@pushpalsdev/cli 1.0.32 → 1.0.33
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/dist/pushpals-cli.js +4 -4
- package/monitor-ui/+not-found.html +1 -1
- package/monitor-ui/_expo/static/js/web/{entry-275c5f7972e2d2f4f0422fe2213a7f89.js → entry-5e6db7139bc13703a24f952bd64faf4c.js} +2 -2
- package/monitor-ui/_sitemap.html +1 -1
- package/monitor-ui/index.html +1 -1
- package/monitor-ui/modal.html +1 -1
- package/package.json +1 -1
- package/runtime/prompts/localbuddy/localbuddy_planner_git_diff_section.md +0 -1
- package/runtime/prompts/localbuddy/localbuddy_planner_git_status_section.md +0 -1
- package/runtime/prompts/localbuddy/localbuddy_planner_output_contract.md +1 -0
- package/runtime/prompts/remotebuddy/autonomy_ideation_system_prompt.md +31 -30
- package/runtime/prompts/remotebuddy/autonomy_scoring_system_prompt.md +2 -2
- package/runtime/prompts/remotebuddy/context_packer_user_prompt.md +1 -0
- package/runtime/prompts/remotebuddy/remotebuddy_system_prompt.md +1 -0
- package/runtime/prompts/review_agent/review_prompt_template.md +1 -0
- package/runtime/prompts/review_agent/reviewer.md +6 -4
- package/runtime/prompts/workerpals/commit_message_prompt.md +3 -0
- package/runtime/prompts/workerpals/miniswe_broker_system_prompt.md +10 -9
- package/runtime/prompts/workerpals/miniswe_strict_tool_use_guidance.md +1 -0
- package/runtime/prompts/workerpals/openai_codex_runtime_policy_appendix.md +1 -0
- package/runtime/prompts/workerpals/openai_codex_task_execute_system_prompt.md +2 -0
- package/runtime/prompts/workerpals/task_quality_critic_system_prompt.md +3 -2
- package/runtime/sandbox/apps/workerpals/src/backends/openai_codex_backend.ts +4 -4
- package/runtime/sandbox/apps/workerpals/src/backends/openhands_task_execute.ts +1 -4
- package/runtime/sandbox/apps/workerpals/src/common/execution_utils.ts +5 -3
- package/runtime/sandbox/apps/workerpals/src/common/generic_python_executor.ts +1 -4
- package/runtime/sandbox/apps/workerpals/src/common/worktree_cleanup.ts +3 -2
- package/runtime/sandbox/apps/workerpals/src/docker_executor.ts +42 -27
- package/runtime/sandbox/apps/workerpals/src/execute_job.ts +7 -7
- package/runtime/sandbox/apps/workerpals/src/job_runner.ts +7 -4
- package/runtime/sandbox/apps/workerpals/src/workerpals_main.ts +2 -1
- package/runtime/sandbox/packages/shared/src/autonomy_policy.ts +8 -3
- package/runtime/sandbox/packages/shared/src/communication.ts +19 -8
- package/runtime/sandbox/packages/shared/src/config.ts +9 -24
- package/runtime/sandbox/packages/shared/src/config_template_parity.ts +5 -6
- package/runtime/sandbox/packages/shared/src/git_backend.ts +5 -9
- package/runtime/sandbox/packages/shared/src/local_network.ts +3 -1
- package/runtime/sandbox/packages/shared/src/localbuddy_runtime.ts +4 -5
- package/runtime/sandbox/packages/shared/src/vision.ts +6 -2
- package/runtime/sandbox/prompts/workerpals/commit_message_prompt.md +3 -0
- package/runtime/sandbox/prompts/workerpals/miniswe_broker_system_prompt.md +10 -9
- package/runtime/sandbox/prompts/workerpals/miniswe_strict_tool_use_guidance.md +1 -0
- package/runtime/sandbox/prompts/workerpals/openai_codex_runtime_policy_appendix.md +1 -0
- package/runtime/sandbox/prompts/workerpals/openai_codex_task_execute_system_prompt.md +2 -0
- package/runtime/sandbox/prompts/workerpals/task_quality_critic_system_prompt.md +3 -2
- package/runtime/vision.example.md +24 -5
|
@@ -50,10 +50,7 @@ export function parseLocalBuddyRuntimeSnapshot(raw: string): LocalBuddyRuntimeSn
|
|
|
50
50
|
return {
|
|
51
51
|
localbuddy: {
|
|
52
52
|
enabled,
|
|
53
|
-
port:
|
|
54
|
-
Number.isFinite(port) && port >= 1 && port <= 65_535
|
|
55
|
-
? port
|
|
56
|
-
: DEFAULT_LOCALBUDDY_PORT,
|
|
53
|
+
port: Number.isFinite(port) && port >= 1 && port <= 65_535 ? port : DEFAULT_LOCALBUDDY_PORT,
|
|
57
54
|
},
|
|
58
55
|
};
|
|
59
56
|
}
|
|
@@ -155,7 +152,9 @@ function resolveRuntimeConfigDir(workspaceRoot: string, configuredDir?: string):
|
|
|
155
152
|
}
|
|
156
153
|
|
|
157
154
|
function parseBoolEnv(value: string | undefined): boolean | undefined {
|
|
158
|
-
const text = String(value ?? "")
|
|
155
|
+
const text = String(value ?? "")
|
|
156
|
+
.trim()
|
|
157
|
+
.toLowerCase();
|
|
159
158
|
if (!text) return undefined;
|
|
160
159
|
if (TRUTHY.has(text)) return true;
|
|
161
160
|
if (FALSY.has(text)) return false;
|
|
@@ -40,7 +40,9 @@ export type VisionDocValidation = {
|
|
|
40
40
|
const MAX_KEY_ITEMS_PER_BUCKET = 8;
|
|
41
41
|
|
|
42
42
|
function toLines(markdown: string): string[] {
|
|
43
|
-
return String(markdown ?? "")
|
|
43
|
+
return String(markdown ?? "")
|
|
44
|
+
.replace(/\r\n/g, "\n")
|
|
45
|
+
.split("\n");
|
|
44
46
|
}
|
|
45
47
|
|
|
46
48
|
function extractOneSentence(lines: string[]): string {
|
|
@@ -75,7 +77,9 @@ function extractOneSentence(lines: string[]): string {
|
|
|
75
77
|
}
|
|
76
78
|
|
|
77
79
|
function normalizeItem(value: string): string {
|
|
78
|
-
return String(value ?? "")
|
|
80
|
+
return String(value ?? "")
|
|
81
|
+
.replace(/\s+/g, " ")
|
|
82
|
+
.trim();
|
|
79
83
|
}
|
|
80
84
|
|
|
81
85
|
function dedupeAndClamp(values: string[]): string[] {
|
|
@@ -10,6 +10,7 @@ Output only the raw commit message text — no markdown fences, no explanation,
|
|
|
10
10
|
- <specific implementation detail>
|
|
11
11
|
|
|
12
12
|
Tests:
|
|
13
|
+
|
|
13
14
|
- <test runner command>
|
|
14
15
|
|
|
15
16
|
## Writing rules
|
|
@@ -25,12 +26,14 @@ Background context: "can you add one more unit test for localbuddy"
|
|
|
25
26
|
|
|
26
27
|
Bad (copies instruction / uses planning language):
|
|
27
28
|
{{type}}({{area}}): lets add one more unit test for localbuddy
|
|
29
|
+
|
|
28
30
|
- At least one new unit test is added validating a meaningful LocalBuddy behavior.
|
|
29
31
|
- All existing and new tests pass.
|
|
30
32
|
- No unrelated files are modified.
|
|
31
33
|
|
|
32
34
|
Good (reads the diff):
|
|
33
35
|
{{type}}({{area}}): add unit test for LocalBuddy request routing and error response handling
|
|
36
|
+
|
|
34
37
|
- add test case in localbuddy.test.ts asserting router returns 404 for unknown tool calls
|
|
35
38
|
- add negative test for malformed request payload returning 400 with error message
|
|
36
39
|
- extract shared test fixtures into testHelpers.ts to reduce duplication
|
|
@@ -5,18 +5,19 @@ Repository root: {{repo}}
|
|
|
5
5
|
|
|
6
6
|
Output format (STRICT JSON, no markdown, no extra keys unless specified):
|
|
7
7
|
{
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
|
|
8
|
+
"actions": [
|
|
9
|
+
{"type":"read_file","path":"README.md"},
|
|
10
|
+
{"type":"append_line","path":"README.md","line":"..."},
|
|
11
|
+
{"type":"replace_text_once","path":"x","old":"a","new":"b"},
|
|
12
|
+
{"type":"write_file","path":"x","content":"..."},
|
|
13
|
+
{"type":"run_shell","command":"git status --porcelain"}
|
|
14
|
+
],
|
|
15
|
+
"done": false,
|
|
16
|
+
"note": "short explanation"
|
|
17
17
|
}
|
|
18
18
|
|
|
19
19
|
Rules:
|
|
20
|
+
|
|
20
21
|
- Keep actions minimal and directly relevant.
|
|
21
22
|
- JSON syntax must be exact: use ":" between keys and values, never ",".
|
|
22
23
|
- Use double quotes for all keys and string values.
|
|
@@ -1,4 +1,5 @@
|
|
|
1
1
|
CRITICAL: You must use tools to make progress.
|
|
2
|
+
|
|
2
3
|
- Use the environment's tools (file read/list/search, and file edit/write/patch) to inspect and modify the repo.
|
|
3
4
|
- Do NOT only describe what you would do; actually do it.
|
|
4
5
|
- Avoid broad scans; choose one target file quickly.
|
|
@@ -1,12 +1,14 @@
|
|
|
1
1
|
You are PushPals WorkerPal running via the OpenAI Codex CLI backend.
|
|
2
2
|
|
|
3
3
|
Non-negotiable runtime invariants:
|
|
4
|
+
|
|
4
5
|
- Codex CLI is required infrastructure in this environment.
|
|
5
6
|
- Do not modify tests or production code to bypass, stub, or remove Codex CLI usage due to assumed environment limitations.
|
|
6
7
|
- Do not "adapt around" missing Codex access by rewriting coverage or behavior expectations.
|
|
7
8
|
- If Codex CLI authentication/execution is unavailable, fail loudly with a clear error and stop.
|
|
8
9
|
|
|
9
10
|
Execution rules:
|
|
11
|
+
|
|
10
12
|
- Keep edits minimal, correct, and scoped to the requested task.
|
|
11
13
|
- Read relevant files before editing, then run focused validation.
|
|
12
14
|
- Report blockers explicitly; do not hide platform/runtime issues with workaround edits.
|
|
@@ -2,8 +2,9 @@ You are a strict code-review critic for worker-generated patches.
|
|
|
2
2
|
Return exactly one JSON object with keys:
|
|
3
3
|
{"score": <0-10 number>, "findings": [string], "must_fix": [string], "revision_guidance": string}
|
|
4
4
|
Scoring rubric:
|
|
5
|
+
|
|
5
6
|
- 10: complete, correct, and robust with strong validation coverage.
|
|
6
7
|
- 8-9: good quality with minor non-blocking issues.
|
|
7
8
|
- <=7: requires revision before commit.
|
|
8
|
-
must_fix must list blocking issues only.
|
|
9
|
-
Do not include markdown or prose outside JSON.
|
|
9
|
+
must_fix must list blocking issues only.
|
|
10
|
+
Do not include markdown or prose outside JSON.
|
|
@@ -9,18 +9,21 @@
|
|
|
9
9
|
## 1) Who this is for
|
|
10
10
|
|
|
11
11
|
### Primary users
|
|
12
|
+
|
|
12
13
|
- **User type A:** (e.g., app developers, SREs, analysts, end-users)
|
|
13
14
|
- Jobs-to-be-done: …
|
|
14
15
|
- Pain today: …
|
|
15
16
|
- Success looks like: …
|
|
16
17
|
|
|
17
18
|
### Secondary users
|
|
19
|
+
|
|
18
20
|
- **User type B:** …
|
|
19
21
|
- Jobs-to-be-done: …
|
|
20
22
|
- Pain today: …
|
|
21
23
|
- Success looks like: …
|
|
22
24
|
|
|
23
|
-
### Non-users (explicitly
|
|
25
|
+
### Non-users (explicitly _not_ optimizing for)
|
|
26
|
+
|
|
24
27
|
- **Not for:** …
|
|
25
28
|
- Why: …
|
|
26
29
|
|
|
@@ -31,13 +34,15 @@
|
|
|
31
34
|
## 2) The problem we solve
|
|
32
35
|
|
|
33
36
|
### Today’s reality
|
|
37
|
+
|
|
34
38
|
- What is hard / slow / risky today?
|
|
35
39
|
- What failures happen repeatedly? (bugs, incidents, misconfig, confusion)
|
|
36
40
|
- What is expensive? (time, money, cognitive load, coordination)
|
|
37
41
|
|
|
38
42
|
### The change we want
|
|
39
|
-
|
|
40
|
-
- In
|
|
43
|
+
|
|
44
|
+
- In 6–12 months, what should feel _meaningfully easier_?
|
|
45
|
+
- In 2–3 years, what should be _obviously different_?
|
|
41
46
|
|
|
42
47
|
> **Optional:** Add a 3–5 line “story” of a user before vs after.
|
|
43
48
|
|
|
@@ -66,11 +71,13 @@ These are **tie-breakers** when tradeoffs happen. Put them in priority order.
|
|
|
66
71
|
Pick a small set of metrics you can actually track.
|
|
67
72
|
|
|
68
73
|
### User-facing outcomes
|
|
74
|
+
|
|
69
75
|
- **Time-to-success:** e.g., median time from install → first successful use
|
|
70
76
|
- **Quality:** e.g., bug rate / support tickets per active user
|
|
71
77
|
- **Trust:** e.g., SLO compliance, error rate, crash-free sessions
|
|
72
78
|
|
|
73
79
|
### Developer / maintainer outcomes
|
|
80
|
+
|
|
74
81
|
- **Change velocity:** PR cycle time, lead time to release
|
|
75
82
|
- **Operational burden:** pages/alerts per week, toil hours
|
|
76
83
|
- **Maintainability:** test coverage for critical paths, build time, flake rate
|
|
@@ -81,17 +88,20 @@ Pick a small set of metrics you can actually track.
|
|
|
81
88
|
|
|
82
89
|
## 5) Scope and boundaries
|
|
83
90
|
|
|
84
|
-
### In scope (what we
|
|
91
|
+
### In scope (what we _are_)
|
|
92
|
+
|
|
85
93
|
- Core capability A: …
|
|
86
94
|
- Core capability B: …
|
|
87
95
|
- Core capability C: …
|
|
88
96
|
|
|
89
|
-
### Out of scope / non-goals (what we are
|
|
97
|
+
### Out of scope / non-goals (what we are _not_)
|
|
98
|
+
|
|
90
99
|
- Not a replacement for: …
|
|
91
100
|
- Not trying to support: …
|
|
92
101
|
- Not optimizing for: …
|
|
93
102
|
|
|
94
103
|
### Compatibility & support policy (optional)
|
|
104
|
+
|
|
95
105
|
- Supported platforms / versions: …
|
|
96
106
|
- Breaking changes policy: …
|
|
97
107
|
- Deprecation timeline: …
|
|
@@ -120,6 +130,7 @@ Pick 3–5 items max. Each should be **outcome-oriented**.
|
|
|
120
130
|
These are “bets” with explicit results.
|
|
121
131
|
|
|
122
132
|
### Objective A: <name>
|
|
133
|
+
|
|
123
134
|
- **Problem:** …
|
|
124
135
|
- **Approach:** …
|
|
125
136
|
- **Deliverables:** …
|
|
@@ -127,6 +138,7 @@ These are “bets” with explicit results.
|
|
|
127
138
|
- **Exit criteria:** How we’ll know it worked (measurable)
|
|
128
139
|
|
|
129
140
|
### Objective B: <name>
|
|
141
|
+
|
|
130
142
|
- …
|
|
131
143
|
|
|
132
144
|
---
|
|
@@ -136,6 +148,7 @@ These are “bets” with explicit results.
|
|
|
136
148
|
Describe where this repo is going, without over-promising.
|
|
137
149
|
|
|
138
150
|
### Strategic bets
|
|
151
|
+
|
|
139
152
|
- **Bet 1:** …
|
|
140
153
|
- Why it matters: …
|
|
141
154
|
- What we’ll likely build: …
|
|
@@ -143,6 +156,7 @@ Describe where this repo is going, without over-promising.
|
|
|
143
156
|
- **Bet 2:** …
|
|
144
157
|
|
|
145
158
|
### “If we’re right, then…”
|
|
159
|
+
|
|
146
160
|
- Users will be able to: …
|
|
147
161
|
- Maintainers will spend less time on: …
|
|
148
162
|
- The ecosystem will have: …
|
|
@@ -152,6 +166,7 @@ Describe where this repo is going, without over-promising.
|
|
|
152
166
|
## 9) Guardrails and constraints
|
|
153
167
|
|
|
154
168
|
### Guardrails (how we avoid harm / churn)
|
|
169
|
+
|
|
155
170
|
- Prefer changes that are **reversible** or behind flags.
|
|
156
171
|
- Default to **secure / safe** settings.
|
|
157
172
|
- Optimize for the **common path**; support escape hatches for experts.
|
|
@@ -159,6 +174,7 @@ Describe where this repo is going, without over-promising.
|
|
|
159
174
|
- Pay down operational toil before adding big surface area.
|
|
160
175
|
|
|
161
176
|
### Constraints (reality checks)
|
|
177
|
+
|
|
162
178
|
- Staffing level / maintainer bandwidth: …
|
|
163
179
|
- Hard requirements (privacy, compliance, perf, cost): …
|
|
164
180
|
- External dependencies: …
|
|
@@ -181,11 +197,14 @@ Describe where this repo is going, without over-promising.
|
|
|
181
197
|
## Appendix (optional but powerful)
|
|
182
198
|
|
|
183
199
|
### A) Glossary
|
|
200
|
+
|
|
184
201
|
- Term: definition…
|
|
185
202
|
|
|
186
203
|
### B) Personas (one-page each)
|
|
204
|
+
|
|
187
205
|
- Persona, environment, constraints, success criteria…
|
|
188
206
|
|
|
189
207
|
### C) Example “no” responses (template)
|
|
208
|
+
|
|
190
209
|
- “Thanks — this is valuable, but it conflicts with our non-goal X…”
|
|
191
210
|
- “We’d reconsider if metric Y becomes a problem…”
|