by @fishmingyu in #135
• [profiling] graph-RAG profiling harness scaffolding by @MihirJagtap in #134
• feat(graph): line-range query primitive + typed API + multi-edge anchor schema (closes #125) by @siriuxyu in #127
• chore(license): bulk-annotate sources with SPDX/REUSE headers (Apache-2.0) by @fishmingyu in #141
• ci(license): enforce REUSE/SPDX compliance via pre-commit hook + CI gate by @fishmingyu in #142
• chore(lint): clear pre-existing flake8 debt that was blocking pre-commit by @fishmingyu in #143
• docs: refresh for MCP server, agent skills, graph range query, and C++ backend by @fishmingyu in #159
• ci: stop integration-serial timeout + gate serial chain behind path filter by @fishmingyu in #158
• chore(agent): codify PR-template + no-attribution rules for code agents by @fishmingyu in #161
• fix(ci): stop self-hosted runner wedging on subprocess timeouts by @fishmingyu in #163
• fix(ci): lower scip-python timeout so it fires before the job cap; drop NOTICE by @fishmingyu in #164
• feat(web): DeepWiki-style code-QA demo over codeminer-base-dataset repos by @fishmingyu in #165
• feat(agent): graph-aware retrieval composer + rigorous graph-vs-retrieval ablation (#133) by @fishmingyu in #172
• feat(graph): dependency-analysis plugin + LocAgent harness result (graph belongs offline) (#133) by @fishmingyu in #173
• ci: iter-1 scope cancel-in-progress to PR refs by @fishmingyu in #174
• perf(graph): batch edge insertion in decoders (O(E^2) → O(E)) by @fishmingyu in #176
• ci: iter-2 add pytest-timeout guardrail to integration-serial by @fishmingyu in #175
• test(graph): skip [cpp] range-query test — no TU-bearing C++ fixture in Multilingual (#133) by @fishmingyu in #179
• feat(mcp): dependency_subgraph tool — call-graph nodes+edges JSON for impact analysis / DeepWiki view (#133) by @fishmingyu in #180
• test(agent-compile): everything-available arm — graph used 1/24 when grep present (#133) by @fishmingyu in #177
• feat(agent): GraphRAG retriever — graph +5@10, identifier seeding 2x@1 (#133) by @fishmingyu in #178
• feat(retrieval): pure-retrieval BM25+embedding baseline for RFC #133 … by @Turquoise-T in #171
• chore(repo): maintenance — root declutter, agent/tools/, IVF index, clients/ baselines, examples docs by @fishmingyu in #182
• feat: DeepWiki-style wiki + QA demo for indexed repos (#166) by @fishmingyu in #167
• chore(license): drop REUSE/SPDX enforcement, keep Apache-2.0 by @fishmingyu in #185
• feat(examples): complete graph-RAG profiling harness + codeminer_base wiring (#131, #119) by @fishmingyu in #183
• refactor(agent): split default tools into read/grep/glob/bash by @fishmingyu in #184
• feat(synthesize): vocabulary-overlap guard for synthesized queries by @fishmingyu in #189
• feat(dataset): freeze 30/70 codeminer-base partition + scenario labels by @fishmingyu in #190
• feat(eval): experiment runner — model dispatch + per-axis aggregation by @fishmingyu in #191
• perf(profiling): incremental-graph commit-chain benchmark by @fishmingyu in #193
• [ls_index][graph/incremental] use clangd $/progress for index-completion detection by @siriuxyu in #195
• feat(agent): centralize 0<->1 line numbering at the agent boundary by @fishmingyu in #188
• feat(agent): LLM retry policy + token-budgeted chat history by @fishmingyu in #192
• fix(compiler): resolve skill index_requirements from config.yaml on disk by @fishmingyu in #187
• refactor(agent): prune skills, split tools from skills, type boundaries by @fishmingyu in #196
• fix(test): drop test/scripts/init.py shadowing top-level scripts by @fishmingyu in #197
• refactor(agent-compile): consolidate scripts + Anthropic prompt caching (~74% sweep cost cut) by @fishmingyu in #200
• chore(claude): move CLAUDE.md into .claude/ and add layered rules by @fishmingyu in #201
• chore(agent-compile): drop fit/held-out partition subsystem by @fishmingyu in #202
• feat(web): interactive code graph (LSP click-to-source) + wiki-as-graph UI by @fishmingyu in #204
• fix(chunking): support tree-sitter-language-pack 1.8 by @Cyoyuu in #206
• feat(web): top-down dependency code graph + unified CodeGraph explorer by @fishmingyu in #205
• feat(dataset): add CodeMiner synthesis traversal pipeline by @fishmingyu in #209
• fix(dataset): avoid optional Claude SDK imports in unit tests by @fishmingyu in #210
• feat(web): clickable citation chips on ask page by @boqiny in #211
• feat(web): enhance codegraph rendering using Files + Symbols on fcose layout by @boqiny in #213
• feat(agent-compile): span-overlap localization eval + pre-load architecture + synthesis per-category sweep by @fishmingyu in #214
• docs: refresh README landing page and sync mkdocs to current code by @fishmingyu in #215
• fix(agent): make the forced localization schema turn optional by @boqiny in #216
• feat(web): multi-turn ask conversations by @boqiny in #217
• feat(web): improve code graph expand and node source peeks by @boqiny in #218
• [codex] Productize wiki system maps by @fishmingyu in #221
• feat(web): add local GPU LLM support and demo startup scripts by @YashJayswal24 in #220
• [codex] Add Codex agent guidance by @fishmingyu in #239
• [codex] Rehome incremental index package by @fishmingyu in #223
• [codex] Introduce language metadata registry by @fishmingyu in #224
• [codex] Derive repo chunking languages from registry by @fishmingyu in #225
• [codex] Document language contribution workflow by @fishmingyu in #226
• [codex] Add language scaffold script by @fishmingyu in #227
• [codex] Route graph patchers through language registry by @fishmingyu in #228
• [codex] Route LS delegates through language registry by @fishmingyu in #229
• [codex] Move LSP metadata into language registry by @fishmingyu in #230
• [codex] Route chunkers through language registry by @fishmingyu in #231
• [codex] Derive core decoder languages from registry by @fishmingyu in #232
• [codex] Add Java tree-sitter chunker by @fishmingyu in #233
• [codex] Add Ruby tree-sitter chunker by @fishmingyu in #234
• [codex] Add C# tree-sitter chunker by @fishmingyu in #235
• [codex] Add PHP tree-sitter chunker by @fishmingyu in #236
• [codex] Add Kotlin tree-sitter chunker by @fishmingyu in #237
• [codex] Track language capability matrix by @fishmingyu in #238
• feat(synthesis): v2 multi-repo benchmark — 25 repos, 500 queries, 99% valid by @fishmingyu in #219
• chore: fix local GPU demo defaults by @fishmingyu in #222
• feat(agent-runtime): runtime probe — ship embedding pre-load, cut graph+verify (experiment + findings) by @fishmingyu in #240
• [codex] Add generic Java LSP symbol graph backend by @fishmingyu in #241
• [codex] Add graph backend alignment harness by @fishmingyu in #242
• [codex] Decode generic LSP reference edges by @fishmingyu in #243
• [codex] Gate LSP core acceleration on decode profiling by @fishmingyu in #244
• [codex] finish multi-language LSP framework by @fishmingyu in #245
• [codex] promote graph-layer core API by @fishmingyu in #246
• [codex] track SCIP cold-start options by @fishmingyu in #247
• feat(scip): promote multilingual cold-start routes by @fishmingyu in #249
• refactor(core): centralize scip decoder registry by @fishmingyu in #253
• refactor(scip): share decoder normalization helpers by @fishmingyu in #254
• [codex] stabilize Python 3.12 CI dependencies by @fishmingyu in #255
• [codex] stabilize Ruby smoke tool wrappers by @fishmingyu in #256
• [codex] refresh SCIP roadmap issue triage by @fishmingyu in #257
• [codex] clarify historical Kotlin roadmap gate by @fishmingyu in #258
• docs(make): refresh scip cold-start env copy by @fishmingyu in #259
• feat(agent-compile): Qwen2.5-Coder local backend (7B/14B/32B) + eval by @fishmingyu in #248
• [codex] feat(retrieval): add query-aware planner by @fishmingyu in #265
• feat(agent-compile): compact pre-load + embedding/router ablations by @fishmingyu in #267
• fix(graph): match cold-start symbols by line attrs by @fishmingyu in #268
• ci: prewarm tree-sitter parsers before unit tests by @fishmingyu in #269
• [codex] Keep GPU dependencies out of unit tier by @fishmingyu in #274
• [codex] Agent runner architecture milestones by @fishmingyu in #272
• [codex] Graph-backed LSP route tools by @fishmingyu in #273
• [codex] Add runtime trace events by @fishmingyu in #275
• [codex] Add context ledger summaries by @fishmingyu in #277
• feat(agent): add harness spec by @fishmingyu in #278
• ci(actions): keep runner temp data off root disk by @fishmingyu in #280
• refactor(agent): move runner plumbing into packages by @fishmingyu in #279
• refactor(eval): move pareto diagnostics out of scripts by @fishmingyu in #281
• refactor(eval): move format diagnostics out of scripts by @fishmingyu in #282
• refactor(eval): share agent metric primitives by @fishmingyu in #283
• ci(actions): run slow tests after fast lanes by @fishmingyu in #284
• refactor(eval): move sweep harness into package by @fishmingyu in #285
• refactor(mcp): share LSP line boundary by @fishmingyu in #286
• feat(eval): plan small agent feedback slices by @fishmingyu in #287
• refactor(eval): share agent localization scoring by @fishmingyu in #288
• refactor(agent): make localization formatting opt-in by @fishmingyu in #289
• [codex] Reset runner architecture milestones by @fishmingyu in #290
• [codex] Add context ledger runtime contract by @fishmingyu in #291
• [codex] Summarize agent runtime traces by @fishmingyu in #292
• [codex] Add baseline task envelope by @fishmingyu in #293
• feat(eval): add graph lsp baseline adapter by @fishmingyu in #294
• feat(eval): add baseline batch runner by @fishmingyu in #295
• refactor(eval): run loc baselines through batch runner by @fishmingyu in #296
• chore(agent): deprecate agent compile shims by @fishmingyu in #297
• refactor(eval): move loc baseline runner into agent package by @fishmingyu in #298
• feat(eval): add agent promotion evidence gate by @fishmingyu in #299
• test(agent): guard deprecated compile shims by @fishmingyu in #300
• test(agent): guard lsp route skill contract by @fishmingyu in #301
• ci: gate slow tier behind explicit triggers by @fishmingyu in #302
• refactor(eval): move agent compile sweep logic into core by @fishmingyu in #303
• feat(agent): add opt-in lsp route context by @fishmingyu in #304
• [codex] Gate LSP route context seeds by @fishmingyu in #305
• [codex] Summarize agent feedback cells by @fishmingyu in #306
• feat(retrieval-ablation): graph as a RAG op — BFS scoped + graph-value by @fishmingyu in #270
• feat(rerank): wire cross-encoder rerank path end-to-end by @YashJayswal24 in #264
• [codex] Add static LSP provider validation by @fishmingyu in #307
• feat(web): LLM dependency labels on graph edges (hover tooltip, on-demand + cached) by @YashJayswal24 in #276
• feat(web): polish sidebar, graph interaction, and ask bar by @boqiny in #261
• ci: isolate gpu embedding tests by @fishmingyu in #262
• docs(readme): realign project entrypoints by @fishmingyu in #308
• docs(lsp): clarify provider acceleration gate by @fishmingyu in #310
• feat(lsp): add provider validation CLI by @fishmingyu in #311
• feat(lsp): add replay benchmark and artifact quality gates by @fishmingyu in #312
• feat(index): reuse snapshot-addressed artifacts by @fishmingyu in #313
• feat(agent): add snapshot semantic service by @fishmingyu in #314
• docs(retrieval): document query-aware planner and LSP skills by @fishmingyu in #316
• docs: fix dangling NOTICE link and add orphan pages to mkdocs nav by @fishmingyu in #315
• ci: add strict docs build workflow and retier astropy MCP tests by @fishmingyu in #317
• refactor(core): share SCIP decode helpers, add large-repo profiling gate by @fishmingyu in #318
• fix(eval): honor sweep runtime configuration by @fishmingyu in #324
• perf(agent): bound default grep with ripgrep by @fishmingyu in #326
• feat(eval): add content-locked artifact bundles by @fishmingyu in #319
• fix(compiler): enforce durable artifact contracts by @fishmingyu in #320
• fix(agent): align prompts and tool dispatch by @fishmingyu in #321
• feat(retrieval): add graph-aware fusion operators by @fishmingyu in #322
• fix(index): skip source-less regex content reads by @fishmingyu in #323
• perf(eval): stage only required sweep indexes by @fishmingyu in #325
• fix(scip): tolerate malformed Cargo workspace member globs by @boqiny in #328
• fix(web): repo card footer overflow on multi-language repos by @boqiny in #329
• feat(eval): record reproducible sweep protocols by @fishmingyu in #330
• feat(web): configure serving backends by @fishmingyu in #331
• feat: make incremental view maintenance reachable from the product by @YashJayswal24 in #332
• feat(web): surface incremental maintenance cost in the demo by @MihirJagtap in #333
• feat(landing): add codenib.ai landing page by @boqiny in #334
• ci: route workflow entry jobs to local runner by @fishmingyu in #336
• fix(ci): grant label sync checkout access [skip tests] by @fishmingyu in #337
• docs(brand): rename user-facing product to CodeNib by @fishmingyu in #338
• test(agent): stabilize ripgrep syntax coverage by @fishmingyu in #341
• feat(cli): add CodeNib command aliases by @fishmingyu in #339
• test(brand): lock CodeMiner compatibility contracts by @fishmingyu in #340
• refactor(namespace): migrate main to CodeNib by @fishmingyu in #343
• docs(readme): add centered brand header by @fishmingyu in #344
• feat(release): ship the CodeNib developer preview by @fishmingyu in #347
• docs(release): clarify trusted publisher setup by @fishmingyu in #348
• docs: sync all docs with post-rename main reality by @fishmingyu in #345
• docs: remove obsolete license transition note by @fishmingyu in #349
• fix(release): enable public Pages dispatch by @fishmingyu in #350
• docs(release): finalize v0.1.0 metadata by @fishmingyu in #351
• ci(release): split TestPyPI publishing by @fishmingyu in #352
• feat(product): ship repository Wiki developer preview by @fishmingyu in #355
• feat(agent): force a final answer for interactive Ask by @boqiny in #353
• feat(llm): configure LiteLLM backends explicitly by @fishmingyu in #356
• feat(wiki): generate coherent source-grounded pages by @fishmingyu in #357
• fix(agent): keep sparse Ask free of heavy runtimes by @fishmingyu in #360
• fix(product): close installed Wiki acceptance gaps by @fishmingyu in #364
• fix(graph): reject incomplete LSP symbol snapshots by @fishmingyu in #365
• feat(graph): diagnose repository toolchains by @fishmingyu in #361
• feat(wiki): synthesize grounded architecture narratives by @fishmingyu in #363
• feat(context): ship agent-native repository serving by @fishmingyu in #366
• docs(brand): align product and paper positioning by @fishmingyu in #367
• fix(mcp): migrate to SDK v2 by @fishmingyu in #368
• feat(web): link the demo header to docs.codenib.ai by @boqiny in #358
• docs(roadmap): record agent compile RFC closure by @fishmingyu in #369
• docs(readme): simplify the installation path by @fishmingyu in #370
• docs(readme): clarify the architecture section by @fishmingyu in #371
• docs(citation): cite the CodeNib arXiv paper by @fishmingyu in #372
• feat(landing): refine feature icons and site branding by @fishmingyu in #373
• fix(runtime): reconcile indexing and MCP contracts by @fishmingyu in #374
• feat(wiki): harden grounded pages and graph exploration by @fishmingyu in #377
• docs(site): refresh the public CodeNib documentation by @fishmingyu in #375
• fix(web): distinguish subsystem map hierarchy by @fishmingyu in #378
• feat(docs): align the incremental demo with the site theme by @fishmingyu in #376
• docs(readme): refresh the Wiki screenshot by @fishmingyu in #380
• fix(docs): disable remote font loading by @fishmingyu in #381
• feat(web): guide users to index their own repository by @fishmingyu in #382
• fix(release): validate annotated tags from origin by @fishmingyu in #383

New Contributors

• @stzoozz made their first contribution in #11
• @siriuxyu made their first contribution in #45
• @boqiny made their first contribution in #83
• @imaryandokania made their first contribution in #86
• @Turquoise-T made their first contribution in #91
• @Yizhao111 made their first contribution in #92
• @tfan10031 made their first contribution in #114
• @MihirJagtap made their first contribution in #134
• @Cyoyuu made their first contribution in #206
• @YashJayswal24 made their first contribution in #220

Full Changelog: https://github.com/sysevol-ai/CodeNib/commits/v0.1.0