@warnyin/sdlc 0.5.1 → 0.5.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +15 -0
- package/LICENSE +21 -21
- package/bin/cli.mjs +12 -1
- package/lib/caps.mjs +45 -45
- package/lib/config.mjs +41 -41
- package/lib/delta.mjs +227 -160
- package/lib/frontmatter.mjs +59 -59
- package/lib/glob.mjs +29 -29
- package/lib/manifest.mjs +99 -99
- package/lib/settings-merge.mjs +63 -63
- package/lib/validate.mjs +196 -186
- package/package.json +42 -42
- package/payload/adapters/agents-md.md +8 -8
- package/payload/adapters/claude/agents/sdlc-architect.md +12 -12
- package/payload/adapters/claude/agents/sdlc-builder.md +14 -14
- package/payload/adapters/claude/agents/sdlc-contractor.md +13 -13
- package/payload/adapters/claude/agents/sdlc-evaluator.md +13 -13
- package/payload/adapters/claude/agents/sdlc-learner.md +16 -16
- package/payload/adapters/claude/agents/sdlc-ops.md +11 -11
- package/payload/adapters/claude/agents/sdlc-quality.md +13 -13
- package/payload/adapters/claude/agents/sdlc-security.md +12 -12
- package/payload/adapters/claude/commands/sdlc/converge.md +5 -5
- package/payload/adapters/claude/commands/sdlc/init.md +4 -4
- package/payload/adapters/claude/commands/sdlc/next.md +4 -4
- package/payload/adapters/claude/commands/sdlc/observe.md +4 -4
- package/payload/adapters/claude/commands/sdlc/steer.md +4 -4
- package/payload/adapters/claude/skills/contract-writing/SKILL.md +26 -26
- package/payload/adapters/claude/skills/delta-spec-format/SKILL.md +36 -33
- package/payload/adapters/claude/skills/sdlc-conventions/SKILL.md +26 -26
- package/payload/adapters/cline.md +8 -8
- package/payload/adapters/copilot.md +8 -8
- package/payload/adapters/cursor.mdc +7 -7
- package/payload/adapters/gemini.md +8 -8
- package/payload/adapters/windsurf.md +4 -4
- package/payload/hooks/_shared.mjs +154 -154
- package/payload/hooks/guard-writes.mjs +83 -83
- package/payload/hooks/inject-context.mjs +55 -55
- package/payload/hooks/journal.mjs +58 -58
- package/payload/hooks/session-summary.mjs +50 -50
- package/payload/hooks/validate-artifact.mjs +80 -80
- package/payload/playbook/context.md +26 -26
- package/payload/playbook/converge.md +19 -19
- package/payload/playbook/init.md +22 -22
- package/payload/playbook/observe.md +20 -20
- package/payload/playbook/principles.md +28 -28
- package/payload/playbook/routing.md +19 -19
- package/payload/playbook/rules-card.md +16 -16
- package/payload/playbook/ship.md +2 -0
- package/payload/playbook/steer.md +21 -21
- package/payload/templates/change-deep.md +29 -29
- package/payload/templates/change-standard.md +28 -28
- package/payload/templates/change-vibe.md +19 -19
- package/payload/templates/config.yaml +8 -8
- package/payload/templates/constitution.md +14 -14
- package/payload/templates/contract-evals.md +9 -9
- package/payload/templates/contract-tests.md +9 -9
- package/payload/templates/harness.md +33 -33
- package/payload/templates/spec.md +14 -14
- package/payload/templates/steering.md +9 -9
- package/scripts/validate.mjs +47 -47
|
@@ -1,19 +1,19 @@
|
|
|
1
|
-
# Model routing
|
|
2
|
-
|
|
3
|
-
Generic tiers only — the harness adapter maps them to real models
|
|
4
|
-
(Claude Code agents: cheap→haiku, balanced→sonnet, deepest→opus).
|
|
5
|
-
|
|
6
|
-
| Task kind | Tier | Why |
|
|
7
|
-
|---|---|---|
|
|
8
|
-
| requirements shaping, architecture, deep design | deepest | judgment-heavy, small volume |
|
|
9
|
-
| standard implementation (sdlc-builder) | balanced | quality/cost sweet spot |
|
|
10
|
-
| test generation (sdlc-contractor) | cheap | mechanical from the contract table |
|
|
11
|
-
| eval judging (sdlc-evaluator) | cheap | rubric scoring, high volume |
|
|
12
|
-
| review panel passes | cheap–balanced | parallel, bounded scope |
|
|
13
|
-
| learning distillation (sdlc-learner) | cheap | summarization over journals |
|
|
14
|
-
|
|
15
|
-
Rules:
|
|
16
|
-
- Task lines in change.md may carry `[tier:cheap|balanced|deepest]`; default = balanced.
|
|
17
|
-
- Never send a mechanical task to deepest "to be safe" — that is the waste the
|
|
18
|
-
routing table exists to prevent.
|
|
19
|
-
- Escalate one tier only after a concrete failure at the current tier (journal it).
|
|
1
|
+
# Model routing
|
|
2
|
+
|
|
3
|
+
Generic tiers only — the harness adapter maps them to real models
|
|
4
|
+
(Claude Code agents: cheap→haiku, balanced→sonnet, deepest→opus).
|
|
5
|
+
|
|
6
|
+
| Task kind | Tier | Why |
|
|
7
|
+
|---|---|---|
|
|
8
|
+
| requirements shaping, architecture, deep design | deepest | judgment-heavy, small volume |
|
|
9
|
+
| standard implementation (sdlc-builder) | balanced | quality/cost sweet spot |
|
|
10
|
+
| test generation (sdlc-contractor) | cheap | mechanical from the contract table |
|
|
11
|
+
| eval judging (sdlc-evaluator) | cheap | rubric scoring, high volume |
|
|
12
|
+
| review panel passes | cheap–balanced | parallel, bounded scope |
|
|
13
|
+
| learning distillation (sdlc-learner) | cheap | summarization over journals |
|
|
14
|
+
|
|
15
|
+
Rules:
|
|
16
|
+
- Task lines in change.md may carry `[tier:cheap|balanced|deepest]`; default = balanced.
|
|
17
|
+
- Never send a mechanical task to deepest "to be safe" — that is the waste the
|
|
18
|
+
routing table exists to prevent.
|
|
19
|
+
- Escalate one tier only after a concrete failure at the current tier (journal it).
|
|
@@ -1,16 +1,16 @@
|
|
|
1
|
-
# sdlc rules card
|
|
2
|
-
<!-- ≤40 lines · embedded verbatim in non-Claude tool adapters; Claude gets the same rules enforced by hooks. -->
|
|
3
|
-
|
|
4
|
-
- Work flows through `sdlc/changes/<id>/change.md`: new → [design] → contract → build → verify → [review] → ship.
|
|
5
|
-
- NEVER edit `sdlc/specs/**` or `sdlc/changes/archive/**` by hand. Living specs change only
|
|
6
|
-
via a change's `## Delta:` section, merged by `npx @warnyin/sdlc archive <id>` at ship.
|
|
7
|
-
- NEVER hand-edit `journal.ndjson` or `sdlc/.state/**` — they are machine-owned.
|
|
8
|
-
- Write tests + evals (`contract/`) BEFORE code. No implementation while status is `new`.
|
|
9
|
-
- Ambiguity: make the safest assumption and record it under `## Assumptions`; use
|
|
10
|
-
`[NEEDS CLARIFICATION: q]` only for facts you cannot obtain — resolve all before contract.
|
|
11
|
-
- Respect line caps written in each template comment; run `npx @warnyin/sdlc validate <id>`
|
|
12
|
-
before claiming any gate passed — a red validator means the gate did NOT pass.
|
|
13
|
-
- Constitution edits go through /sdlc:steer only; always-loaded context ≤ 60 lines total.
|
|
14
|
-
- Verify = real test run + eval rubric. Max 3 fix rounds, then escalate to the human.
|
|
15
|
-
- Hard-floor (security, payments, data-loss, irreversible): tier = deep, human approves ship.
|
|
16
|
-
- Before editing an area, read any steering file whose `pathMatch` covers it.
|
|
1
|
+
# sdlc rules card
|
|
2
|
+
<!-- ≤40 lines · embedded verbatim in non-Claude tool adapters; Claude gets the same rules enforced by hooks. -->
|
|
3
|
+
|
|
4
|
+
- Work flows through `sdlc/changes/<id>/change.md`: new → [design] → contract → build → verify → [review] → ship.
|
|
5
|
+
- NEVER edit `sdlc/specs/**` or `sdlc/changes/archive/**` by hand. Living specs change only
|
|
6
|
+
via a change's `## Delta:` section, merged by `npx @warnyin/sdlc archive <id>` at ship.
|
|
7
|
+
- NEVER hand-edit `journal.ndjson` or `sdlc/.state/**` — they are machine-owned.
|
|
8
|
+
- Write tests + evals (`contract/`) BEFORE code. No implementation while status is `new`.
|
|
9
|
+
- Ambiguity: make the safest assumption and record it under `## Assumptions`; use
|
|
10
|
+
`[NEEDS CLARIFICATION: q]` only for facts you cannot obtain — resolve all before contract.
|
|
11
|
+
- Respect line caps written in each template comment; run `npx @warnyin/sdlc validate <id>`
|
|
12
|
+
before claiming any gate passed — a red validator means the gate did NOT pass.
|
|
13
|
+
- Constitution edits go through /sdlc:steer only; always-loaded context ≤ 60 lines total.
|
|
14
|
+
- Verify = real test run + eval rubric. Max 3 fix rounds, then escalate to the human.
|
|
15
|
+
- Hard-floor (security, payments, data-loss, irreversible): tier = deep, human approves ship.
|
|
16
|
+
- Before editing an area, read any steering file whose `pathMatch` covers it.
|
package/payload/playbook/ship.md
CHANGED
|
@@ -10,6 +10,8 @@ Precondition: `status: verified` (+ review passed when it ran).
|
|
|
10
10
|
`npx @warnyin/sdlc archive <id>`
|
|
11
11
|
(validates --strict, merges every Delta into `sdlc/specs/`, promotes evals,
|
|
12
12
|
stamps `status: shipped`, moves the folder to `changes/archive/<date>-<id>/`).
|
|
13
|
+
Any `⚠ MODIFIED Requirement …` line means the new body carried away a scenario
|
|
14
|
+
the spec still promised: confirm it was intended and name it in the digest.
|
|
13
15
|
3. **Learn** — delegate to `sdlc-learner` (cheap) with the archived change.md +
|
|
14
16
|
its journal.ndjson. It proposes ≤3 items: add-rule (with evidence pointer) /
|
|
15
17
|
expire-or-demote (rule or steering that never fired) / harness tweak.
|
|
@@ -1,21 +1,21 @@
|
|
|
1
|
-
# /sdlc:steer — manage the static/dynamic boundary
|
|
2
|
-
|
|
3
|
-
The ONLY sanctioned way to edit always-loaded context.
|
|
4
|
-
|
|
5
|
-
1. `node sdlc/.hooks/journal.mjs open-steer`
|
|
6
|
-
2. Apply the requested edits:
|
|
7
|
-
- New knowledge → a steering file with the LEAST resident inclusion mode that
|
|
8
|
-
works: `agent` > `manual` > `paths` > `always` (always needs justification).
|
|
9
|
-
- Constitution edits: SHALL/SHALL NOT lines only. If the always-budget
|
|
10
|
-
(60 lines) would overflow, something must be demoted or deleted first —
|
|
11
|
-
name the displaced line explicitly.
|
|
12
|
-
3. Hygiene pass (do it every time, it is 30 seconds):
|
|
13
|
-
- `/sdlc:observe` data — steering never pointer-hit across the last N changes
|
|
14
|
-
→ propose demote (`paths`→`manual`) or delete.
|
|
15
|
-
- Rules with no guard/journal evidence of ever mattering → propose expiry.
|
|
16
|
-
- Apply what the user agrees to (reductions may be applied without asking).
|
|
17
|
-
4. `npx @warnyin/sdlc validate` — the always-budget check must be green.
|
|
18
|
-
5. `node sdlc/.hooks/journal.mjs close`
|
|
19
|
-
|
|
20
|
-
Learning direction is one-way by design: content flows from always → paths →
|
|
21
|
-
manual → deleted as evidence accumulates. Getting leaner is the success metric.
|
|
1
|
+
# /sdlc:steer — manage the static/dynamic boundary
|
|
2
|
+
|
|
3
|
+
The ONLY sanctioned way to edit always-loaded context.
|
|
4
|
+
|
|
5
|
+
1. `node sdlc/.hooks/journal.mjs open-steer`
|
|
6
|
+
2. Apply the requested edits:
|
|
7
|
+
- New knowledge → a steering file with the LEAST resident inclusion mode that
|
|
8
|
+
works: `agent` > `manual` > `paths` > `always` (always needs justification).
|
|
9
|
+
- Constitution edits: SHALL/SHALL NOT lines only. If the always-budget
|
|
10
|
+
(60 lines) would overflow, something must be demoted or deleted first —
|
|
11
|
+
name the displaced line explicitly.
|
|
12
|
+
3. Hygiene pass (do it every time, it is 30 seconds):
|
|
13
|
+
- `/sdlc:observe` data — steering never pointer-hit across the last N changes
|
|
14
|
+
→ propose demote (`paths`→`manual`) or delete.
|
|
15
|
+
- Rules with no guard/journal evidence of ever mattering → propose expiry.
|
|
16
|
+
- Apply what the user agrees to (reductions may be applied without asking).
|
|
17
|
+
4. `npx @warnyin/sdlc validate` — the always-budget check must be green.
|
|
18
|
+
5. `node sdlc/.hooks/journal.mjs close`
|
|
19
|
+
|
|
20
|
+
Learning direction is one-way by design: content flows from always → paths →
|
|
21
|
+
manual → deleted as evidence accumulates. Getting leaner is the success metric.
|
|
@@ -1,29 +1,29 @@
|
|
|
1
|
-
---
|
|
2
|
-
id: <kebab-id>
|
|
3
|
-
tier: deep
|
|
4
|
-
status: new
|
|
5
|
-
---
|
|
6
|
-
# Change: <title>
|
|
7
|
-
<!-- cap:150 · deep tier: hard-floor surface (security/payments/data-loss/irreversible) or new/multi-capability delta. Human gates apply per Autonomy policy. -->
|
|
8
|
-
|
|
9
|
-
## Why (≤5 lines)
|
|
10
|
-
<problem + outcome. No solutioning.>
|
|
11
|
-
|
|
12
|
-
## Assumptions
|
|
13
|
-
- <assumption made instead of asking, with the reason it is safe>
|
|
14
|
-
|
|
15
|
-
## Delta: <capability>
|
|
16
|
-
|
|
17
|
-
### ADDED Requirement: <name>
|
|
18
|
-
The system SHALL <behavior>.
|
|
19
|
-
|
|
20
|
-
#### Scenario: <name>
|
|
21
|
-
- WHEN <condition>
|
|
22
|
-
- THEN <observable outcome>
|
|
23
|
-
|
|
24
|
-
## Design
|
|
25
|
-
<!-- decisions & trade-offs only — never restate the delta. Escalate irreversible decisions per Autonomy policy. -->
|
|
26
|
-
- decision: <what> · alternatives: <a/b> · because: <why>
|
|
27
|
-
|
|
28
|
-
## Tasks
|
|
29
|
-
- [ ] T1 <task> [P] [tier:balanced]
|
|
1
|
+
---
|
|
2
|
+
id: <kebab-id>
|
|
3
|
+
tier: deep
|
|
4
|
+
status: new
|
|
5
|
+
---
|
|
6
|
+
# Change: <title>
|
|
7
|
+
<!-- cap:150 · deep tier: hard-floor surface (security/payments/data-loss/irreversible) or new/multi-capability delta. Human gates apply per Autonomy policy. -->
|
|
8
|
+
|
|
9
|
+
## Why (≤5 lines)
|
|
10
|
+
<problem + outcome. No solutioning.>
|
|
11
|
+
|
|
12
|
+
## Assumptions
|
|
13
|
+
- <assumption made instead of asking, with the reason it is safe>
|
|
14
|
+
|
|
15
|
+
## Delta: <capability>
|
|
16
|
+
|
|
17
|
+
### ADDED Requirement: <name>
|
|
18
|
+
The system SHALL <behavior>.
|
|
19
|
+
|
|
20
|
+
#### Scenario: <name>
|
|
21
|
+
- WHEN <condition>
|
|
22
|
+
- THEN <observable outcome>
|
|
23
|
+
|
|
24
|
+
## Design
|
|
25
|
+
<!-- decisions & trade-offs only — never restate the delta. Escalate irreversible decisions per Autonomy policy. -->
|
|
26
|
+
- decision: <what> · alternatives: <a/b> · because: <why>
|
|
27
|
+
|
|
28
|
+
## Tasks
|
|
29
|
+
- [ ] T1 <task> [P] [tier:balanced]
|
|
@@ -1,28 +1,28 @@
|
|
|
1
|
-
---
|
|
2
|
-
id: <kebab-id>
|
|
3
|
-
tier: standard
|
|
4
|
-
status: new
|
|
5
|
-
---
|
|
6
|
-
# Change: <title>
|
|
7
|
-
<!-- cap:100 · standard tier. Delta sections ARE the spec change — merged mechanically at ship, never re-narrated. -->
|
|
8
|
-
|
|
9
|
-
## Why (≤5 lines)
|
|
10
|
-
<problem + outcome. No solutioning.>
|
|
11
|
-
|
|
12
|
-
## Assumptions
|
|
13
|
-
- <assumption made instead of asking, with the reason it is safe — delete section if none>
|
|
14
|
-
<!-- unresolved ambiguity the agent cannot assume → [NEEDS CLARIFICATION: question] inline where it bites -->
|
|
15
|
-
|
|
16
|
-
## Delta: <capability>
|
|
17
|
-
|
|
18
|
-
### ADDED Requirement: <name>
|
|
19
|
-
The system SHALL <behavior>.
|
|
20
|
-
|
|
21
|
-
#### Scenario: <name>
|
|
22
|
-
- WHEN <condition>
|
|
23
|
-
- THEN <observable outcome>
|
|
24
|
-
|
|
25
|
-
## Tasks
|
|
26
|
-
<!-- [P] = parallelizable wave · [tier:cheap|balanced|deepest] per the routing table in harness.md -->
|
|
27
|
-
- [ ] T1 <task> [P] [tier:balanced]
|
|
28
|
-
- [ ] T2 <task> [tier:cheap]
|
|
1
|
+
---
|
|
2
|
+
id: <kebab-id>
|
|
3
|
+
tier: standard
|
|
4
|
+
status: new
|
|
5
|
+
---
|
|
6
|
+
# Change: <title>
|
|
7
|
+
<!-- cap:100 · standard tier. Delta sections ARE the spec change — merged mechanically at ship, never re-narrated. -->
|
|
8
|
+
|
|
9
|
+
## Why (≤5 lines)
|
|
10
|
+
<problem + outcome. No solutioning.>
|
|
11
|
+
|
|
12
|
+
## Assumptions
|
|
13
|
+
- <assumption made instead of asking, with the reason it is safe — delete section if none>
|
|
14
|
+
<!-- unresolved ambiguity the agent cannot assume → [NEEDS CLARIFICATION: question] inline where it bites -->
|
|
15
|
+
|
|
16
|
+
## Delta: <capability>
|
|
17
|
+
|
|
18
|
+
### ADDED Requirement: <name>
|
|
19
|
+
The system SHALL <behavior>.
|
|
20
|
+
|
|
21
|
+
#### Scenario: <name>
|
|
22
|
+
- WHEN <condition>
|
|
23
|
+
- THEN <observable outcome>
|
|
24
|
+
|
|
25
|
+
## Tasks
|
|
26
|
+
<!-- [P] = parallelizable wave · [tier:cheap|balanced|deepest] per the routing table in harness.md -->
|
|
27
|
+
- [ ] T1 <task> [P] [tier:balanced]
|
|
28
|
+
- [ ] T2 <task> [tier:cheap]
|
|
@@ -1,19 +1,19 @@
|
|
|
1
|
-
---
|
|
2
|
-
id: <kebab-id>
|
|
3
|
-
tier: vibe
|
|
4
|
-
status: new
|
|
5
|
-
---
|
|
6
|
-
# Change: <title>
|
|
7
|
-
<!-- cap:40 · vibe tier = one file, no contract. Reversible, no behavior-contract change, ≤2 files. -->
|
|
8
|
-
|
|
9
|
-
## Why (≤3 lines)
|
|
10
|
-
<problem + outcome>
|
|
11
|
-
|
|
12
|
-
## Assumptions
|
|
13
|
-
- <assumption the agent made instead of asking — delete section if none>
|
|
14
|
-
|
|
15
|
-
## Tasks
|
|
16
|
-
- [ ] T1 <task>
|
|
17
|
-
|
|
18
|
-
## Receipt (filled at ship)
|
|
19
|
-
- files touched: · test result: · cost:
|
|
1
|
+
---
|
|
2
|
+
id: <kebab-id>
|
|
3
|
+
tier: vibe
|
|
4
|
+
status: new
|
|
5
|
+
---
|
|
6
|
+
# Change: <title>
|
|
7
|
+
<!-- cap:40 · vibe tier = one file, no contract. Reversible, no behavior-contract change, ≤2 files. -->
|
|
8
|
+
|
|
9
|
+
## Why (≤3 lines)
|
|
10
|
+
<problem + outcome>
|
|
11
|
+
|
|
12
|
+
## Assumptions
|
|
13
|
+
- <assumption the agent made instead of asking — delete section if none>
|
|
14
|
+
|
|
15
|
+
## Tasks
|
|
16
|
+
- [ ] T1 <task>
|
|
17
|
+
|
|
18
|
+
## Receipt (filled at ship)
|
|
19
|
+
- files touched: · test result: · cost:
|
|
@@ -1,8 +1,8 @@
|
|
|
1
|
-
# @warnyin/sdlc project config — machine-read; keep minimal.
|
|
2
|
-
language: en
|
|
3
|
-
tools: [] # filled by `warnyin-sdlc init`
|
|
4
|
-
# Optional price table for cost reporting (USD per 1M tokens).
|
|
5
|
-
# prices:
|
|
6
|
-
# claude-sonnet-5: { input: 3, output: 15, cacheRead: 0.3 }
|
|
7
|
-
# Optional per-artifact cap overrides (see lib/caps.mjs for defaults).
|
|
8
|
-
# caps: {}
|
|
1
|
+
# @warnyin/sdlc project config — machine-read; keep minimal.
|
|
2
|
+
language: en
|
|
3
|
+
tools: [] # filled by `warnyin-sdlc init`
|
|
4
|
+
# Optional price table for cost reporting (USD per 1M tokens).
|
|
5
|
+
# prices:
|
|
6
|
+
# claude-sonnet-5: { input: 3, output: 15, cacheRead: 0.3 }
|
|
7
|
+
# Optional per-artifact cap overrides (see lib/caps.mjs for defaults).
|
|
8
|
+
# caps: {}
|
|
@@ -1,14 +1,14 @@
|
|
|
1
|
-
# Constitution — <project>
|
|
2
|
-
<!-- cap:30 · ALWAYS LOADED: every line here costs tokens in EVERY turn. Prove residency or move it to steering. -->
|
|
3
|
-
|
|
4
|
-
## Stack (facts only, max 3 lines)
|
|
5
|
-
- <runtime / framework / db — one line each>
|
|
6
|
-
|
|
7
|
-
## Hard rules (SHALL / SHALL NOT only — no advice)
|
|
8
|
-
- The agent SHALL NOT edit `sdlc/specs/**` or `sdlc/changes/archive/**` outside `/sdlc:ship`.
|
|
9
|
-
- The agent SHALL record every assumption in the change's `## Assumptions` before acting on it.
|
|
10
|
-
- <add a rule each time the agent misbehaves; each new rule must displace an old one once the always-budget (60 lines) is full>
|
|
11
|
-
|
|
12
|
-
## Workflow
|
|
13
|
-
- Changes flow: new → [design] → contract → build → verify → [review] → ship.
|
|
14
|
-
- Tier by stakes: vibe | standard | deep — triage table lives in `sdlc/harness.md`.
|
|
1
|
+
# Constitution — <project>
|
|
2
|
+
<!-- cap:30 · ALWAYS LOADED: every line here costs tokens in EVERY turn. Prove residency or move it to steering. -->
|
|
3
|
+
|
|
4
|
+
## Stack (facts only, max 3 lines)
|
|
5
|
+
- <runtime / framework / db — one line each>
|
|
6
|
+
|
|
7
|
+
## Hard rules (SHALL / SHALL NOT only — no advice)
|
|
8
|
+
- The agent SHALL NOT edit `sdlc/specs/**` or `sdlc/changes/archive/**` outside `/sdlc:ship`.
|
|
9
|
+
- The agent SHALL record every assumption in the change's `## Assumptions` before acting on it.
|
|
10
|
+
- <add a rule each time the agent misbehaves; each new rule must displace an old one once the always-budget (60 lines) is full>
|
|
11
|
+
|
|
12
|
+
## Workflow
|
|
13
|
+
- Changes flow: new → [design] → contract → build → verify → [review] → ship.
|
|
14
|
+
- Tier by stakes: vibe | standard | deep — triage table lives in `sdlc/harness.md`.
|
|
@@ -1,9 +1,9 @@
|
|
|
1
|
-
# Eval contract — <change-id>
|
|
2
|
-
<!-- cap:40 · verifies the non-deterministic half: trajectory + quality. Scored by sdlc-evaluator (cheap tier). -->
|
|
3
|
-
|
|
4
|
-
## Rubric (score 1–5 each)
|
|
5
|
-
- Trajectory: did the agent read the contract before writing code? run tests before claiming done?
|
|
6
|
-
- Quality: <change-specific bars>
|
|
7
|
-
|
|
8
|
-
## Pass bar
|
|
9
|
-
- all scores ≥ 4 · failures route back to `/sdlc:build` with a cluster note
|
|
1
|
+
# Eval contract — <change-id>
|
|
2
|
+
<!-- cap:40 · verifies the non-deterministic half: trajectory + quality. Scored by sdlc-evaluator (cheap tier). -->
|
|
3
|
+
|
|
4
|
+
## Rubric (score 1–5 each)
|
|
5
|
+
- Trajectory: did the agent read the contract before writing code? run tests before claiming done?
|
|
6
|
+
- Quality: <change-specific bars>
|
|
7
|
+
|
|
8
|
+
## Pass bar
|
|
9
|
+
- all scores ≥ 4 · failures route back to `/sdlc:build` with a cluster note
|
|
@@ -1,9 +1,9 @@
|
|
|
1
|
-
# Test contract — <change-id>
|
|
2
|
-
<!-- cap:60 · written BEFORE code. This is the deterministic half of the contract with the AI; failing tests are generated from this table. -->
|
|
3
|
-
|
|
4
|
-
| # | Given / When / Then | Kind (unit/int/e2e) | Maps to requirement |
|
|
5
|
-
|---|---|---|---|
|
|
6
|
-
| 1 | <g/w/t> | unit | <requirement name> |
|
|
7
|
-
|
|
8
|
-
## Out of scope (explicitly untested + why)
|
|
9
|
-
- <item — reason>
|
|
1
|
+
# Test contract — <change-id>
|
|
2
|
+
<!-- cap:60 · written BEFORE code. This is the deterministic half of the contract with the AI; failing tests are generated from this table. -->
|
|
3
|
+
|
|
4
|
+
| # | Given / When / Then | Kind (unit/int/e2e) | Maps to requirement |
|
|
5
|
+
|---|---|---|---|
|
|
6
|
+
| 1 | <g/w/t> | unit | <requirement name> |
|
|
7
|
+
|
|
8
|
+
## Out of scope (explicitly untested + why)
|
|
9
|
+
- <item — reason>
|
|
@@ -1,33 +1,33 @@
|
|
|
1
|
-
# Harness — <project>
|
|
2
|
-
<!-- cap:60 · CONFIGURE-phase output; reviewed like code. Registry + tables only — doctrine lives in sdlc/.playbook/. -->
|
|
3
|
-
|
|
4
|
-
## Tools & MCP (what the agent may call)
|
|
5
|
-
| Tool/MCP | Scope | Notes |
|
|
6
|
-
|---|---|---|
|
|
7
|
-
| <tool> | <what it may touch> | <when to use> |
|
|
8
|
-
|
|
9
|
-
## Sandbox & execution
|
|
10
|
-
- test command: `<cmd>`
|
|
11
|
-
- sandbox notes: <where code runs, what it cannot reach>
|
|
12
|
-
|
|
13
|
-
## Guardrails (mirror of installed hooks — deterministic, the agent cannot skip them)
|
|
14
|
-
- `sdlc/specs/**` and archive are write-locked outside ship.
|
|
15
|
-
- Artifact line caps validated on every write.
|
|
16
|
-
- Session token/cost journaled per change.
|
|
17
|
-
|
|
18
|
-
## Model routing (generic tiers — the harness adapter maps them to real models)
|
|
19
|
-
| Task kind | Tier |
|
|
20
|
-
|---|---|
|
|
21
|
-
| requirements, architecture, deep design | deepest |
|
|
22
|
-
| standard implementation | balanced |
|
|
23
|
-
| test generation, review passes, mechanical/scaffold, eval judging, learning | cheap |
|
|
24
|
-
|
|
25
|
-
## Tier triage (stakes → tier)
|
|
26
|
-
- vibe: reversible, no behavior-contract change, ≤2 files.
|
|
27
|
-
- deep: security / payments / data-loss / irreversible surface, new capability, or multi-capability delta.
|
|
28
|
-
- otherwise: standard.
|
|
29
|
-
|
|
30
|
-
## Autonomy policy
|
|
31
|
-
- auto-ship: vibe, standard.
|
|
32
|
-
- escalate to human: hard-floor (security, payments, data-loss, irreversible), verify failed > 3 rounds,
|
|
33
|
-
token budget exceeded, information the agent cannot obtain or safely assume.
|
|
1
|
+
# Harness — <project>
|
|
2
|
+
<!-- cap:60 · CONFIGURE-phase output; reviewed like code. Registry + tables only — doctrine lives in sdlc/.playbook/. -->
|
|
3
|
+
|
|
4
|
+
## Tools & MCP (what the agent may call)
|
|
5
|
+
| Tool/MCP | Scope | Notes |
|
|
6
|
+
|---|---|---|
|
|
7
|
+
| <tool> | <what it may touch> | <when to use> |
|
|
8
|
+
|
|
9
|
+
## Sandbox & execution
|
|
10
|
+
- test command: `<cmd>`
|
|
11
|
+
- sandbox notes: <where code runs, what it cannot reach>
|
|
12
|
+
|
|
13
|
+
## Guardrails (mirror of installed hooks — deterministic, the agent cannot skip them)
|
|
14
|
+
- `sdlc/specs/**` and archive are write-locked outside ship.
|
|
15
|
+
- Artifact line caps validated on every write.
|
|
16
|
+
- Session token/cost journaled per change.
|
|
17
|
+
|
|
18
|
+
## Model routing (generic tiers — the harness adapter maps them to real models)
|
|
19
|
+
| Task kind | Tier |
|
|
20
|
+
|---|---|
|
|
21
|
+
| requirements, architecture, deep design | deepest |
|
|
22
|
+
| standard implementation | balanced |
|
|
23
|
+
| test generation, review passes, mechanical/scaffold, eval judging, learning | cheap |
|
|
24
|
+
|
|
25
|
+
## Tier triage (stakes → tier)
|
|
26
|
+
- vibe: reversible, no behavior-contract change, ≤2 files.
|
|
27
|
+
- deep: security / payments / data-loss / irreversible surface, new capability, or multi-capability delta.
|
|
28
|
+
- otherwise: standard.
|
|
29
|
+
|
|
30
|
+
## Autonomy policy
|
|
31
|
+
- auto-ship: vibe, standard.
|
|
32
|
+
- escalate to human: hard-floor (security, payments, data-loss, irreversible), verify failed > 3 rounds,
|
|
33
|
+
token budget exceeded, information the agent cannot obtain or safely assume.
|
|
@@ -1,14 +1,14 @@
|
|
|
1
|
-
# Spec: <capability>
|
|
2
|
-
<!-- cap:150 (soft) · living spec — observable behavior only, no implementation detail. Split the capability beyond the cap. -->
|
|
3
|
-
|
|
4
|
-
## Purpose
|
|
5
|
-
<!-- one or two lines; commands grep this header first (progressive disclosure) -->
|
|
6
|
-
|
|
7
|
-
## Requirements
|
|
8
|
-
|
|
9
|
-
### Requirement: <name>
|
|
10
|
-
The system SHALL <behavior>.
|
|
11
|
-
|
|
12
|
-
#### Scenario: <name>
|
|
13
|
-
- WHEN <condition>
|
|
14
|
-
- THEN <observable outcome>
|
|
1
|
+
# Spec: <capability>
|
|
2
|
+
<!-- cap:150 (soft) · living spec — observable behavior only, no implementation detail. Split the capability beyond the cap. -->
|
|
3
|
+
|
|
4
|
+
## Purpose
|
|
5
|
+
<!-- one or two lines; commands grep this header first (progressive disclosure) -->
|
|
6
|
+
|
|
7
|
+
## Requirements
|
|
8
|
+
|
|
9
|
+
### Requirement: <name>
|
|
10
|
+
The system SHALL <behavior>.
|
|
11
|
+
|
|
12
|
+
#### Scenario: <name>
|
|
13
|
+
- WHEN <condition>
|
|
14
|
+
- THEN <observable outcome>
|
|
@@ -1,9 +1,9 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: <topic>
|
|
3
|
-
inclusion: paths # always | paths | manual | agent
|
|
4
|
-
pathMatch: ["src/<area>/**"]
|
|
5
|
-
---
|
|
6
|
-
# Steering: <topic>
|
|
7
|
-
<!-- cap:40 · loaded only when pathMatch hits or explicitly requested. Dense, scoped conventions — no generalities. -->
|
|
8
|
-
|
|
9
|
-
<conventions, gotchas, and reference patterns for this scope>
|
|
1
|
+
---
|
|
2
|
+
name: <topic>
|
|
3
|
+
inclusion: paths # always | paths | manual | agent
|
|
4
|
+
pathMatch: ["src/<area>/**"]
|
|
5
|
+
---
|
|
6
|
+
# Steering: <topic>
|
|
7
|
+
<!-- cap:40 · loaded only when pathMatch hits or explicitly requested. Dense, scoped conventions — no generalities. -->
|
|
8
|
+
|
|
9
|
+
<conventions, gotchas, and reference patterns for this scope>
|
package/scripts/validate.mjs
CHANGED
|
@@ -1,47 +1,47 @@
|
|
|
1
|
-
#!/usr/bin/env node
|
|
2
|
-
// Thin CLI wrapper — validator core lives in lib/validate.mjs so that
|
|
3
|
-
// installed hooks (sdlc/.hooks/lib/) can share the exact same logic.
|
|
4
|
-
// Exit codes: 0 = clean, 1 = errors, 2 = usage/setup error.
|
|
5
|
-
|
|
6
|
-
import fs from 'node:fs';
|
|
7
|
-
import path from 'node:path';
|
|
8
|
-
import process from 'node:process';
|
|
9
|
-
import { fileURLToPath } from 'node:url';
|
|
10
|
-
import { validateAll, formatIssues } from '../lib/validate.mjs';
|
|
11
|
-
|
|
12
|
-
export * from '../lib/validate.mjs';
|
|
13
|
-
|
|
14
|
-
function main() {
|
|
15
|
-
const args = process.argv.slice(2);
|
|
16
|
-
const strict = args.includes('--strict');
|
|
17
|
-
const rootIdx = args.indexOf('--root');
|
|
18
|
-
const projectRoot = rootIdx !== -1 ? args[rootIdx + 1] : process.cwd();
|
|
19
|
-
const positional = args.filter((a, i) => !a.startsWith('--') && args[i - 1] !== '--root');
|
|
20
|
-
const changeId = positional[0] && positional[0] !== '--all' ? positional[0] : null;
|
|
21
|
-
|
|
22
|
-
const sdlcRoot = path.join(projectRoot, 'sdlc');
|
|
23
|
-
if (!fs.existsSync(sdlcRoot)) {
|
|
24
|
-
console.error(`No sdlc/ directory at ${projectRoot} — run \`npx @warnyin/sdlc init\` first.`);
|
|
25
|
-
process.exit(2);
|
|
26
|
-
}
|
|
27
|
-
|
|
28
|
-
const issues = validateAll(sdlcRoot, { strict, changeId });
|
|
29
|
-
if (issues.length) console.log(formatIssues(issues));
|
|
30
|
-
const errors = issues.filter((i) => i.level === 'error').length;
|
|
31
|
-
const warns = issues.length - errors;
|
|
32
|
-
console.log(`validate: ${errors} error(s), ${warns} warning(s)${strict ? ' [strict]' : ''}`);
|
|
33
|
-
process.exit(errors > 0 ? 1 : 0);
|
|
34
|
-
}
|
|
35
|
-
|
|
36
|
-
function isEntrypoint() {
|
|
37
|
-
if (!process.argv[1]) return false;
|
|
38
|
-
try {
|
|
39
|
-
return fs.realpathSync.native(path.resolve(process.argv[1])) === fileURLToPath(import.meta.url);
|
|
40
|
-
} catch {
|
|
41
|
-
return false;
|
|
42
|
-
}
|
|
43
|
-
}
|
|
44
|
-
|
|
45
|
-
if (isEntrypoint()) {
|
|
46
|
-
main();
|
|
47
|
-
}
|
|
1
|
+
#!/usr/bin/env node
|
|
2
|
+
// Thin CLI wrapper — validator core lives in lib/validate.mjs so that
|
|
3
|
+
// installed hooks (sdlc/.hooks/lib/) can share the exact same logic.
|
|
4
|
+
// Exit codes: 0 = clean, 1 = errors, 2 = usage/setup error.
|
|
5
|
+
|
|
6
|
+
import fs from 'node:fs';
|
|
7
|
+
import path from 'node:path';
|
|
8
|
+
import process from 'node:process';
|
|
9
|
+
import { fileURLToPath } from 'node:url';
|
|
10
|
+
import { validateAll, formatIssues } from '../lib/validate.mjs';
|
|
11
|
+
|
|
12
|
+
export * from '../lib/validate.mjs';
|
|
13
|
+
|
|
14
|
+
function main() {
|
|
15
|
+
const args = process.argv.slice(2);
|
|
16
|
+
const strict = args.includes('--strict');
|
|
17
|
+
const rootIdx = args.indexOf('--root');
|
|
18
|
+
const projectRoot = rootIdx !== -1 ? args[rootIdx + 1] : process.cwd();
|
|
19
|
+
const positional = args.filter((a, i) => !a.startsWith('--') && args[i - 1] !== '--root');
|
|
20
|
+
const changeId = positional[0] && positional[0] !== '--all' ? positional[0] : null;
|
|
21
|
+
|
|
22
|
+
const sdlcRoot = path.join(projectRoot, 'sdlc');
|
|
23
|
+
if (!fs.existsSync(sdlcRoot)) {
|
|
24
|
+
console.error(`No sdlc/ directory at ${projectRoot} — run \`npx @warnyin/sdlc init\` first.`);
|
|
25
|
+
process.exit(2);
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
const issues = validateAll(sdlcRoot, { strict, changeId });
|
|
29
|
+
if (issues.length) console.log(formatIssues(issues));
|
|
30
|
+
const errors = issues.filter((i) => i.level === 'error').length;
|
|
31
|
+
const warns = issues.length - errors;
|
|
32
|
+
console.log(`validate: ${errors} error(s), ${warns} warning(s)${strict ? ' [strict]' : ''}`);
|
|
33
|
+
process.exit(errors > 0 ? 1 : 0);
|
|
34
|
+
}
|
|
35
|
+
|
|
36
|
+
function isEntrypoint() {
|
|
37
|
+
if (!process.argv[1]) return false;
|
|
38
|
+
try {
|
|
39
|
+
return fs.realpathSync.native(path.resolve(process.argv[1])) === fileURLToPath(import.meta.url);
|
|
40
|
+
} catch {
|
|
41
|
+
return false;
|
|
42
|
+
}
|
|
43
|
+
}
|
|
44
|
+
|
|
45
|
+
if (isEntrypoint()) {
|
|
46
|
+
main();
|
|
47
|
+
}
|