4 Commits

Include renames

Author	SHA1	Message	Date
timothy	2fee3f0b94	docs(592): record that a skipped CI context is not red [decisions-edit] ... Amends ci.monitor-armed-at-pr-open (prose + Signals only; heading and key unchanged, no supersession) with the monitor-classification rules that were missing. Landing #436/#583 today, my CI monitor filtered per-context statuses on `!= "success"` and announced "NOT all green" on two fully green PRs, because `Build & push image (amd64)` reports `skipped`. Nothing was blocked — Gitea's combined /status already treats skipped as non-blocking and reported overall=success — but a false red costs a diagnosis cycle every time. Two corrections recorded: - The image job is skipped on EVERY PR (job-level `if: github.event_name != 'pull_request'`; images build only on push-to-main and tags), NOT because of the docs-only mechanism. Misattributing it to docs-only is a plausible-sounding wrong diagnosis, since docs-only gates STEPS precisely so required jobs still report success. decisions.md already stated the fact from the branch-protection angle; the monitor-authoring consequence was missing. - skipped / failure / cancelled are three distinct meanings and must not be collapsed. Prefer gating on the combined `.state`. The documented filter is verified in BOTH directions: silent on a green PR carrying a skipped build, and still dirty on a genuinely pending run. My first draft of it was itself broken — `select(.status != …)` after the pipeline had renamed `.status` to `.st`, so it compared against null and reported a green PR as nine failures. That failure is recorded in the note, per the "verify your detector" rule. fixes #592	2026-07-25 11:53:35 +02:00
timothy	7e5d20be98	fix(583): gate every model-less dispatch, not just implementer-looking ones ... Independent review of d221a065 found the prompt-text heuristic both over- and under-fired. Confirmed repros: a read-only recon brief merely mentioning "worktree" nagged, while "author the change and open a PR", "land this on the branch" and "make the changes and commit them" all passed silently — the gate missed exactly the case it existed to catch. Root cause behind all three findings: the hook contradicted its own rule. The HARD CONSTRAINT says "every dispatched agent"; the hook gated only dispatches whose prose looked like an implementer. Prompt text is not a reliable signal for authority. Inverted: ask whenever `model` is absent, exempting only `fork` (the tool ignores a fork's model override, so a prompt could not be acted on). This dissolves all three findings rather than patching the regex — no phrasing dependence, no false-positive concept, and no "cannot commit" claim to be wrong about. The reviewer was right that Explore/Plan/claude-code-guide all carry Bash, so the old exemption rationale was false. The noise objection is answered by the escape hatch, not by scoping: naming a tier costs one parameter and the hook never fires. Self-eliminating for anyone following the rule. Decision record updated to record the rejected narrow design and why. Re-verified: 11 payloads incl. all three findings, the invariants (model named -> never fires; fork exempt; non-Agent passes), and robustness (malformed JSON, empty payload, missing tool_input, embedded backticks/quotes/newlines) — never crashes, never emits malformed JSON. decisions-validate: OK.	2026-07-25 11:19:31 +02:00
timothy	d221a06522	chore(583): make per-agent model routing a hard constraint + PreToolUse gate ... The kickoff tells the orchestrator to route agents by capability, but that rule lived only in a prose paragraph. On 2026-07-25 a session dispatched two implementers (#436, #440) with `model` omitted, silently inheriting the orchestrator tier — while following every bullet in HARD CONSTRAINTS in the same session. The bulleted list is what functions as the checklist; prose above it reads as background. - HARD CONSTRAINTS: keyed routing bullet requiring the tier to be stated in the dispatch itself, so an invisible omission becomes visible output. Prose paragraph tightened to point at the key rather than restate the table (the kickoff is pasted into every session — duplication is a per-session tax, #542). - .claude/hooks/pretooluse-agent-model.sh: PreToolUse on Agent, `ask` when a committing agent is dispatched with no explicit `model`. Narrow by design — passes through read-only/recon types, `fork` (model override ignored by the tool), and any dispatch already naming a tier, because a gate that fires on every fan-out trains one-shot dismissal. `ask` not `deny`: routing is a judgment call with no derivable right answer, unlike the H6/H10 merge gate. - New decision record `process.per-agent-model-routing`; catalog regenerated. Decision matrix verified against 9 payloads incl. a replay of the dispatch that missed. decisions-validate: OK. fixes #583	2026-07-25 11:02:42 +02:00
timothy	12e5c3d26f	docs(542): record the workflow lore, then prune the kickoff doc to instructions ... Timothy asked why the kickoff handoff doc stores historical narrative when it should be instructions. It shouldn't — its own lore section is chartered as "STANDING workflow/orchestration rules only" with the why belonging in docs/decisions.md. But an inventory of every bullet against the decision corpus inverted the premise: only ~8 of ~38 were actually covered. 19 had no record anywhere and 11 more were half-covered, so that single file was the ONLY copy of the mandatory review rubric, the whole CI-triage vocabulary, the build-concurrency policy, the H12 session-end audit, and the plumbing-merge recipe. Pruning first would have destroyed them. So the records come first. New topic file docs/decisions/workflow-process.md carries 32 records (ci.*, process.*, testing.*) covering every NONE and PARTIAL the inventory found, including the Gitea `?milestones=` no-op bug whose only copy was the archived selector section this prune deletes. Only then the prune: HARD CONSTRAINTS and the lore section become one- or two-line rules, each citing the decision key that holds its evidence, and the 40-line "Archived — do not follow" section is gone. 636 -> 353 lines, with every cited key verified to resolve against the corpus. The aggregate corpus budget is re-baselined 4800 -> 5600 with the reason in the code: the corpus grew because knowledge MOVED into it, which is the system working, not drift. refs #542	2026-07-21 20:04:17 +02:00