mirror of
https://github.com/bmad-code-org/BMAD-METHOD.git
synced 2026-08-29 03:44:18 +08:00
Brian
47bab7d15c
* feat(project-context): rewrite as prescriptive AGENTS.md generator Replace the kernel+bundle context system with a single product: a short verified agent guide (AGENTS.md). A field trial of the first version showed repo scanning produces polished-but-useless factoids; the rewrite fills a fixed section plan from ranked evidence channels (executable config and CI, targeted git history, session logs, human interview) and uses the repository only to verify claims, never as the source of knowledge. - Intents: bootstrap, refresh, record (capture an observed agent mistake), audit; query is gone with the bundle - Per-fact entry files, trust frontmatter, index, placement machinery, and the skill's context.py mechanics script are removed; accountability moves to one plain ledger file recording every candidate claim and its disposition - Skill directory only; docs, forwarding husks, and shared scripts untouched * refactor(project-context): per-section admission rules, two-tier guide Revisions from two end-to-end trials plus review: - Replace the global non-derivable test with per-section admission rules: brevity (orientation), authority (policy), universal need verified by execution (commands, verification), wrong-default-assumption (conventions), localization value (pointers), observed failure only (pitfalls) - Two-tier output: AGENTS.md (orientation + policy + pointer) for every session, AGENTS-dev.md for coding sessions; single file when tiny - Pitfalls can never be nominated by scans: sources are recorded lessons, maintainer recall, session evidence, and the writing session's own caught mistakes; retirement only when the guarded thing is gone or the human says so, since a working rule erases its own evidence - Interview ergonomics: recall questions, never review lists; testimony the repo contradicts is surfaced with evidence, never written or dropped - Trial-driven fixes: guide-to-filesystem link check, mutating-command go-ahead as the interview's first question, plain-English rewrite throughout * fix(project-context): bidirectional coverage trace, history-evidenced pitfalls Round-3 trial findings: an unsourced pitfall entered the guide at composition time because coverage only checked ledger-to-guide; and repeat-fix git history, the strongest pitfall evidence observed, was not an explicitly admitted source. * refactor(project-context): move Where-things-are to AGENTS.md, imperative lines Where-things-are pointers serve planning sessions as much as coding ones, so they belong in the always-loaded file. Shape rules now require every line to state an action (bare facts only as justification clauses) and stable contract headings across runs. * docs(project-context): session-kind guides as a third structural axis A maintainer-named frequent session kind (UX, manual testing, data work) may earn its own AGENTS-<kind>.md behind a pointer; module-level differences stay with scoped guides. * refactor(project-context): action-gated dev-guide pointer, two-file example The AGENTS-dev.md hop is the most common progressive-discovery trigger, so it is now gated on the first hands-on action rather than session self-classification, names its payoff, and names the exemption. The contract's worked example shows the two-file form with the pointer in situ. Scoped-guide discovery no longer assumes harness nearest-file loading: the root-guide pointer is the mechanism. * refactor(project-context): adopt shared memlog, drop unearned claims The run record is now a standard memlog kept with the shared memlog.py script — append-only typed entries, latest entry wins — replacing the bespoke ledger format; stale-disposition notes become structurally impossible. Two appeal-to-measurement assertions cut: the operative admission and exclusion rules carry that load. * docs(project-context): guard handwritten guides The skill never commits — its output stays as working-tree changes for the user. Headless runs never rewrite a guide the memlog doesn't record writing; they leave an AGENTS.md.proposed for an interactive merge. * docs(project-context): fold in prior-art research findings Five adoptions from the generator prior-art survey: prohibitions name their permitted alternative; an emphasis-marker budget; a git-log --diff-filter=DR drift check on refresh; TODO placeholders over guessed greenfield commands; commit and branch conventions mined from history. * docs(project-context): route candidates to enforcement before prose Compose now asks, per accepted candidate, whether a hook, lint rule, or CI check enforces it better than a guide line; the line is the fallback and a landed check deletes it. * docs(project-context): narrow refresh interview and contradiction flagging Refresh interviews shrink to one recall question — what changed since the last run. Cross-file contradictions are flagged only when they change behavior; rewording and overlap are not contradictions. * refactor(project-context): conversational skill, no script, AGENTS.md block Refine the skill into an implementation-layer capability: a conversation that produces one small verified block inside the repo's AGENTS.md. The human is in the loop for every write; there is no autonomous mode. - Drop src/scripts/context.py and its tests. Nothing it did is needed once the output is a single spliced block rather than a bundle of files. - Replace guide-contract.md and evidence.md with best-practices.md (admission, exclusion, retirement, retrieval, maintenance) and template.md (section list plus a worked example, no placeholders). - Collapse the two-file AGENTS.md/AGENTS-dev.md split into one block. A pointer the agent must choose to follow gets skipped; anything load-bearing goes in the always-loaded file. - Replace per-section admission rules with one test: anything derivable from source is read live, never stored. Commands stated in package.json, a Makefile, or CI config no longer earn a line; their caveats do. - Ask up front whether a run covers the root only or named sub-projects, gated on observable evidence (a workspace manifest, per-directory build manifests). - Husk bmad-document-project and bmad-generate-project-context onto setup intent, and say plainly that the deeper system-explanation altitude is a separate capability rather than shipping a thin substitute. - Align module-help.csv, bmad-correct-course, the analyst menu, and the docs set with the block as the output. --------- Co-authored-by: Alex Verkhovsky <alexey.verkhovsky@gmail.com>