GitNexus/gitnexus/skills
enih 1e5a1ad01e
fix(wiki): configure limits and retry truncated pages (#3775)
* feat(wiki): let callers set the completion token limit

Reasoning models can spend the hardcoded 16384 cap before a page is finished. Keep that default, and honor a flag, GITNEXUS_MAX_COMPLETION_TOKENS, or maxCompletionTokens in the CLI config.

Fixes #3774

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(wiki): reject LLM responses cut off at the completion token limit

callLLM accepted a response whose finish_reason was "length" as a
finished one, streamed or not, so a page cut off mid-sentence or
mid-table was written and the run reported success. With a reasoning
model the limit can be spent before the answer starts.

Both paths now throw when the provider reports finish_reason "length",
naming the limit. The generator already treats a thrown error as a
failed module: the page is not written, the module is listed under
"Failed modules", and the next run regenerates it.

---------

Co-authored-by: nullptr <null@null.ptr>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Samuel Mbabhazi <samuelmbabhazi@gmail.com>
Co-authored-by: Gergo Magyar <gergomagyar0@gmail.com>
Co-authored-by: Gergő Magyar <gergomagyar@icloud.com>
2026-10-31 13:24:37 +00:00
..
gitnexus-lfg feat(skills): GitNexus Engineering Tool Kits (#2566) 2026-07-19 15:07:24 +01:00
gitnexus-plan fix(skills): publish gitnexus-plan artifacts on macOS without an interpreter (#2905) (#2922) 2026-08-11 12:24:53 +01:00
gitnexus-review feat(cache): derive parser and PDG cache identities automatically (#3606) 2026-10-17 07:38:45 +03:00
gitnexus-work fix(mcp): stop scaling the detect_changes query with the diff's hunk count (#2915) (#2930) 2026-08-12 14:51:17 +01:00
gitnexus-cli.md fix(wiki): configure limits and retry truncated pages (#3775) 2026-10-31 13:24:37 +00:00
gitnexus-debugging.md feat(mcp): reduce response size and query overhead (#3621) 2026-10-18 17:32:09 +01:00
gitnexus-exploring.md feat(mcp): reduce response size and query overhead (#3621) 2026-10-18 17:32:09 +01:00
gitnexus-guide.md feat(mcp): reduce response size and query overhead (#3621) 2026-10-18 17:32:09 +01:00
gitnexus-impact-analysis.md fix(mcp): name the indexed ref on hot read tool staleness (#3291) (#3293) 2026-09-16 07:29:04 +00:00
gitnexus-pdg-query.md docs: fix bundled skill reference drift (#2362) 2026-07-03 09:50:56 +01:00
gitnexus-refactoring.md fix(rename): apply the exact reviewed edit plan (#3617) 2026-10-17 19:38:01 +01:00
gitnexus-taint-analysis.md feat(cache): derive parser and PDG cache identities automatically (#3606) 2026-10-17 07:38:45 +03:00