All pull requests

Pull requests

• docs: add a review guide and a pre-PR self-review checklist

  #206·vchamarthi opened Oct 23, 2026Contributor·5 of 6 tasks·

  ·
  3

• feat(repo): stamp and schema-check repo budget JSON as repo_budget.v1

  #205·antonwolfy opened Oct 23, 2026Contributor·5 tasks done·

  ·
  10

• test(records): hold readers of with_docs/without_docs to dokimi.records

  #203·antonwolfy opened Oct 23, 2026Contributor·5 tasks done·

  ·
  18

• docs(architecture): module map and API landing page follow the import layers

  #201·antonwolfy opened Oct 23, 2026Contributor·5 tasks done·

  ·
  6

• docs(repo): the patch arm's name rule, the tasks check flag and host record, both new arms in the README

  #199·antonwolfy opened Oct 23, 2026Contributor·5 tasks done·

  ·
  3

• fix(novelty): the report does not show a 0 the gate leaves unchecked as a clean 0

  #197·antonwolfy opened Oct 23, 2026Contributor·5 tasks done·

  ·
  18

• refactor(compare): split per-arm checks out of _provenance_warnings

  skip-changelog
  #195·napetrov opened Oct 23, 2026Contributor·

  ·
  4

• ci(mutation): mutmut pilot over the stats, gates and cache key

  #178·napetrov opened Oct 22, 2026Contributor·5 tasks done·

  ·
  34

• feat(repo): show result.json process counts in repo report and repo compare

  #177·napetrov opened Oct 22, 2026Contributor·

  ·
  13

• fix(gates): nothing measured is not a pass

  #176·napetrov opened Oct 22, 2026Contributor·5 tasks done·

  ·
  15

• feat(novelty): --repeats for routing noise floor; keep declined replies

  cli-interface-change
  #175·napetrov opened Oct 22, 2026Contributor·5 tasks done·

  ·
  16

• feat(arms): multi-turn session measurement with per-turn usage

  cli-interface-change
  #174·napetrov opened Oct 22, 2026Contributor·6 tasks done·

  ·
  22

• feat(novelty): analyze states the measured share of readable words on stdout

  #173·napetrov opened Oct 22, 2026Contributor·5 tasks done·

  ·
  16

• feat(novelty): routing takes the catalog field, skips disabled and mirrored skills, adds all-vs-all

  cli-interface-change
  #172·napetrov opened Oct 22, 2026Contributor·5 tasks done·

  ·
  27

• feat(novelty): estimate-only projects the calls and dollars a run will spend

  #166·napetrov opened Oct 22, 2026Contributor·5 tasks done·

  ·
  28

• feat(novelty): usage and cost block for routing --model

  #164·napetrov opened Oct 22, 2026Contributor·5 tasks done·

  ·
  18

• feat(catalog): review skills against the Agent Skills spec, add --strict and --format json

  cli-interface-change
  #163·napetrov opened Oct 22, 2026Contributor·5 tasks done·

  ·
  19

• feat(skills): draft dokimi-design-evals skill

  #162·napetrov opened Oct 22, 2026Contributor·

  ·
  14

• feat(runner): plan.v1 / result.v1 and engine-computed completeness

  #161·napetrov opened Oct 22, 2026Contributor·

  ·
  16

• feat(repo): process metrics in result.json, manifest process_metrics, grade optional for dokimi: graders

  #157·napetrov opened Oct 22, 2026Contributor·4 tasks done·

  ·
  16

• feat(context, repo): consistency of repeated runs; pass^k and path stability in repo compare

  cli-interface-change
  #155·napetrov opened Oct 22, 2026Contributor·

  ·
  37

• feat(repo): skill/skill-catalog arms, cache tokens, MCP config when repo ships one

  cli-interface-change
  #137·napetrov opened Oct 20, 2026Contributor·

  ·
  88

• feat(repo): Codex and Copilot CLI harness profiles, native review mode

  #116·napetrov opened Oct 19, 2026Contributor·

  ·
  129

• feat(repo): --delegation and an execution id for repo run cells

  cli-interface-change
  #107·napetrov opened Oct 19, 2026Contributor·

  ·
  64