@koreanhole/kandev 0.0.0-stage → 0.1.0
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/README.md +367 -2
- package/bin/codex-acp.js +16 -0
- package/bin/kandev-auto-sync.mjs +101 -0
- package/bin/kandev-config.js +53 -0
- package/bin/kandev.js +35 -0
- package/config/config.yaml +6 -0
- package/config/docker/projects/opencodex-cli.json +79 -0
- package/config/docker/projects/samsung-bus-tracker.json +91 -0
- package/config/gateways.json +14 -0
- package/config/pipeline.json +150 -0
- package/config/workflows/sdlc.yaml +1019 -0
- package/docker/Dockerfile +68 -0
- package/docker/Dockerfile.opencodex-cli +44 -0
- package/docker/Dockerfile.samsung-bus-tracker +75 -0
- package/package.json +61 -4
- package/scripts/agent-tools-docker.mjs +223 -0
- package/scripts/baseline.mjs +20 -0
- package/scripts/codex-medium +2 -0
- package/scripts/codex-stage +22 -0
- package/scripts/gate.mjs +909 -0
- package/scripts/gateways/docker.mjs +64 -0
- package/scripts/gateways/speckit.mjs +78 -0
- package/scripts/install-prerequisites.mjs +48 -0
- package/scripts/lib/artifacts.mjs +990 -0
- package/scripts/lib/bugfix.mjs +325 -0
- package/scripts/lib/checksum.mjs +166 -0
- package/scripts/lib/docker-workspace.mjs +1209 -0
- package/scripts/lib/gateways.mjs +79 -0
- package/scripts/lib/kandev.mjs +273 -0
- package/scripts/lib/mcp.mjs +111 -0
- package/scripts/lib/pipeline.mjs +548 -0
- package/scripts/lib/planning-replan.mjs +103 -0
- package/scripts/lib/resume.mjs +207 -0
- package/scripts/lib/review-history.mjs +260 -0
- package/scripts/lib/stage-boundary.mjs +146 -0
- package/scripts/lib/stage-model.mjs +23 -0
- package/scripts/lib/task-worktree.mjs +40 -0
- package/scripts/measure-tokens.mjs +121 -0
- package/scripts/planning-tools.mjs +166 -0
- package/scripts/replan-planning.mjs +82 -0
- package/scripts/review-digest.mjs +240 -0
- package/scripts/run-android-e2e.mjs +116 -0
- package/scripts/run-code-review.mjs +281 -0
- package/scripts/run-detached.mjs +163 -0
- package/scripts/run-doc-review.mjs +155 -0
- package/scripts/run-gateways.mjs +138 -0
- package/scripts/sync.mjs +588 -0
- package/scripts/verify-change.mjs +252 -0
- package/scripts/verify-node.mjs +288 -0
- package/scripts/verify.mjs +442 -0
- package/scripts/wait-status.mjs +88 -0
|
@@ -0,0 +1,1019 @@
|
|
|
1
|
+
version: 2
|
|
2
|
+
type: kandev_workflow
|
|
3
|
+
workflows:
|
|
4
|
+
- name: Agentic SDLC
|
|
5
|
+
description: >-
|
|
6
|
+
Five gated agent stages plus a human approval lane: generic agent gateways,
|
|
7
|
+
Spec Kit planning and document review, clean-context implementation,
|
|
8
|
+
independent code review, and browser end-to-end verification. Every agent
|
|
9
|
+
transition requires a machine-readable artifact and an explicit completion
|
|
10
|
+
signal; a person reviews the verified worktree and moves the task to Done.
|
|
11
|
+
steps:
|
|
12
|
+
- name: 1. Agent Gateway
|
|
13
|
+
position: 0
|
|
14
|
+
color: bg-slate-500
|
|
15
|
+
profile_ref: SDLC 1 · Gateway
|
|
16
|
+
is_start_step: true
|
|
17
|
+
show_in_command_panel: true
|
|
18
|
+
allow_manual_move: false
|
|
19
|
+
auto_advance_requires_signal: true
|
|
20
|
+
cancel_triggers_turn_complete: false
|
|
21
|
+
complete_task_on_enter: false
|
|
22
|
+
events:
|
|
23
|
+
on_enter:
|
|
24
|
+
- type: auto_start_agent
|
|
25
|
+
prompt: |
|
|
26
|
+
You are Stage 1, the agent gateway. Work only in the task's repository
|
|
27
|
+
worktree. Do not write application code.
|
|
28
|
+
|
|
29
|
+
Stage boundary: only `.specify/`, `.agents/`, and
|
|
30
|
+
`.agentic/gateway.json` may change. The gate snapshots the worktree and
|
|
31
|
+
rejects any application, specification, or other out-of-scope path.
|
|
32
|
+
|
|
33
|
+
The task description belongs to Planning and is intentionally not
|
|
34
|
+
provided here. The gateway runner executes every gateway enabled in
|
|
35
|
+
the workflow configuration. Do not hard-code a vendor or assume the
|
|
36
|
+
current gateway list cannot grow.
|
|
37
|
+
|
|
38
|
+
Tool-output discipline:
|
|
39
|
+
Bound every command. Build/test logs: `2>&1 | tail -60`.
|
|
40
|
+
File/report reads: `| head -c 4000`. Never run unbounded `cat`,
|
|
41
|
+
`rg` over HTML/base64/minified assets or reports, `ls -R` of
|
|
42
|
+
`node_modules`, or `find` over caches. If output may exceed ~8KB,
|
|
43
|
+
redirect to `.agentic/logs/<name>.log`, then inspect with
|
|
44
|
+
`rg -n -m 20` or `sed -n 'a,bp'`. A tool result larger than ~8KB is
|
|
45
|
+
a pipeline defect: rerun bounded before reasoning about it.
|
|
46
|
+
|
|
47
|
+
Tool-calling discipline:
|
|
48
|
+
Every turn MUST execute a tool call until the stage is complete. Never
|
|
49
|
+
output conversational commentary, plans, explanations, or text-only
|
|
50
|
+
messages without calling a tool in the same turn. Do not stop to explain
|
|
51
|
+
what you will do.
|
|
52
|
+
Use the `agent-tools` MCP server's `run_process` tool with `argv` only;
|
|
53
|
+
in tool declarations it may appear as `run_process`, `agent-tools/run_process`,
|
|
54
|
+
`agent-tools.run_process`, or `mcp__agent_tools__run_process`.
|
|
55
|
+
Wait for agent-tools to be ready before running any stage command. If it is
|
|
56
|
+
absent, use the host's tool discovery and a non-shell wait, then refresh the
|
|
57
|
+
tool catalog and retry for up to 60 seconds. Never use a host shell as a
|
|
58
|
+
substitute. If still unavailable, stop without signaling success; the gate
|
|
59
|
+
will block or resume this stage.
|
|
60
|
+
|
|
61
|
+
As your first bridge call, execute the gateway runner in one shot using `sh`:
|
|
62
|
+
argv: ["sh", "-c", "node \"$KANDEV_WORKFLOW_ROOT/scripts/run-gateways.mjs\" --cwd \"$PWD\" --task \"agent gateway\" --json"]
|
|
63
|
+
|
|
64
|
+
Do not run shell commands, list files, read files, or edit anything before
|
|
65
|
+
or after the runner. Never create or edit `.agentic/gateway.json` yourself;
|
|
66
|
+
only `run-gateways.mjs` may write `.agentic/gateway.json`.
|
|
67
|
+
|
|
68
|
+
Completion rule: signal only when the runner exits 0,
|
|
69
|
+
`.agentic/gateway.json` has verdict PASS, every enabled gateway in it
|
|
70
|
+
has status PASS, and `application_files_changed` is empty. Call
|
|
71
|
+
`step_complete_kandev` to complete this step. On FAIL, leave the
|
|
72
|
+
artifact in place and call `step_complete_kandev` so the gate records
|
|
73
|
+
the failure; the gate decides the transition.
|
|
74
|
+
|
|
75
|
+
Resume contract: a message beginning with `[Kandev resume` is a
|
|
76
|
+
continuation of the current stage, not a new task. Do not restart
|
|
77
|
+
completed work, change scope, or move the step. Produce or signal the
|
|
78
|
+
named `.agentic` artifact and call `step_complete_kandev`. If this
|
|
79
|
+
stage ends in FAIL, write the FAIL artifact and signal it; do not stop
|
|
80
|
+
silently.
|
|
81
|
+
|
|
82
|
+
- name: 2. Planning
|
|
83
|
+
position: 1
|
|
84
|
+
color: bg-blue-500
|
|
85
|
+
profile_ref: SDLC 2 · Planning
|
|
86
|
+
is_start_step: false
|
|
87
|
+
show_in_command_panel: true
|
|
88
|
+
allow_manual_move: false
|
|
89
|
+
auto_advance_requires_signal: true
|
|
90
|
+
cancel_triggers_turn_complete: false
|
|
91
|
+
complete_task_on_enter: false
|
|
92
|
+
events:
|
|
93
|
+
on_enter:
|
|
94
|
+
- type: auto_start_agent
|
|
95
|
+
prompt: |
|
|
96
|
+
You are Stage 2, Spec Kit planning and document review. Work only in
|
|
97
|
+
the task's repository worktree. Do not write application code.
|
|
98
|
+
|
|
99
|
+
Your first bridge action MUST be `agent-tools.run_process` with
|
|
100
|
+
`["printenv","KANDEV_WORKFLOW_ROOT"]`; your second MUST be `["pwd"]`;
|
|
101
|
+
wait for both string outputs before calling any script or reading
|
|
102
|
+
files (never call scripts in the same parallel turn as printenv/pwd);
|
|
103
|
+
your third MUST read `<worktree>/.agents/skills/speckit-specify/SKILL.md`.
|
|
104
|
+
Follow that skill file. Do not use the shell tool. Do not inspect
|
|
105
|
+
`node_modules`, `~/.npm`, `~/.kandev`, `scripts/lib`, the implementation
|
|
106
|
+
of `run-doc-review.mjs` or `planning-tools.mjs`, or package sources.
|
|
107
|
+
Invoke helper scripts as commands only; their contracts are in this
|
|
108
|
+
prompt. Read the other `speckit-*` SKILL.md files in order before using
|
|
109
|
+
them.
|
|
110
|
+
|
|
111
|
+
{{task_prompt}}
|
|
112
|
+
|
|
113
|
+
Tool-output discipline:
|
|
114
|
+
Bound every command. Build/test logs: `2>&1 | tail -60`.
|
|
115
|
+
File/report reads: `| head -c 4000`. Never run unbounded `cat`,
|
|
116
|
+
`rg` over HTML/base64/minified assets or reports, `ls -R` of
|
|
117
|
+
`node_modules`, or `find` over caches. If output may exceed ~8KB,
|
|
118
|
+
redirect to `.agentic/logs/<name>.log`, then inspect with
|
|
119
|
+
`rg -n -m 20` or `sed -n 'a,bp'`. A tool result larger than ~8KB is
|
|
120
|
+
a pipeline defect: rerun bounded before reasoning about it.
|
|
121
|
+
|
|
122
|
+
Tool-calling discipline:
|
|
123
|
+
Every turn MUST execute a tool call until the stage is complete. Never
|
|
124
|
+
output conversational commentary, plans, explanations, or text-only
|
|
125
|
+
messages without calling a tool in the same turn. Do not stop to explain
|
|
126
|
+
what you will do.
|
|
127
|
+
Use the `agent-tools` MCP server's `run_process` tool with `argv` only;
|
|
128
|
+
in tool declarations it may appear as `run_process`, `agent-tools/run_process`,
|
|
129
|
+
`agent-tools.run_process`, or `mcp__agent_tools__run_process`.
|
|
130
|
+
Wait for agent-tools to be ready before running any stage command. If it is
|
|
131
|
+
absent, use the host's tool discovery and a non-shell wait, then refresh the
|
|
132
|
+
tool catalog and retry for up to 60 seconds. Never use a host shell as a
|
|
133
|
+
substitute. If still unavailable, stop without signaling success; the gate
|
|
134
|
+
will block or resume this stage.
|
|
135
|
+
As your first bridge call, execute `run_process` with `argv: ["printenv", "KANDEV_WORKFLOW_ROOT"]`.
|
|
136
|
+
As your second bridge call, execute `run_process` with `argv: ["pwd"]`.
|
|
137
|
+
Once both paths are obtained, immediately proceed to execute the stage
|
|
138
|
+
actions without stopping to talk.
|
|
139
|
+
|
|
140
|
+
Use the project's Spec Kit skills in this order:
|
|
141
|
+
$speckit-specify -> $speckit-clarify -> $speckit-plan -> $speckit-tasks
|
|
142
|
+
Do not run `$speckit-implement`; implementation belongs to the next
|
|
143
|
+
stage. `$speckit-clarify` must not wait for a human: resolve each
|
|
144
|
+
question from repository evidence and the task description, and record
|
|
145
|
+
every assumption in `spec.md`. Use `.specify/feature.json` to locate
|
|
146
|
+
the feature directory created by `$speckit-specify`.
|
|
147
|
+
|
|
148
|
+
Classify the task before writing the plan. Write `change_type` and
|
|
149
|
+
`classification_reason` in `.agentic/spec.json`. Use `bugfix` when the
|
|
150
|
+
task describes an existing defect, regression, crash, or broken
|
|
151
|
+
behavior. Do not call a defect a feature to skip reproduction.
|
|
152
|
+
A `feature` classification must name the new behavior and explain why
|
|
153
|
+
no existing behavior is being fixed. If the task contains `[bug]`,
|
|
154
|
+
`bug:`, `bugfix:`, `hotfix:`, `regression:`, an issue reference, or a
|
|
155
|
+
Korean bug/error/outage word, use `bugfix`; the gate rejects a feature
|
|
156
|
+
classification for any bug marker.
|
|
157
|
+
|
|
158
|
+
Bugfix branch (required when `change_type` is `bugfix`):
|
|
159
|
+
1. After `$speckit-specify` and `$speckit-clarify`, write
|
|
160
|
+
`.agentic/bugfix.json` with the issue symptom, the original and
|
|
161
|
+
expected behavior, the canonical reproduction command, the pinned
|
|
162
|
+
reproduction files, the root-cause evidence, and the planned
|
|
163
|
+
regression test path. The driver must be
|
|
164
|
+
`.agentic/bugfix-repro.mjs`; pin its sha256 together with every
|
|
165
|
+
other `.agentic` file it imports. Use this contract:
|
|
166
|
+
{
|
|
167
|
+
"stage": "bugfix",
|
|
168
|
+
"task": "<exact task string>",
|
|
169
|
+
"timestamp": "<ISO-8601>",
|
|
170
|
+
"verdict": "PASS",
|
|
171
|
+
"issue": {"summary": "...", "source": "...", "observed": "...", "expected": "..."},
|
|
172
|
+
"reproduction": {
|
|
173
|
+
"driver": ".agentic/bugfix-repro.mjs",
|
|
174
|
+
"command": ["node", ".agentic/bugfix-repro.mjs"],
|
|
175
|
+
"files": [{"path": ".agentic/bugfix-repro.mjs", "sha256": "..."}],
|
|
176
|
+
"scenario_id": "BUG-1",
|
|
177
|
+
"result_path": ".agentic/bugfix-result.json",
|
|
178
|
+
"expected_before": "failed",
|
|
179
|
+
"expected_after": "passed"
|
|
180
|
+
},
|
|
181
|
+
"root_cause": {
|
|
182
|
+
"summary": "...",
|
|
183
|
+
"evidence": [{"path": "src/file.ts", "line": 1, "note": "..."}],
|
|
184
|
+
"causal_chain": ["trigger", "fault", "visible result"]
|
|
185
|
+
},
|
|
186
|
+
"fix_scope": ["src/file.ts"],
|
|
187
|
+
"regression_test": {
|
|
188
|
+
"path": "tests/bugfix/example.test.ts",
|
|
189
|
+
"command": ["npm", "test", "--", "tests/bugfix/example.test.ts"],
|
|
190
|
+
"framework": "node-test" | "junit" | "playwright" | "other"
|
|
191
|
+
}
|
|
192
|
+
}
|
|
193
|
+
2. Write `.agentic/bugfix-repro.mjs` as a real E2E driver for the
|
|
194
|
+
current platform. It must drive the actual UI, CLI, or Android
|
|
195
|
+
device, write `.agentic/bugfix-result.json` with
|
|
196
|
+
`{"scenario":"BUG-1","status":"failed|passed","evidence":"..."}`,
|
|
197
|
+
and exit non-zero while the bug exists.
|
|
198
|
+
The driver `.agentic/bugfix-repro.mjs` MUST ONLY write to
|
|
199
|
+
`.agentic/bugfix-result.json`. It MUST NOT write to or reference
|
|
200
|
+
any file under `.agentic/bugfix-runs/` (such as
|
|
201
|
+
`planning-before.result.json` or `implementation-before.result.json`).
|
|
202
|
+
Hardcoding writes to `.agentic/bugfix-runs/` inside the driver will
|
|
203
|
+
corrupt historical failure evidence during Stage 3 and Stage 5
|
|
204
|
+
replays and will be rejected by the planning finalizer and the gate.
|
|
205
|
+
3. Run the driver before `$speckit-plan` with `agent-tools.run_process`
|
|
206
|
+
and `argv` only. Save bounded output to
|
|
207
|
+
`.agentic/bugfix-runs/planning-before.log`, copy the driver result to
|
|
208
|
+
`.agentic/bugfix-runs/planning-before.result.json`, and write
|
|
209
|
+
`.agentic/bugfix-runs/planning-before.json` with `phase`,
|
|
210
|
+
`scenario_id`, `status: "failed"`, `exit_code`, `evidence`, `log`,
|
|
211
|
+
`result_path`, and `timestamp`. If the driver exits 0 or reports
|
|
212
|
+
`passed`, stop; do not reclassify the task as a feature.
|
|
213
|
+
4. Analyze the root cause from the running code, not from the symptom.
|
|
214
|
+
Record at least one `path:line` evidence entry outside `.agentic/`,
|
|
215
|
+
`specs/`, and `.specify/`, a causal chain with at least two steps,
|
|
216
|
+
and the fix scope.
|
|
217
|
+
5. Only after the failing reproduction and root-cause evidence exist,
|
|
218
|
+
run `$speckit-plan` and `$speckit-tasks`. Name the reproduced
|
|
219
|
+
behavior `BUG-1`, add a matching `AC-BUG-1` acceptance criterion,
|
|
220
|
+
and plan the regression test at the exact path in
|
|
221
|
+
`bugfix.json.regression_test.path`.
|
|
222
|
+
|
|
223
|
+
The planning finalizer validates `.agentic/bugfix.json` and the
|
|
224
|
+
`planning-before` evidence. A missing or passing pre-fix run is a
|
|
225
|
+
blocker; never downgrade it to `feature` to advance.
|
|
226
|
+
|
|
227
|
+
If a `$speckit-*` skill is not exposed in your skill list, read the
|
|
228
|
+
corresponding `.agents/skills/speckit-<name>/SKILL.md` file and follow
|
|
229
|
+
it directly. The project skill files are authoritative. Do not search
|
|
230
|
+
Kandev internals, `~/.kandev`, `node_modules`, or the host installation
|
|
231
|
+
for them. Use `agent-tools.run_process` for every command; the shell
|
|
232
|
+
tool does not inherit `KANDEV_WORKFLOW_ROOT`. Obtain that value with
|
|
233
|
+
`["printenv","KANDEV_WORKFLOW_ROOT"]` and pass absolute paths.
|
|
234
|
+
|
|
235
|
+
Stage boundary: only `specs/` and `.specify/feature.json` may change.
|
|
236
|
+
Do not modify application files, `.agents`, any other `.specify` file,
|
|
237
|
+
or implementation artifacts. The gate rejects out-of-scope paths.
|
|
238
|
+
|
|
239
|
+
Keep spec.md self-consistent across FR-*, AC-*, and SC-*: use one
|
|
240
|
+
explicit start anchor and pass/fail condition per timing/freshness
|
|
241
|
+
rule, state explicit precedence when two ACs cover fallback/empty
|
|
242
|
+
states, and leave architecture, data-model fields, and adb/clock-jump
|
|
243
|
+
driver steps in plan.md, data-model.md, and quickstart.md.
|
|
244
|
+
Follow these self-consistency rules:
|
|
245
|
+
- Refresh ordering rule: Define latest refresh by monotonic request sequence or snapshot version; late-completing older refreshes are dropped.
|
|
246
|
+
- Measurable outcomes timing rule: Measurable Outcomes (`SC-*`) sample times must always be at or after the maximum allowed display deadline (e.g. if FR allows up to 20 seconds after 17:00:00 for the widget to render, SC must sample at 17:00:25 or 17:00:30, never at 17:00:10).
|
|
247
|
+
- Inactive / fallback state rule: Clarify RON active window vs inactive fallback in a concise single state definition.
|
|
248
|
+
|
|
249
|
+
After the documents exist, run a bounded review loop. The requirement
|
|
250
|
+
review run is the snapshot of record: every listed document, including
|
|
251
|
+
`analysis.md`, must be final before that run starts, and must not change
|
|
252
|
+
until the next round starts. Each round runs both reviewers on the same
|
|
253
|
+
final documents:
|
|
254
|
+
1. Finish every listed document first. Invoke the `$speckit-analyze`
|
|
255
|
+
skill on the feature directory and write its complete report to
|
|
256
|
+
`.agentic/speckit-analyze.md`. The report must state a PASS/FAIL
|
|
257
|
+
verdict and count CRITICAL, major, and minor findings. Fold every
|
|
258
|
+
CRITICAL or major analyze finding into the feature documents and
|
|
259
|
+
`analysis.md` before the requirement review starts. `analysis.md`
|
|
260
|
+
must contain the final cross-artifact review and no unresolved
|
|
261
|
+
CRITICAL finding.
|
|
262
|
+
2. Start the requirement review as a detached process with the
|
|
263
|
+
`agent-tools` MCP server and `run_process` with `argv` only;
|
|
264
|
+
`command_line` is forbidden. Resolve `KANDEV_WORKFLOW_ROOT` and the
|
|
265
|
+
absolute worktree path first:
|
|
266
|
+
["node","<printed root>/scripts/run-doc-review.mjs","--cwd","<printed worktree>","--input","<feature directory>","--log",".agentic/doc-review.log","--status",".agentic/doc-review.status.json"]
|
|
267
|
+
It returns immediately with a monitorPid. Wait with:
|
|
268
|
+
["node","<printed root>/scripts/wait-status.mjs","--status",".agentic/doc-review.status.json","--timeout-ms","280000"]
|
|
269
|
+
using `timeout_ms` 300000. Repeat that wait once if still running,
|
|
270
|
+
then poll every 60 seconds until completed, failed, or 30 minutes
|
|
271
|
+
pass. On failure, record the error and retry at most once. Do not
|
|
272
|
+
inspect the npm registry or debug package resolution.
|
|
273
|
+
3. Parse the latest RunSummary JSON from `.agentic/doc-review.log`.
|
|
274
|
+
Record its run id, finding stable ids, and blocker/major/minor counts. The
|
|
275
|
+
wrapper runs the pinned `@koreanhole/requirement-agent@0.1.7` with
|
|
276
|
+
the ambiguity, testability, and consistency roles. The run's
|
|
277
|
+
`run.json`, `findings.json`, and `snapshot.json` are authoritative.
|
|
278
|
+
4. In Round 1, every blocker must be remediated in `spec.md` followed
|
|
279
|
+
by Round 2. Fix requirement-agent majors only when they
|
|
280
|
+
change the implementation or test contract. Record every remaining
|
|
281
|
+
testability or consistency major in `accepted_majors` with a
|
|
282
|
+
concrete reason and the exact `stableId` from `findings.json`; do
|
|
283
|
+
not rewrite the contract just to make the count fall. A later round
|
|
284
|
+
may legitimately have more majors than the previous round because
|
|
285
|
+
the reviewer reviews revised text; display ids may renumber, so use
|
|
286
|
+
`stableId` when carrying a major across rounds. Do not treat an
|
|
287
|
+
increase as a failure. Keep observation windows, fixture
|
|
288
|
+
ids, clock jumps, and timing procedures in `quickstart.md` or the
|
|
289
|
+
bugfix driver, not in `spec.md`. Once two completed review rounds
|
|
290
|
+
exist, the `FR-*`, `AC-*`, and `SC-*` id set from the latest
|
|
291
|
+
completed round is frozen. Do not add, renumber, or split ids
|
|
292
|
+
during remediation; the wrapper and finalizer reject new ids. A
|
|
293
|
+
finding that needs genuinely new behavior is a planning blocker:
|
|
294
|
+
write the FAIL/blocked report and stop for replan. Edit only the
|
|
295
|
+
passages cited by the findings. A failed wrapper run may be retried
|
|
296
|
+
once as infrastructure recovery.
|
|
297
|
+
5. Stop reviewing when the latest completed round has zero blockers,
|
|
298
|
+
or once at least two completed review rounds exist (`rounds >= 2`,
|
|
299
|
+
including after Round 2 or Round 3), if a remaining blocker finding
|
|
300
|
+
in `findings.json` is already satisfied by existing `spec.md`
|
|
301
|
+
clauses (a disputed or single-role interpretation that does not
|
|
302
|
+
require new `FR-*`/`AC-*` scope), do NOT fail the stage or start
|
|
303
|
+
another round: write `verdict: "PASS"`, record the exact counts from
|
|
304
|
+
`run.json`, list every remaining blocker's `stableId` in
|
|
305
|
+
`blocker_ids: ["<final blocker stableId>"]`, and justify each in
|
|
306
|
+
`accepted_blockers: [{"id": "<final blocker stableId>", "reason": "<concrete citation in spec.md showing why the requirement is already unambiguous and testable>"}]`
|
|
307
|
+
(when `blockers` is 0, set `blocker_ids: []` and `accepted_blockers: []`
|
|
308
|
+
or omit them). At Round 3 (the final allowed round), if findings
|
|
309
|
+
remain regarding edge case timings, sampling intervals, or
|
|
310
|
+
interpretations that do not alter the core user scenario, the agent
|
|
311
|
+
MUST NOT fail the stage: it must set `verdict: "PASS"`, populate
|
|
312
|
+
`blocker_ids`, and provide concrete citations in `accepted_blockers`
|
|
313
|
+
showing why the requirement is unambiguous and testable, so that
|
|
314
|
+
Stage 2 successfully advances to Stage 3. Write the PASS envelope
|
|
315
|
+
with every remaining major in `accepted_majors`; do not run another
|
|
316
|
+
round just to lower the count.
|
|
317
|
+
If you edited any listed document after that run, its snapshot is
|
|
318
|
+
stale: run another review round when the budget allows, otherwise
|
|
319
|
+
stop and write the FAIL/blocked report. If the wrapper refuses a new
|
|
320
|
+
round because three completed rounds already exist, stop. If it
|
|
321
|
+
refuses because the requirement id set grew or a reviewed document
|
|
322
|
+
expanded past the remediation budget, remove the added ids or text
|
|
323
|
+
and address the finding by clarifying the existing requirements; if
|
|
324
|
+
that is impossible, stop and write the FAIL/blocked report. Do not
|
|
325
|
+
delete ids or edit the wrapper to bypass the guard. Run the
|
|
326
|
+
finalizer first even on FAIL so the snapshot hashes are recorded,
|
|
327
|
+
then write the FAIL/blocked report. Do not start a fourth round. The
|
|
328
|
+
wrapper writes `.agentic/planning-blocked.json` with the reason and
|
|
329
|
+
review history; report it and call `step_complete_kandev` so the
|
|
330
|
+
gate records the blocked state.
|
|
331
|
+
|
|
332
|
+
After the final clean round, write `.agentic/spec.json` with:
|
|
333
|
+
{
|
|
334
|
+
"stage": "planning",
|
|
335
|
+
"task": "<copy the exact task string>",
|
|
336
|
+
"timestamp": "<ISO-8601>",
|
|
337
|
+
"change_type": "feature" | "bugfix",
|
|
338
|
+
"classification_reason": "<why this is a feature or bugfix>",
|
|
339
|
+
"platform": "web" | "android" | "node",
|
|
340
|
+
"feature_dir": "<relative feature directory>",
|
|
341
|
+
"documents": ["spec.md", "plan.md", "tasks.md", "analysis.md", "checklists/requirements.md", ...],
|
|
342
|
+
"functional_requirements": [{"id": "FR-001", "text": "..."}],
|
|
343
|
+
"acceptance_criteria": [{"id": "AC-1", "given": "...", "when": "...", "then": "..."}],
|
|
344
|
+
"out_of_scope": ["..."],
|
|
345
|
+
"risks": ["..."],
|
|
346
|
+
"assumptions": ["..."],
|
|
347
|
+
"application_files_changed": []
|
|
348
|
+
}
|
|
349
|
+
Include every functional requirement and acceptance criterion from the
|
|
350
|
+
final `spec.md`. Label the acceptance scenarios with their AC ids in
|
|
351
|
+
`spec.md` so the contract and the document agree. Every listed document
|
|
352
|
+
must exist under `feature_dir`; include `spec.md`, `plan.md`,
|
|
353
|
+
`tasks.md`, `analysis.md`, and `checklists/requirements.md` at minimum.
|
|
354
|
+
`analysis.md` must already be final and included in the latest review
|
|
355
|
+
snapshot; a document created or edited after that run is rejected.
|
|
356
|
+
|
|
357
|
+
Then write `.agentic/spec-review.json` with the standard review
|
|
358
|
+
envelope plus both reviewer records:
|
|
359
|
+
{
|
|
360
|
+
"stage": "planning-review",
|
|
361
|
+
"task": "<copy the exact task string>",
|
|
362
|
+
"timestamp": "<ISO-8601>",
|
|
363
|
+
"verdict": "PASS",
|
|
364
|
+
"rounds": <number of completed review runs>,
|
|
365
|
+
"blockers": 0,
|
|
366
|
+
"majors": <final requirement-agent major count>,
|
|
367
|
+
"minors": <count>,
|
|
368
|
+
"major_history": [<counts>],
|
|
369
|
+
"blocker_ids": [],
|
|
370
|
+
"accepted_blockers": [],
|
|
371
|
+
"major_ids": ["<final major stableId>"],
|
|
372
|
+
"accepted_majors": [{"id": "<final major stableId>", "reason": "<why it does not change the contract>"}],
|
|
373
|
+
"reviewers": {
|
|
374
|
+
"requirement_agent": {
|
|
375
|
+
"package": "@koreanhole/requirement-agent@0.1.7",
|
|
376
|
+
"roles": ["ambiguity", "testability", "consistency"],
|
|
377
|
+
"run_id": "<latest run id>",
|
|
378
|
+
"status": "completed",
|
|
379
|
+
"blockers": 0,
|
|
380
|
+
"majors": <final requirement-agent major count>,
|
|
381
|
+
"minors": <count>
|
|
382
|
+
},
|
|
383
|
+
"speckit_analyze": {
|
|
384
|
+
"skill": "$speckit-analyze",
|
|
385
|
+
"report": ".agentic/speckit-analyze.md",
|
|
386
|
+
"status": "completed",
|
|
387
|
+
"verdict": "PASS",
|
|
388
|
+
"critical": 0,
|
|
389
|
+
"major": 0,
|
|
390
|
+
"minor": <count>
|
|
391
|
+
}
|
|
392
|
+
},
|
|
393
|
+
"agent": "@koreanhole/requirement-agent@0.1.7 + $speckit-analyze"
|
|
394
|
+
}
|
|
395
|
+
Finally run the deterministic finalizer with `agent-tools.run_process`:
|
|
396
|
+
["node","<printed root>/scripts/planning-tools.mjs","finalize","--cwd","<printed worktree>"]
|
|
397
|
+
It writes `reviewed_documents` from the latest review run's
|
|
398
|
+
`snapshot.json`, validates the feature directory, checklists, and
|
|
399
|
+
`.specify/feature.json`, and exits non-zero on a mismatch. Set
|
|
400
|
+
`rounds`, `blockers`, `majors`, `minors`, `major_history`, `major_ids`,
|
|
401
|
+
and both reviewer count fields from the completed run artifacts, with
|
|
402
|
+
one `major_history` entry per completed round. Do not hand-edit the
|
|
403
|
+
hashes it writes. If it reports a changed or missing document, run
|
|
404
|
+
another review round of the final documents when the budget allows;
|
|
405
|
+
otherwise block for replan.
|
|
406
|
+
|
|
407
|
+
Completion rule: signal only when the finalizer exits 0,
|
|
408
|
+
`.agentic/spec.json` parses, `spec-review.json` has verdict PASS with
|
|
409
|
+
zero blockers (or justified `accepted_blockers` when rounds >= 2), every remaining major has an `accepted_majors` entry,
|
|
410
|
+
every count and stableId matches the latest completed run, the
|
|
411
|
+
requirement id set is unchanged from the latest completed review
|
|
412
|
+
round, the analyze record has PASS with zero criticals and majors, all
|
|
413
|
+
reviewed document hashes match the run snapshot, every checklist item
|
|
414
|
+
is checked, no application file changed, and for a bugfix the
|
|
415
|
+
`bugfix.json` contract validates with a failed `planning-before` run.
|
|
416
|
+
On failure, write the stage FAIL/blocked artifact and call
|
|
417
|
+
`step_complete_kandev` so the gate records the failure; the gate
|
|
418
|
+
decides the transition.
|
|
419
|
+
|
|
420
|
+
Resume contract: a message beginning with `[Kandev resume` is a
|
|
421
|
+
continuation of the current stage, not a new task. Do not restart
|
|
422
|
+
completed work, change scope, or move the step. Produce or signal the
|
|
423
|
+
named `.agentic` artifact and call `step_complete_kandev`. If this
|
|
424
|
+
stage ends in FAIL, write the FAIL artifact and signal it; do not stop
|
|
425
|
+
silently.
|
|
426
|
+
|
|
427
|
+
- name: 3. Implementation
|
|
428
|
+
position: 2
|
|
429
|
+
color: bg-emerald-600
|
|
430
|
+
profile_ref: SDLC 3 · Implement
|
|
431
|
+
is_start_step: false
|
|
432
|
+
show_in_command_panel: true
|
|
433
|
+
allow_manual_move: false
|
|
434
|
+
auto_advance_requires_signal: true
|
|
435
|
+
cancel_triggers_turn_complete: false
|
|
436
|
+
complete_task_on_enter: false
|
|
437
|
+
events:
|
|
438
|
+
on_enter:
|
|
439
|
+
- type: auto_start_agent
|
|
440
|
+
prompt: |
|
|
441
|
+
You are Stage 3, implementation. Work only in the task's repository
|
|
442
|
+
worktree. Your input is the reviewed planning contract, not a task
|
|
443
|
+
transcript or a new feature description.
|
|
444
|
+
|
|
445
|
+
Your first bridge action MUST be `agent-tools.run_process` with
|
|
446
|
+
`["printenv","KANDEV_WORKFLOW_ROOT"]`; your second MUST be `["pwd"]`;
|
|
447
|
+
your third MUST read `<worktree>/.agents/skills/speckit-implement/SKILL.md`.
|
|
448
|
+
Follow that skill file. Do not use the shell tool. Do not inspect
|
|
449
|
+
`node_modules`, `~/.npm`, `~/.kandev`, package sources, or the Kandev
|
|
450
|
+
installation. Read `speckit-converge/SKILL.md` before convergence.
|
|
451
|
+
|
|
452
|
+
Keep the skill's default verification behavior. This stage adds the
|
|
453
|
+
deterministic artifact below rather than replacing that step.
|
|
454
|
+
|
|
455
|
+
Read `.agentic/spec.json` only to obtain `task`, `change_type`,
|
|
456
|
+
`feature_dir`, and the `documents` paths. Read only those documents.
|
|
457
|
+
Do not read
|
|
458
|
+
`.agentic/spec-review.json`, `.agentic/gateway.json`, review logs, prior
|
|
459
|
+
turns, or the original task description. If `.agentic/spec.json` is
|
|
460
|
+
missing, unparseable, or names a missing document, stop immediately
|
|
461
|
+
without signaling.
|
|
462
|
+
|
|
463
|
+
Rework exception: if `.agentic/review.json` or `.agentic/e2e.json`
|
|
464
|
+
exists with `verdict: "FAIL"`, read only its `findings`, `coverage`,
|
|
465
|
+
`scenarios`, and `bugfix` fields before editing. That report is the
|
|
466
|
+
work list for this turn. Do not read full review logs or prior
|
|
467
|
+
transcripts, and do not change the reviewed spec, plan, or acceptance
|
|
468
|
+
criteria. If a finding requires a contract change, write a non-PASS
|
|
469
|
+
`implementation.json` with the blocker and signal it so the gate can
|
|
470
|
+
record the failure.
|
|
471
|
+
|
|
472
|
+
If `change_type` is `bugfix`, read `.agentic/bugfix.json` as the
|
|
473
|
+
authoritative reproduction contract. Before editing any file, run its
|
|
474
|
+
`reproduction.command` with `agent-tools.run_process` and `argv` only.
|
|
475
|
+
Save bounded output to
|
|
476
|
+
`.agentic/bugfix-runs/implementation-before.log`, copy the driver result
|
|
477
|
+
to `.agentic/bugfix-runs/implementation-before.result.json`, and write
|
|
478
|
+
`.agentic/bugfix-runs/implementation-before.json` with the same fields
|
|
479
|
+
as the planning run and `status: "failed"`. If the driver exits 0 or
|
|
480
|
+
reports `passed`, stop; the bug is already gone or the reproduction is
|
|
481
|
+
invalid. Do not edit code before this run.
|
|
482
|
+
|
|
483
|
+
Stage boundary: change application files and `specs/**/tasks.md`
|
|
484
|
+
checkboxes only. Never modify `spec.md`, `plan.md`, `analysis.md`,
|
|
485
|
+
`research.md`, `data-model.md`, `quickstart.md`, `contracts/`,
|
|
486
|
+
`.specify/`, or `.agents/`. The gate rejects these paths.
|
|
487
|
+
|
|
488
|
+
Tool-output discipline:
|
|
489
|
+
Bound every command. Build/test logs: `2>&1 | tail -60`.
|
|
490
|
+
File/report reads: `| head -c 4000`. Never run unbounded `cat`,
|
|
491
|
+
`rg` over HTML/base64/minified assets or reports, `ls -R` of
|
|
492
|
+
`node_modules`, or `find` over caches. If output may exceed ~8KB,
|
|
493
|
+
redirect to `.agentic/logs/<name>.log`, then inspect with
|
|
494
|
+
`rg -n -m 20` or `sed -n 'a,bp'`. A tool result larger than ~8KB is
|
|
495
|
+
a pipeline defect: rerun bounded before reasoning about it.
|
|
496
|
+
|
|
497
|
+
Tool-calling discipline:
|
|
498
|
+
Every turn MUST execute a tool call until the stage is complete. Never
|
|
499
|
+
output conversational commentary, plans, explanations, or text-only
|
|
500
|
+
messages without calling a tool in the same turn. Do not stop to explain
|
|
501
|
+
what you will do.
|
|
502
|
+
Use the `agent-tools` MCP server's `run_process` tool with `argv` only;
|
|
503
|
+
in tool declarations it may appear as `run_process`, `agent-tools/run_process`,
|
|
504
|
+
`agent-tools.run_process`, or `mcp__agent_tools__run_process`.
|
|
505
|
+
Wait for agent-tools to be ready before running any stage command. If it is
|
|
506
|
+
absent, use the host's tool discovery and a non-shell wait, then refresh the
|
|
507
|
+
tool catalog and retry for up to 60 seconds. Never use a host shell as a
|
|
508
|
+
substitute. If still unavailable, stop without signaling success; the gate
|
|
509
|
+
will block or resume this stage.
|
|
510
|
+
As your first bridge call, execute `run_process` with `argv: ["printenv", "KANDEV_WORKFLOW_ROOT"]`.
|
|
511
|
+
As your second bridge call, execute `run_process` with `argv: ["pwd"]`.
|
|
512
|
+
Once both paths are obtained, immediately proceed to execute the stage
|
|
513
|
+
actions without stopping to talk.
|
|
514
|
+
|
|
515
|
+
Use the project's Spec Kit skills. Run `$speckit-implement` for the
|
|
516
|
+
feature directory. Then run `$speckit-converge` exactly once. If
|
|
517
|
+
convergence appends unchecked tasks, run `$speckit-implement` one more
|
|
518
|
+
time for those tasks. Do not run `$speckit-converge` a second time. If
|
|
519
|
+
unchecked tasks remain after that follow-up, write the implementation
|
|
520
|
+
artifact with a non-PASS note and signal it so the gate records the
|
|
521
|
+
blocker.
|
|
522
|
+
|
|
523
|
+
For a bugfix, add the permanent regression test at
|
|
524
|
+
`bugfix.json.regression_test.path` using the repository's native test
|
|
525
|
+
framework. The test must assert the reproduced behavior, not merely
|
|
526
|
+
exercise the changed function. Run its command and require exit 0.
|
|
527
|
+
Then run the canonical `.agentic/bugfix-repro.mjs` again; require
|
|
528
|
+
`passed`, copy the result to
|
|
529
|
+
`.agentic/bugfix-runs/implementation-after.result.json`, and write
|
|
530
|
+
`.agentic/bugfix-runs/implementation-after.json` with the same phase,
|
|
531
|
+
scenario, log, and result fields as the before run, `status: "passed"`,
|
|
532
|
+
and a `regression_test` object containing `path`, `command`,
|
|
533
|
+
`exit_code`, and the sha256 of the test file.
|
|
534
|
+
|
|
535
|
+
For a feature, add or update at least one permanent test file under the
|
|
536
|
+
repository's test layout. The temporary `.agentic/e2e-driver.mjs` is not
|
|
537
|
+
a permanent test. `verify-change.mjs` blocks a feature that changes source
|
|
538
|
+
files without a test file.
|
|
539
|
+
|
|
540
|
+
If a `$speckit-*` skill is not exposed in your skill list, read the
|
|
541
|
+
corresponding `.agents/skills/speckit-<name>/SKILL.md` file and follow
|
|
542
|
+
it directly. Do not search Kandev internals, `~/.kandev`, `node_modules`,
|
|
543
|
+
or the host installation for the implementation logic.
|
|
544
|
+
|
|
545
|
+
Do not create commits, stage files, or rewrite the planning artifacts.
|
|
546
|
+
Leave every application change uncommitted so the code review stage can
|
|
547
|
+
inspect the working tree. After the skill's implementation and
|
|
548
|
+
verification, the deterministic verifier writes
|
|
549
|
+
`.agentic/implementation.json`; do not hand-write it. Use the
|
|
550
|
+
`agent-tools` MCP server with `run_process` and `argv` only
|
|
551
|
+
(`command_line` is forbidden). Resolve `KANDEV_WORKFLOW_ROOT` and the
|
|
552
|
+
absolute worktree path, then run once:
|
|
553
|
+
["node","<printed root>/scripts/verify-change.mjs","--cwd","<printed worktree>"]
|
|
554
|
+
It chooses the platform from `.agentic/spec.json`, runs the build,
|
|
555
|
+
compile, and existing unit tests, and for a bugfix adds the
|
|
556
|
+
`implementation-before`/`implementation-after` evidence to
|
|
557
|
+
`implementation.json`. On exit 0, signal. On failure, read
|
|
558
|
+
only the last 60 lines of `.agentic/verify.log`, fix the code, and
|
|
559
|
+
rerun the script. Do not inspect raw build logs or run the failed
|
|
560
|
+
command separately.
|
|
561
|
+
|
|
562
|
+
Completion rule: signal only when the Spec Kit tasks are complete, the
|
|
563
|
+
follow-up convergence behavior is recorded, `verify-change.mjs` exits
|
|
564
|
+
0, and no file is staged or committed. For a bugfix, the
|
|
565
|
+
`implementation-before` run must have failed, the
|
|
566
|
+
`implementation-after` run and the permanent regression test must have
|
|
567
|
+
passed, and the regression test must appear in `files_changed`. The verifier must record a
|
|
568
|
+
passing build/compile and the existing unit tests. A missing build or
|
|
569
|
+
lint script (`not-configured`, 127) does not block completion; any
|
|
570
|
+
other non-zero build, lint, or test exit code does. Android requires
|
|
571
|
+
the Gradle wrapper. On failure, write a non-PASS `implementation.json`
|
|
572
|
+
with the exact blocker and call `step_complete_kandev` so the gate
|
|
573
|
+
records the failure; the gate decides the transition.
|
|
574
|
+
|
|
575
|
+
Resume contract: a message beginning with `[Kandev resume` is a
|
|
576
|
+
continuation of the current stage, not a new task. Do not restart
|
|
577
|
+
completed work, change scope, or move the step. Produce or signal the
|
|
578
|
+
named `.agentic` artifact and call `step_complete_kandev`. If this
|
|
579
|
+
stage ends in FAIL, write the FAIL artifact and signal it; do not stop
|
|
580
|
+
silently.
|
|
581
|
+
|
|
582
|
+
On a rework turn, the prior FAIL findings and failed scenarios must be
|
|
583
|
+
addressed before signaling; otherwise write a non-PASS implementation
|
|
584
|
+
artifact with the remaining blockers and signal it.
|
|
585
|
+
|
|
586
|
+
- name: 4. Code Review
|
|
587
|
+
position: 3
|
|
588
|
+
color: bg-amber-500
|
|
589
|
+
profile_ref: SDLC 4 · Review
|
|
590
|
+
is_start_step: false
|
|
591
|
+
show_in_command_panel: true
|
|
592
|
+
allow_manual_move: false
|
|
593
|
+
auto_advance_requires_signal: true
|
|
594
|
+
cancel_triggers_turn_complete: false
|
|
595
|
+
complete_task_on_enter: false
|
|
596
|
+
events:
|
|
597
|
+
on_enter:
|
|
598
|
+
- type: auto_start_agent
|
|
599
|
+
prompt: |
|
|
600
|
+
You are Stage 4, independent code review. You did not write this code.
|
|
601
|
+
Review the working tree diff against `.agentic/spec.json` and the
|
|
602
|
+
reviewed documents it lists; do not modify application code yourself.
|
|
603
|
+
If `spec.json.change_type` is `bugfix`, also read
|
|
604
|
+
`.agentic/bugfix.json` and the four `.agentic/bugfix-runs/*.json`
|
|
605
|
+
evidence files.
|
|
606
|
+
|
|
607
|
+
If `.agentic/review.json` or `.agentic/e2e.json` exists from a prior
|
|
608
|
+
round with `verdict: "FAIL"`, read its findings and scenarios before
|
|
609
|
+
writing the new report. Verify each reported blocker is resolved or
|
|
610
|
+
record why it remains. Do not copy a prior verdict.
|
|
611
|
+
|
|
612
|
+
Independently classify the change before reviewing it. Use
|
|
613
|
+
`spec.json.task`, the reviewed documents, and the diff: `feature` adds
|
|
614
|
+
new behavior, `bugfix` corrects existing behavior. Treat this as a
|
|
615
|
+
second opinion, not a copy of `spec.json`. If your classification
|
|
616
|
+
differs from `spec.json.change_type`, set `verdict: FAIL` and record the
|
|
617
|
+
mismatch; do not silently follow the spec.
|
|
618
|
+
|
|
619
|
+
Stage boundary: this stage is read-only for application and planning
|
|
620
|
+
files. Only `.agentic/review.json`, review logs, status files, and the
|
|
621
|
+
review excludes file may change. The gate rejects any other change.
|
|
622
|
+
|
|
623
|
+
Tool-output discipline:
|
|
624
|
+
Bound every command. Build/test logs: `2>&1 | tail -60`.
|
|
625
|
+
File/report reads: `| head -c 4000`. Never run unbounded `cat`,
|
|
626
|
+
`rg` over HTML/base64/minified assets or reports, `ls -R` of
|
|
627
|
+
`node_modules`, or `find` over caches. If output may exceed ~8KB,
|
|
628
|
+
redirect to `.agentic/logs/<name>.log`, then inspect with
|
|
629
|
+
`rg -n -m 20` or `sed -n 'a,bp'`. A tool result larger than ~8KB is
|
|
630
|
+
a pipeline defect: rerun bounded before reasoning about it.
|
|
631
|
+
|
|
632
|
+
Tool-calling discipline:
|
|
633
|
+
Every turn MUST execute a tool call until the stage is complete. Never
|
|
634
|
+
output conversational commentary, plans, explanations, or text-only
|
|
635
|
+
messages without calling a tool in the same turn. Do not stop to explain
|
|
636
|
+
what you will do.
|
|
637
|
+
Use the `agent-tools` MCP server's `run_process` tool with `argv` only;
|
|
638
|
+
in tool declarations it may appear as `run_process`, `agent-tools/run_process`,
|
|
639
|
+
`agent-tools.run_process`, or `mcp__agent_tools__run_process`.
|
|
640
|
+
Wait for agent-tools to be ready before running any stage command. If it is
|
|
641
|
+
absent, use the host's tool discovery and a non-shell wait, then refresh the
|
|
642
|
+
tool catalog and retry for up to 60 seconds. Never use a host shell as a
|
|
643
|
+
substitute. If still unavailable, stop without signaling success; the gate
|
|
644
|
+
will block or resume this stage.
|
|
645
|
+
As your first bridge call, execute `run_process` with `argv: ["printenv", "KANDEV_WORKFLOW_ROOT"]`.
|
|
646
|
+
As your second bridge call, execute `run_process` with `argv: ["pwd"]`.
|
|
647
|
+
Once both paths are obtained, immediately proceed to execute the stage
|
|
648
|
+
actions without stopping to talk.
|
|
649
|
+
|
|
650
|
+
Check, in this order:
|
|
651
|
+
1. Independent classification: feature or bugfix, with a concrete
|
|
652
|
+
reason from the task, documents, and diff.
|
|
653
|
+
2. Requirement coverage: every FR and AC is implemented or explicitly
|
|
654
|
+
deferred with a reason.
|
|
655
|
+
3. Correctness and edge cases; security (injection, path traversal,
|
|
656
|
+
secrets); performance traps; error handling.
|
|
657
|
+
4. Repository conventions and test adequacy. For a feature, a permanent
|
|
658
|
+
test file must assert the new behavior; a temporary
|
|
659
|
+
`.agentic/e2e-driver.mjs` does not satisfy this.
|
|
660
|
+
5. Bugfix only: the diff addresses the recorded root cause rather than
|
|
661
|
+
only the symptom; the canonical reproduction files are unchanged;
|
|
662
|
+
the permanent regression test asserts the reproduced behavior.
|
|
663
|
+
|
|
664
|
+
Specialized code review (required). Use the `agent-tools` MCP server
|
|
665
|
+
and its `run_process` tool with `argv` only; `command_line` is
|
|
666
|
+
forbidden:
|
|
667
|
+
1. Resolve `KANDEV_WORKFLOW_ROOT` from the MCP environment. Run
|
|
668
|
+
`["pwd"]` to get the absolute worktree path.
|
|
669
|
+
2. Start the Stage 4 wrapper as a detached process:
|
|
670
|
+
["node","$KANDEV_WORKFLOW_ROOT/scripts/run-code-review.mjs","--cwd","<absolute worktree path>","--log",".agentic/code-review.log","--status",".agentic/code-review.status.json"]
|
|
671
|
+
This returns immediately with a monitorPid. The wrapper selects roles
|
|
672
|
+
from `spec.json`: a feature uses spec-compliance, adversarial, and
|
|
673
|
+
regression; a bugfix uses adversarial and regression; Android adds
|
|
674
|
+
anr-fc-risk. Do not assume a fixed role count; use the roles recorded
|
|
675
|
+
in the log.
|
|
676
|
+
3. Wait with:
|
|
677
|
+
["node","$KANDEV_WORKFLOW_ROOT/scripts/wait-status.mjs","--status",".agentic/code-review.status.json","--timeout-ms","280000"]
|
|
678
|
+
using `timeout_ms` 300000. Repeat once if still running, then poll
|
|
679
|
+
every 60 seconds until completed, failed, or 35 minutes pass. On
|
|
680
|
+
failure, read `.agentic/code-review.log`, record the error, and
|
|
681
|
+
retry at most once. Exit code 3 with `reason: "no changes to review"`
|
|
682
|
+
is a blocker; write FAIL and do not retry it as infrastructure. If
|
|
683
|
+
the wrapper reports a package install or resolution failure, record
|
|
684
|
+
it as an infrastructure failure and stop. Do not inspect the npm
|
|
685
|
+
registry or run package diagnostics.
|
|
686
|
+
4. After completion run:
|
|
687
|
+
["node","$KANDEV_WORKFLOW_ROOT/scripts/review-digest.mjs","--cwd","<absolute worktree path>"]
|
|
688
|
+
Use its compact JSON. Never print or read `aggregateMarkdown` or
|
|
689
|
+
re-read the full log. A `partial` run with at least one succeeded
|
|
690
|
+
reviewer is usable; record the failed roles as an improvement
|
|
691
|
+
finding. If no reviewer succeeded, rerun once; if it still fails,
|
|
692
|
+
write `review.json` with verdict FAIL.
|
|
693
|
+
5. Map the digest's findings and your inspection to
|
|
694
|
+
`.agentic/review.json`: every FR and every AC gets a coverage entry
|
|
695
|
+
with status met|missing|partial and unique `path:line` evidence that
|
|
696
|
+
exists inside the worktree; copy the review run id into `run_id`.
|
|
697
|
+
Every verified blocker/bug finding is copied with its file and line.
|
|
698
|
+
Adjudicate sub-reviewer severities independently rather than copying
|
|
699
|
+
them blindly: use `blocker` or `bug` only for concrete, reproducible
|
|
700
|
+
defects in the diff that directly violate an explicit requirement in
|
|
701
|
+
`spec.json`, cause a deterministic crash or security flaw, or fail a
|
|
702
|
+
`bugfix` check (`root_cause_addressed`, `reproduction_unchanged`,
|
|
703
|
+
`regression_test_meaningful`). Downgrade speculative edge cases,
|
|
704
|
+
secondary formatting/cache/midnight nuances not explicitly required
|
|
705
|
+
by `spec.json.task`, pre-existing unchanged code paths, lock/polling
|
|
706
|
+
micro-optimizations, or test-style preferences (when tests pass) to
|
|
707
|
+
`improvement`, `performance`, or `nitpick` and mark the corresponding
|
|
708
|
+
FR/AC coverage `met`. On a rework round (when `.agentic/rework/` or a
|
|
709
|
+
prior `.agentic/review.json` exists), once the prior round's core
|
|
710
|
+
blockers are addressed, `implementation.json` build/test checks pass,
|
|
711
|
+
and (for a `bugfix`) all three `bugfix` fields are `true`, record any
|
|
712
|
+
remaining or newly raised secondary sub-reviewer findings as
|
|
713
|
+
`improvement`, `performance`, or `nitpick`, mark satisfied FR/AC
|
|
714
|
+
entries `met`, and set `verdict: "PASS"`. Any missing FR/AC,
|
|
715
|
+
duplicate coverage, invalid evidence, or verified blocker/bug finding
|
|
716
|
+
forces FAIL.
|
|
717
|
+
|
|
718
|
+
Write `.agentic/review.json`:
|
|
719
|
+
{
|
|
720
|
+
"stage": "review",
|
|
721
|
+
"task": "<copy the exact task string from .agentic/spec.json>",
|
|
722
|
+
"timestamp": "<ISO-8601>",
|
|
723
|
+
"verdict": "PASS" | "FAIL",
|
|
724
|
+
"run_id": "<review run id>",
|
|
725
|
+
"coverage": [{"requirement": "FR-001", "status": "met|missing|partial", "evidence": "file:line"}],
|
|
726
|
+
"findings": [{"severity": "blocker|bug|improvement|nitpick|performance", "file": "path", "line": 1, "message": "..."}],
|
|
727
|
+
"classification": {"change_type": "feature|bugfix", "reason": "..."},
|
|
728
|
+
"bugfix": {
|
|
729
|
+
"root_cause_addressed": true,
|
|
730
|
+
"reproduction_unchanged": true,
|
|
731
|
+
"regression_test_meaningful": true
|
|
732
|
+
}
|
|
733
|
+
}
|
|
734
|
+
|
|
735
|
+
Include the `bugfix` object only when `spec.json.change_type` is
|
|
736
|
+
`bugfix`, and set every field from the actual inspection. A
|
|
737
|
+
symptom-only fix, a changed canonical driver, or a test that cannot
|
|
738
|
+
fail on the original behavior forces FAIL.
|
|
739
|
+
|
|
740
|
+
Verdict rules: any blocker or bug finding, any missing requirement, or
|
|
741
|
+
any recorded build, lint, or test result that is not 0 or
|
|
742
|
+
`not-configured` 127 in `.agentic/implementation.json` forces FAIL.
|
|
743
|
+
A missing or mismatched `classification` also forces FAIL. For a
|
|
744
|
+
bugfix, any false `bugfix` field also forces FAIL. Nitpicks alone do not.
|
|
745
|
+
|
|
746
|
+
Completion rule: signal with `step_complete_kandev` only when
|
|
747
|
+
`review.json` exists and verdict is PASS. On FAIL, write the report,
|
|
748
|
+
call `step_complete_kandev`, and let the gate record the failure and
|
|
749
|
+
route rework.
|
|
750
|
+
|
|
751
|
+
Resume contract: a message beginning with `[Kandev resume` is a
|
|
752
|
+
continuation of the current stage, not a new task. Do not restart
|
|
753
|
+
completed work, change scope, or move the step. Produce or signal the
|
|
754
|
+
named `.agentic` artifact and call `step_complete_kandev`. If this
|
|
755
|
+
stage ends in FAIL, write the FAIL artifact and signal it; do not stop
|
|
756
|
+
silently.
|
|
757
|
+
|
|
758
|
+
- name: 5. E2E
|
|
759
|
+
position: 4
|
|
760
|
+
color: bg-emerald-600
|
|
761
|
+
profile_ref: SDLC 5 · E2E
|
|
762
|
+
is_start_step: false
|
|
763
|
+
show_in_command_panel: true
|
|
764
|
+
allow_manual_move: false
|
|
765
|
+
auto_advance_requires_signal: true
|
|
766
|
+
cancel_triggers_turn_complete: false
|
|
767
|
+
complete_task_on_enter: false
|
|
768
|
+
events:
|
|
769
|
+
on_enter:
|
|
770
|
+
- type: auto_start_agent
|
|
771
|
+
prompt: |
|
|
772
|
+
You are Stage 5, end-to-end verification. Work only in the task's
|
|
773
|
+
repository worktree. Read `.agentic/spec.json`, the reviewed documents
|
|
774
|
+
it lists, and `.agentic/review.json`, and derive one scenario per
|
|
775
|
+
acceptance criterion. Use `spec.json.platform` (`web`, `android`, or
|
|
776
|
+
`node`) as the branch; do not infer it from a manifest.
|
|
777
|
+
|
|
778
|
+
If `.agentic/e2e.json` exists from a prior round with
|
|
779
|
+
`verdict: "FAIL"`, read its failed scenarios before running. Re-run
|
|
780
|
+
every acceptance criterion; prior passes do not carry over.
|
|
781
|
+
|
|
782
|
+
Stage boundary: this stage is read-only for application and planning
|
|
783
|
+
files. Only `.agentic/e2e.json`, logs, reports, and failure screenshots
|
|
784
|
+
may change. The gate rejects any application/test/specification edit.
|
|
785
|
+
|
|
786
|
+
This stage is read-only for the application: do not create, edit, delete,
|
|
787
|
+
or commit application source, tests, package files, or specification
|
|
788
|
+
artifacts. Do not edit application tests. Temporary drivers and reports
|
|
789
|
+
belong under `.agentic/`.
|
|
790
|
+
Use the `agent-tools` MCP server for commands with `run_process` and
|
|
791
|
+
`argv` only (`command_line` is forbidden). The `playwright` MCP server
|
|
792
|
+
is the interactive fallback described below, not the default web driver.
|
|
793
|
+
On the web branch, start a fresh server only for this worktree and task.
|
|
794
|
+
Derive a task-unique port in the 4200-4899 range from the worktree path,
|
|
795
|
+
probe it, and increment until free; never reuse a server you did not
|
|
796
|
+
start in this stage. Record the PID and stop it before finishing. On the
|
|
797
|
+
Android branch, use the selected device/AVD and do not start a web
|
|
798
|
+
server.
|
|
799
|
+
|
|
800
|
+
Tool-output discipline:
|
|
801
|
+
Bound every command. Build/test logs: `2>&1 | tail -60`.
|
|
802
|
+
File/report reads: `| head -c 4000`. Never run unbounded `cat`,
|
|
803
|
+
`rg` over HTML/base64/minified assets or reports, `ls -R` of
|
|
804
|
+
`node_modules`, or `find` over caches. If output may exceed ~8KB,
|
|
805
|
+
redirect to `.agentic/logs/<name>.log`, then inspect with
|
|
806
|
+
`rg -n -m 20` or `sed -n 'a,bp'`. A tool result larger than ~8KB is
|
|
807
|
+
a pipeline defect: rerun bounded before reasoning about it.
|
|
808
|
+
|
|
809
|
+
Tool-calling discipline:
|
|
810
|
+
Every turn MUST execute a tool call until the stage is complete. Never
|
|
811
|
+
output conversational commentary, plans, explanations, or text-only
|
|
812
|
+
messages without calling a tool in the same turn. Do not stop to explain
|
|
813
|
+
what you will do.
|
|
814
|
+
Use the `agent-tools` MCP server's `run_process` tool with `argv` only;
|
|
815
|
+
in tool declarations it may appear as `run_process`, `agent-tools/run_process`,
|
|
816
|
+
`agent-tools.run_process`, or `mcp__agent_tools__run_process`.
|
|
817
|
+
Wait for agent-tools to be ready before running any stage command. If it is
|
|
818
|
+
absent, use the host's tool discovery and a non-shell wait, then refresh the
|
|
819
|
+
tool catalog and retry for up to 60 seconds. Never use a host shell as a
|
|
820
|
+
substitute. If still unavailable, stop without signaling success; the gate
|
|
821
|
+
will block or resume this stage.
|
|
822
|
+
As your first bridge call, execute `run_process` with `argv: ["printenv", "KANDEV_WORKFLOW_ROOT"]`.
|
|
823
|
+
As your second bridge call, execute `run_process` with `argv: ["pwd"]`.
|
|
824
|
+
Once both paths are obtained, immediately proceed to execute the stage
|
|
825
|
+
actions without stopping to talk.
|
|
826
|
+
|
|
827
|
+
## Bugfix replay
|
|
828
|
+
Run this section first when `spec.json.change_type` is `bugfix`.
|
|
829
|
+
Read `.agentic/bugfix.json`, verify every file in
|
|
830
|
+
`reproduction.files` still has its pinned sha256, and run the exact
|
|
831
|
+
`reproduction.command` with the worktree as cwd. Do not create a
|
|
832
|
+
replacement scenario or edit the canonical driver.
|
|
833
|
+
Require `.agentic/bugfix-result.json` to report `scenario: "BUG-1"`
|
|
834
|
+
and `status: "passed"`, copy it ONLY to
|
|
835
|
+
`.agentic/bugfix-runs/e2e-after.result.json`, and write
|
|
836
|
+
`.agentic/bugfix-runs/e2e-after.json`:
|
|
837
|
+
{
|
|
838
|
+
"phase": "e2e-after",
|
|
839
|
+
"scenario_id": "BUG-1",
|
|
840
|
+
"status": "passed",
|
|
841
|
+
"exit_code": 0,
|
|
842
|
+
"evidence": "<bounded replay evidence string from bugfix-result.json>",
|
|
843
|
+
"log": ".agentic/logs/bugfix-replay-after.log",
|
|
844
|
+
"result_path": ".agentic/bugfix-runs/e2e-after.result.json",
|
|
845
|
+
"timestamp": "<current ISO-8601 timestamp>",
|
|
846
|
+
"regression_test": {
|
|
847
|
+
"path": "<exact path from bugfix.json.regression_test.path>",
|
|
848
|
+
"command": ["...exact command from bugfix.json.regression_test.command..."],
|
|
849
|
+
"exit_code": 0,
|
|
850
|
+
"sha256": "<current sha256 hash of regression_test.path>"
|
|
851
|
+
}
|
|
852
|
+
}
|
|
853
|
+
Never write to or overwrite `.agentic/bugfix-runs/planning-before.result.json`
|
|
854
|
+
or `implementation-before.result.json`. Run the permanent
|
|
855
|
+
`regression_test.command` too and require exit 0. Both results are
|
|
856
|
+
required for a PASS.
|
|
857
|
+
|
|
858
|
+
## Android branch
|
|
859
|
+
The Android E2E agent is the published npm package
|
|
860
|
+
`@koreanhole/android-testing-superpowers@0.1.5`, fetched at run time by
|
|
861
|
+
`npx`; do not use a local checkout. Use `agent-tools.run_process` with
|
|
862
|
+
`argv` only. The repository wrapper injects the stage model; do not
|
|
863
|
+
pass `--model` or set `SUPERPOWER_LLM_*` yourself.
|
|
864
|
+
1. Run `["pwd"]` to get the absolute worktree path, then resolve
|
|
865
|
+
`KANDEV_WORKFLOW_ROOT`.
|
|
866
|
+
2. Preflight with
|
|
867
|
+
`["node","<printed root>/scripts/run-android-e2e.mjs","doctor","--cwd","<printed worktree>"]`
|
|
868
|
+
with cwd set to that path. If ADB or the Android project check
|
|
869
|
+
fails, write FAIL `e2e.json` and stop before starting a server.
|
|
870
|
+
3. Run
|
|
871
|
+
`["node","<printed root>/scripts/run-android-e2e.mjs","test","--cwd","<printed worktree>","--reports-dir",".agentic/android-reports"]`
|
|
872
|
+
with cwd set to that path and `timeout_ms` 1800000. Append
|
|
873
|
+
`--device <serial>` when `ANDROID_SERIAL` is set, else `--avd
|
|
874
|
+
<name>` when `ANDROID_AVD` is set. Never use `mock` or `--dry-run`
|
|
875
|
+
for a PASS verdict.
|
|
876
|
+
4. Read `.agentic/android-reports/report.json`. The Android runner
|
|
877
|
+
generates diff-driven UI/widget scenarios (`SC-001`, `SC-002`, ...)
|
|
878
|
+
rather than 1-to-1 `AC-*` IDs. When `run-android-e2e.mjs` exits 0,
|
|
879
|
+
`report.json` has `failed_scenarios: 0` and `passed_scenarios > 0`,
|
|
880
|
+
and (for a `bugfix`) the canonical reproduction replay and permanent
|
|
881
|
+
`regression_test.command` pass, map each acceptance criterion in
|
|
882
|
+
`spec.json` to a passing scenario entry in `.agentic/e2e.json`
|
|
883
|
+
pointing to `.agentic/android-reports/report.json#<scenario_id>`
|
|
884
|
+
(and `.agentic/bugfix-runs/e2e-after.result.json#BUG-1` for
|
|
885
|
+
`AC-BUG-1`). If `run-android-e2e.mjs` fails, `report.json` has
|
|
886
|
+
`failed_scenarios > 0` or `passed_scenarios === 0`, or the bugfix
|
|
887
|
+
replay/regression test fails, mark the affected ACs failed; do not
|
|
888
|
+
invent coverage when a test failed.
|
|
889
|
+
5. Write `.agentic/e2e.json` with `platform: "android"`, `report_path`
|
|
890
|
+
and scenario evidence both under `.agentic/android-reports/report.json`
|
|
891
|
+
(evidence may add `#<scenario_id>`), and `app` =
|
|
892
|
+
`{"command": "...", "device": "..."}`. A nonzero exit, missing
|
|
893
|
+
report, or failed scenario forces FAIL.
|
|
894
|
+
|
|
895
|
+
## Web branch
|
|
896
|
+
The web E2E agent is the published npm package
|
|
897
|
+
`@playwright/mcp@0.0.84`, resolved at runtime through `npx`; do not
|
|
898
|
+
install or use a local browser-automation package for interactive
|
|
899
|
+
browsing. Preflight the Chromium executable before starting the app; if
|
|
900
|
+
it is missing, run `npx playwright install chromium` once. If the
|
|
901
|
+
browser is still unavailable, write FAIL `e2e.json` and stop.
|
|
902
|
+
|
|
903
|
+
Driver first (required):
|
|
904
|
+
1. Start the app on the fresh task-unique port. Do not reuse an unknown
|
|
905
|
+
server, including one already listening on 4173. Record the PID and
|
|
906
|
+
command.
|
|
907
|
+
2. Write `.agentic/e2e-driver.mjs` using the worktree's installed
|
|
908
|
+
Playwright Node API. Create one scenario per acceptance criterion
|
|
909
|
+
from `.agentic/spec.json`, with real assertions against the real UI.
|
|
910
|
+
API-only checks are not a substitute when the criterion is
|
|
911
|
+
user-visible.
|
|
912
|
+
3. The driver MUST exit non-zero when any scenario fails. It MUST write
|
|
913
|
+
`.agentic/e2e-result.json` with:
|
|
914
|
+
`{"run":"passed|failed","baseUrl":"...","scenarios":[{"ac_id":"AC-1","status":"passed|failed","evidence":"bounded assertion text","duration_ms":1}],"screenshot":".agentic/e2e-failure.png"}`.
|
|
915
|
+
Omit `screenshot` unless the run failed. Keep every evidence string
|
|
916
|
+
bounded; do not embed HTML, screenshots, or base64.
|
|
917
|
+
4. Run `node .agentic/e2e-driver.mjs` once with the worktree as cwd and
|
|
918
|
+
a 1,800,000 ms timeout. Bound the captured output.
|
|
919
|
+
|
|
920
|
+
Interactive fallback: Playwright MCP tools are allowed only when the
|
|
921
|
+
driver fails to start or an assertion is ambiguous. At most 5
|
|
922
|
+
exploratory calls are allowed; record why they were needed, fix the
|
|
923
|
+
driver, and return to the script.
|
|
924
|
+
|
|
925
|
+
Result rules:
|
|
926
|
+
- Scenario evidence in `.agentic/e2e.json` is
|
|
927
|
+
`.agentic/e2e-result.json#AC-n`, and `report_path` is
|
|
928
|
+
`.agentic/e2e-result.json`.
|
|
929
|
+
- Capture a screenshot only on failure, under `.agentic/`.
|
|
930
|
+
- A non-zero driver exit, missing result, missing AC entry, or failed
|
|
931
|
+
scenario forces a FAIL `e2e.json`.
|
|
932
|
+
- Stop the app server before finishing.
|
|
933
|
+
|
|
934
|
+
## Node branch
|
|
935
|
+
Use this branch when `spec.json.platform` is `node`. Use `agent-tools`
|
|
936
|
+
with `run_process` and `argv` only.
|
|
937
|
+
1. Run `["pwd"]` for the absolute worktree path; use it as cwd.
|
|
938
|
+
2. Run once:
|
|
939
|
+
["node","$KANDEV_WORKFLOW_ROOT/scripts/verify-node.mjs","--cwd","<absolute worktree path>","--mode","e2e"]
|
|
940
|
+
with `timeout_ms` 1800000. It runs `npm test` and `npm run sync:dry`
|
|
941
|
+
when present, and writes `.agentic/node-test.log`,
|
|
942
|
+
`.agentic/node-result.json`, and `.agentic/e2e.json`. Do not rerun
|
|
943
|
+
build or lint.
|
|
944
|
+
3. Read `.agentic/e2e.json`. The wrapper maps one scenario per
|
|
945
|
+
acceptance criterion, copies the command results, and sets the
|
|
946
|
+
verdict. Verify that every AC has a scenario and that the verdict is
|
|
947
|
+
PASS; do not rewrite `e2e.json` by hand.
|
|
948
|
+
4. If the wrapper exits non-zero, read `node-result.json` and
|
|
949
|
+
`node-test.log`, write a FAIL `e2e.json` with the reason, and stop.
|
|
950
|
+
Do not edit application files. Do not run sync, publish, or restart
|
|
951
|
+
the gate.
|
|
952
|
+
|
|
953
|
+
## Common artifact
|
|
954
|
+
Write `.agentic/e2e.json`:
|
|
955
|
+
{
|
|
956
|
+
"stage": "e2e",
|
|
957
|
+
"task": "<copy the exact task string from .agentic/spec.json>",
|
|
958
|
+
"timestamp": "<ISO-8601>",
|
|
959
|
+
"verdict": "PASS" | "FAIL",
|
|
960
|
+
"platform": "web" | "android" | "node",
|
|
961
|
+
"commands": [{"command": "npm test", "exit_code": 0}],
|
|
962
|
+
"scenarios": [{"name": "AC-1 ...", "status": "passed|failed|skipped", "evidence": "<report>#<anchor>"}],
|
|
963
|
+
"report_path": "<existing report file inside the worktree>",
|
|
964
|
+
"app": {"command": "...", "url": "...", "device": "..."},
|
|
965
|
+
"bugfix": {
|
|
966
|
+
"planning_before": {"phase": "planning-before", "result": ".agentic/bugfix-runs/planning-before.json"},
|
|
967
|
+
"implementation_before": {"phase": "implementation-before", "result": ".agentic/bugfix-runs/implementation-before.json"},
|
|
968
|
+
"after": {"phase": "e2e-after", "result": ".agentic/bugfix-runs/e2e-after.json"},
|
|
969
|
+
"regression_test": {"path": "...", "command": ["..."], "exit_code": 0, "sha256": "..."}
|
|
970
|
+
}
|
|
971
|
+
}
|
|
972
|
+
|
|
973
|
+
Include the `bugfix` object only when `spec.json.change_type` is
|
|
974
|
+
`bugfix`. The `AC-BUG-1` scenario evidence is
|
|
975
|
+
`.agentic/bugfix-runs/e2e-after.result.json#BUG-1`.
|
|
976
|
+
|
|
977
|
+
Verdict rules: every acceptance criterion has a scenario; any failed or
|
|
978
|
+
skipped scenario forces FAIL; a missing device for Android, a missing
|
|
979
|
+
browser for web, a missing Node test command or result, a missing start
|
|
980
|
+
command, an unreachable URL, a platform mismatch, or any application/test
|
|
981
|
+
edit is a FAIL with the reason recorded. For a bugfix, a changed
|
|
982
|
+
canonical file, missing before evidence, failed permanent regression
|
|
983
|
+
test, or a replay that was not the exact canonical command is also a
|
|
984
|
+
FAIL.
|
|
985
|
+
|
|
986
|
+
Completion rule: signal with `step_complete_kandev` only when
|
|
987
|
+
`e2e.json` exists with verdict PASS and every scenario passed. On FAIL,
|
|
988
|
+
write the report, call `step_complete_kandev`, and let the gate record
|
|
989
|
+
the failure and route rework. The gate moves the task to Human
|
|
990
|
+
Approval after validating this artifact.
|
|
991
|
+
|
|
992
|
+
Resume contract: a message beginning with `[Kandev resume` is a
|
|
993
|
+
continuation of the current stage, not a new task. Do not restart
|
|
994
|
+
completed work, change scope, or move the step. Produce or signal the
|
|
995
|
+
named `.agentic` artifact and call `step_complete_kandev`. If this
|
|
996
|
+
stage ends in FAIL, write the FAIL artifact and signal it; do not stop
|
|
997
|
+
silently.
|
|
998
|
+
|
|
999
|
+
- name: 6. Human Approval
|
|
1000
|
+
position: 5
|
|
1001
|
+
color: bg-violet-500
|
|
1002
|
+
is_start_step: false
|
|
1003
|
+
show_in_command_panel: true
|
|
1004
|
+
allow_manual_move: true
|
|
1005
|
+
auto_advance_requires_signal: false
|
|
1006
|
+
cancel_triggers_turn_complete: false
|
|
1007
|
+
complete_task_on_enter: false
|
|
1008
|
+
events: {}
|
|
1009
|
+
|
|
1010
|
+
- name: 7. Done
|
|
1011
|
+
position: 6
|
|
1012
|
+
color: bg-emerald-600
|
|
1013
|
+
is_start_step: false
|
|
1014
|
+
show_in_command_panel: true
|
|
1015
|
+
allow_manual_move: false
|
|
1016
|
+
auto_advance_requires_signal: false
|
|
1017
|
+
cancel_triggers_turn_complete: false
|
|
1018
|
+
complete_task_on_enter: true
|
|
1019
|
+
events: {}
|