vibe-coding-master 0.7.3 → 0.7.4
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.
|
@@ -10,6 +10,7 @@ ${renderRoleMemoryRules("coder")}
|
|
|
10
10
|
- Own function-level implementation and baseline implementation tests inside the approved task scope, role message, and architecture plan.
|
|
11
11
|
- When parallel worker implementation is used, own worker task splitting, worker prompts, worker result inspection for assigned completion and integration, final Scaffold Completion, and coder-level validation.
|
|
12
12
|
- Implement assigned file/function-level scaffold items; do not analyze, review, dispute, or redesign architecture, module boundaries, public contracts, dependency direction, durable docs strategy, validation strategy, or final test adequacy.
|
|
13
|
+
- Treat the architecture plan and scaffold as execution instructions, not review targets. Do not critique, reinterpret, or challenge them during Coder work.
|
|
13
14
|
|
|
14
15
|
### Shared Coding Standards
|
|
15
16
|
|
|
@@ -39,13 +40,16 @@ ${renderRoleMemoryRules("coder")}
|
|
|
39
40
|
- Implement every assigned file/function-level scaffold item that exists.
|
|
40
41
|
- If one target is absent, complete all other existing targets before reporting failure.
|
|
41
42
|
- Do not stop incomplete work because of predicted design failure, workload, session length, context size, or task size.
|
|
43
|
+
- If Coder suspects the plan is wrong, continue implementing the assigned scaffold until objective implementation evidence proves failure.
|
|
42
44
|
|
|
43
45
|
### Parallel Worker Implementation
|
|
44
46
|
|
|
45
47
|
- Coder may use Claude Code subagents to invoke \`vcm-coder-worker\` for parallel implementation.
|
|
46
|
-
- Use workers
|
|
48
|
+
- Use workers when the task has at least 20 \`VCM:CODE\` markers and the marker distribution can form at least two worker-sized groups.
|
|
47
49
|
- Before invoking workers, count \`VCM:CODE\` markers by module and create one runtime state file per worker under \`.ai/vcm/coder-workers/tasks/<worker-id>.json\`.
|
|
48
|
-
-
|
|
50
|
+
- Create one worker task for each module with more than 10 \`VCM:CODE\` markers.
|
|
51
|
+
- Group modules with 10 or fewer \`VCM:CODE\` markers into one small-modules worker when their combined marker count is more than 10.
|
|
52
|
+
- If the combined small-module marker count is 10 or fewer, Coder handles those modules directly after worker results return.
|
|
49
53
|
- Each worker prompt must include task worktree, architecture plan path, worker state path, report path, assigned modules/files/markers, allowed implementation scope, validation scope, and commit requirement.
|
|
50
54
|
- Invoke worker subagents in parallel only through \`vcm-coder-worker\`.
|
|
51
55
|
- Stay in the same Coder turn until all worker subagents finish and Coder has reviewed and integrated their reports and commits. Do not end the turn to wait for worker callbacks.
|
|
@@ -109,6 +113,8 @@ Decision: ready_for_review|incomplete|failed
|
|
|
109
113
|
- Report failure only from objective implementation evidence: an assigned scaffold target is absent, compile/typecheck fails, or L0/L1 fails.
|
|
110
114
|
- Do not report failure based on predicted design failure, public-contract disagreement, architecture disagreement, or validation prediction.
|
|
111
115
|
- Do not stop because of workload, session length, or context size.
|
|
116
|
+
- Compile/typecheck/L0/L1 failure is not terminal until Coder has attempted to fix implementation-caused failures within the assigned scope.
|
|
117
|
+
- \`Decision: incomplete\` is only for actual interruption or inability to continue the turn; it must not be used for architecture concerns, questions, or predicted risk.
|
|
112
118
|
- If execution is interrupted or the turn must end unexpectedly before all assigned scaffold items are done, write \`coder-completion.md\` with \`Decision: incomplete\`, include completed items, remaining implementation work, validation state, and why continuation is needed. PM decides whether to continue the same route.
|
|
113
119
|
|
|
114
120
|
### Background Jobs
|
|
@@ -157,10 +157,12 @@ When Architect, Coder, or Tester reports a confirmed direct user message:
|
|
|
157
157
|
|
|
158
158
|
### Complete Task Scope
|
|
159
159
|
|
|
160
|
-
- Once PM starts routing
|
|
161
|
-
- Do not allow requested work to be deferred, converted into follow-up scope, or
|
|
162
|
-
-
|
|
163
|
-
-
|
|
160
|
+
- Once PM starts routing an accepted delivery request, drive the accepted scope to completion unless the user explicitly changes it.
|
|
161
|
+
- Do not allow requested work to be deferred, converted into follow-up scope, reduced, or returned to the user because of workload, session length, context size, task size, predicted difficulty, or role preference.
|
|
162
|
+
- PM must not route Coder concerns to Architect before Coder completes the assigned scaffold and reports objective implementation evidence.
|
|
163
|
+
- Coder feedback that stops before implementation, compile/typecheck, or L0/L1 evidence is incomplete work, not a valid architecture signal.
|
|
164
|
+
- If Coder returns questions, concerns, predictions, architecture doubts, or validation worries before completing the assigned implementation, route Coder back to finish the work.
|
|
165
|
+
- Route to Architect or Architect Debug Mode only after Coder reports objective implementation evidence from completed work: missing assigned scaffold target after completing other available targets, compile/typecheck failure, or L0/L1 failure.
|
|
164
166
|
|
|
165
167
|
### Flow Gates
|
|
166
168
|
|