open-swarm 0.1.1745274322__py3-none-any.whl → 0.1.1745274459__py3-none-any.whl
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.
- {open_swarm-0.1.1745274322.dist-info → open_swarm-0.1.1745274459.dist-info}/METADATA +1 -1
- {open_swarm-0.1.1745274322.dist-info → open_swarm-0.1.1745274459.dist-info}/RECORD +9 -8
- swarm/blueprints/codey/README.md +57 -85
- swarm/blueprints/codey/blueprint_codey.py +896 -1119
- swarm/blueprints/codey/codey_cli.py +259 -47
- swarm/blueprints/codey/metadata.json +23 -0
- {open_swarm-0.1.1745274322.dist-info → open_swarm-0.1.1745274459.dist-info}/WHEEL +0 -0
- {open_swarm-0.1.1745274322.dist-info → open_swarm-0.1.1745274459.dist-info}/entry_points.txt +0 -0
- {open_swarm-0.1.1745274322.dist-info → open_swarm-0.1.1745274459.dist-info}/licenses/LICENSE +0 -0
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: open-swarm
|
3
|
-
Version: 0.1.
|
3
|
+
Version: 0.1.1745274459
|
4
4
|
Summary: Open Swarm: Orchestrating AI Agent Swarms with Django
|
5
5
|
Project-URL: Homepage, https://github.com/yourusername/open-swarm
|
6
6
|
Project-URL: Documentation, https://github.com/yourusername/open-swarm/blob/main/README.md
|
@@ -18,10 +18,11 @@ swarm/blueprints/blueprint_audit_status.json,sha256=6uv6_M8WU5VGr1GhG49_p0-iHHRo
|
|
18
18
|
swarm/blueprints/chatbot/blueprint_chatbot.py,sha256=Fuy_kPQUaZtIKoM01aWGjieak1zGTxI8VBVbi-TzHH0,14441
|
19
19
|
swarm/blueprints/chatbot/templates/chatbot/chatbot.html,sha256=REFnqNg0EHsXxAUfaCJe1YgOKiV_umBXuC6y8veF5CU,1568
|
20
20
|
swarm/blueprints/codey/CODEY.md,sha256=JxGcR0INH0dLk_q4ua1D0YdvX99szyESsbbs4dIy5Sc,742
|
21
|
-
swarm/blueprints/codey/README.md,sha256=
|
22
|
-
swarm/blueprints/codey/blueprint_codey.py,sha256=
|
23
|
-
swarm/blueprints/codey/codey_cli.py,sha256=
|
21
|
+
swarm/blueprints/codey/README.md,sha256=4P9BdRhhUl65W3m1akp-wooM808P8jFWQHm9jbnDjYE,5266
|
22
|
+
swarm/blueprints/codey/blueprint_codey.py,sha256=t6VSEgier8RHzdcZjsAKD098vzIUpsXIkQHwyrVOzDA,48030
|
23
|
+
swarm/blueprints/codey/codey_cli.py,sha256=ovOlfuvxa8CSQ9v41DT1rww2v966QEYnf6UEyYbVwVc,17579
|
24
24
|
swarm/blueprints/codey/instructions.md,sha256=XMvJngQ23vl7xJQx-Sp5UIME2-JQyyxeZFFtIuOtTOI,1209
|
25
|
+
swarm/blueprints/codey/metadata.json,sha256=wsW0jGIKZ-vzrMSMbOuYtVM8rr4joNIeJ0NBQAiHqu4,775
|
25
26
|
swarm/blueprints/codey/session_logs/session_2025-04-19T01-15-31.md,sha256=IRzOdr9wisTQYOc0FZQi-4zlX_vickQrq900SNZ9dPU,270
|
26
27
|
swarm/blueprints/codey/session_logs/session_2025-04-19T01-16-03.md,sha256=2GQcj850IZMz3Fqvet3dynXuTom4ZT7VwoxwWMhgTH8,270
|
27
28
|
swarm/blueprints/common/operation_box_utils.py,sha256=YYntqT6p44r7hxq5GLOS0gyOuInmhvWo1hp6-qKk36Q,3087
|
@@ -298,8 +299,8 @@ swarm/views/message_views.py,sha256=sDUnXyqKXC8WwIIMAlWf00s2_a2T9c75Na5FvYMJwBM,
|
|
298
299
|
swarm/views/model_views.py,sha256=aAbU4AZmrOTaPeKMWtoKK7FPYHdaN3Zbx55JfKzYTRY,2937
|
299
300
|
swarm/views/utils.py,sha256=8Usc0g0L0NPegNAyY20tJBNBy-JLwODf4VmxV0yUtpw,3627
|
300
301
|
swarm/views/web_views.py,sha256=T1CKe-Nyv1C8aDt6QFTGWo_dkH7ojWAvS_QW9mZnZp0,7371
|
301
|
-
open_swarm-0.1.
|
302
|
-
open_swarm-0.1.
|
303
|
-
open_swarm-0.1.
|
304
|
-
open_swarm-0.1.
|
305
|
-
open_swarm-0.1.
|
302
|
+
open_swarm-0.1.1745274459.dist-info/METADATA,sha256=LAmWU8maJObP1Ku7PcMovDBMQykoeKEA-Ly1nCFvmY0,39330
|
303
|
+
open_swarm-0.1.1745274459.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
|
304
|
+
open_swarm-0.1.1745274459.dist-info/entry_points.txt,sha256=fo28d0_zJrytRsh8QqkdlWQT_9lyAwYUx1WuSTDI3HM,177
|
305
|
+
open_swarm-0.1.1745274459.dist-info/licenses/LICENSE,sha256=BU9bwRlnOt_JDIb6OT55Q4leLZx9RArDLTFnlDIrBEI,1062
|
306
|
+
open_swarm-0.1.1745274459.dist-info/RECORD,,
|
swarm/blueprints/codey/README.md
CHANGED
@@ -1,15 +1,52 @@
|
|
1
1
|
# Codey Blueprint
|
2
2
|
|
3
|
-
**Codey** is
|
3
|
+
**Codey** is an agentic code and semantic search/analysis blueprint for Open Swarm, demonstrating agent-based orchestration, robust UX with ANSI/emoji output, spinner feedback, and resilient fallback for agent/LLM errors.
|
4
4
|
|
5
|
-
|
6
|
-
|
5
|
+
---
|
6
|
+
|
7
|
+
## What This Blueprint Demonstrates
|
8
|
+
- **Agent-based code and semantic search** (keyword and semantic)
|
9
|
+
- **LLM fallback and error handling** with user-friendly messages
|
10
|
+
- **Unified ANSI/emoji boxes** for search/analysis results, including summaries, counts, and parameters
|
11
|
+
- **Custom spinner messages**: 'Generating.', 'Generating..', 'Generating...', 'Running...'
|
12
|
+
- **Progress updates** for long-running operations (line numbers, result counts)
|
13
|
+
- **Test mode** for robust, deterministic testing
|
14
|
+
|
15
|
+
## Usage
|
16
|
+
Run with the CLI:
|
17
|
+
```sh
|
18
|
+
swarm-cli run codey --instruction "/codesearch recursion . 5"
|
19
|
+
```
|
20
|
+
|
21
|
+
## Test
|
22
|
+
```sh
|
23
|
+
uv run pytest -v tests/blueprints/test_codey.py
|
24
|
+
```
|
25
|
+
|
26
|
+
## Compliance
|
27
|
+
- Agentic:
|
28
|
+
- UX (ANSI/emoji):
|
29
|
+
- Spinner:
|
30
|
+
- Fallback:
|
31
|
+
- Test Coverage:
|
32
|
+
|
33
|
+
## Required Env Vars
|
34
|
+
- `SWARM_TEST_MODE` (optional): Enables test mode for deterministic output.
|
35
|
+
|
36
|
+
## Extending
|
37
|
+
- See `blueprint_codey.py` for agent logic and UX hooks.
|
38
|
+
- Extend agent capabilities or UX by modifying the `_run_non_interactive` method.
|
39
|
+
|
40
|
+
---
|
41
|
+
_Last updated: 2025-04-21_
|
42
|
+
|
43
|
+
# (Legacy content below)
|
7
44
|
|
8
45
|
Codey is an agentic coding assistant blueprint for Open Swarm, inspired by OpenAI Codex CLI. It orchestrates specialized agents and tools to automate and assist with software engineering tasks, especially those involving code, git, and project workflows.
|
9
46
|
|
10
47
|
---
|
11
48
|
|
12
|
-
##
|
49
|
+
## Features Implemented
|
13
50
|
|
14
51
|
- **Global Instructions**: Reads and injects `~/.codey/instructions.md` as a base prompt for orchestration/coordinator agent.
|
15
52
|
- **Agent Delegation**: Supports delegating tasks to specialized sub-agents (e.g., GitHub agent, code review agent).
|
@@ -19,111 +56,46 @@ Codey is an agentic coding assistant blueprint for Open Swarm, inspired by OpenA
|
|
19
56
|
- **Rich Syntax Highlighting**: Code fences in assistant responses are colorized via Rich.
|
20
57
|
- **Slash Commands**: Built-in `/help`, `/compact`, `/model`, `/approval`, `/history`, `/clear`, and `/clearhistory` available.
|
21
58
|
- **Testable via CLI**: Supports test-driven development and CLI-based interaction.
|
22
|
-
- **Project-Level Instructions**: Automatically loaded and injected from `CODEY.md` if present in the project. No manual step required.
|
23
|
-
- **Interactive/Approval Mode**: Supports interactive prompts for git operations in suggest mode.
|
24
|
-
- **Unified Rich Output Formatting**: Unified and enhanced rich output formatting (boxes, emojis, result summaries).
|
25
|
-
- **Custom Spinner/Progress Messages**: Custom spinner/progress messages for better UX.
|
26
|
-
- **Persistent Session Logging/Audit Trail**: Persistent log of actions, plans, or outputs.
|
27
|
-
- **Full-Context Mode**: Full-context mode for large refactor/analysis.
|
28
|
-
- **Writable Root/Sandboxing CLI/Config Support**: Writable root/sandboxing CLI/config support.
|
29
|
-
- **Command Suggestions/Typeahead/Autocomplete**: Command suggestions/typeahead/autocomplete (CLI and slash commands).
|
30
|
-
- **Session/History Management and Overlays**: Session/history management and overlays.
|
31
|
-
- **Model Selection Overlay and CLI/Agent-Specific Support**: Model selection overlay and CLI/agent-specific support.
|
32
|
-
- **Help and Onboarding Overlays**: Help and onboarding overlays.
|
33
|
-
- **Desktop Notification Support**: Desktop notification support (optional).
|
34
|
-
- **Dangerous Auto-Approve Flag/UX**: Dangerous auto-approve flag/UX.
|
35
|
-
- **Output Formatting/Full Stdout Option**: Output formatting/full stdout option.
|
36
|
-
- **Image Input**: Image input (CLI/UX, future-proof).
|
37
59
|
|
38
60
|
---
|
39
61
|
|
40
|
-
##
|
62
|
+
## Features Partially Implemented
|
41
63
|
|
64
|
+
- **Project-Level Instructions**: Can be injected manually (e.g., `CODEY.md`), but not auto-loaded.
|
42
65
|
- **File/Directory Context Awareness**: File tools exist, but no automatic context file loading or project scanning.
|
43
66
|
- **Rich Output Formatting**: Some ANSI/emoji UX, but not unified or as rich as Codex.
|
44
|
-
- **
|
67
|
+
- **Interactive/Approval Mode**: Basic CLI flag (`--approval-mode`) supports interactive prompts for git operations in suggest mode.
|
45
68
|
|
46
69
|
---
|
47
70
|
|
48
|
-
##
|
71
|
+
## Features Not Yet Implemented
|
49
72
|
|
50
73
|
- **Automatic Plan/Changelog Updates**: Agent does not maintain `.codey/plan_*.md` or changelogs automatically.
|
51
74
|
- **Automatic Context Injection**: Agent does not scan/include relevant files automatically in prompts.
|
75
|
+
- **User Feedback Loop**: No mechanism for user feedback/corrections mid-session.
|
76
|
+
- **Session Logging/Audit Trail**: No persistent log of actions, plans, or outputs.
|
52
77
|
|
53
78
|
---
|
54
79
|
|
55
|
-
##
|
56
|
-
|
57
|
-
This blueprint aims to match all core and advanced features of the OpenAI Codex CLI. Below is the current status:
|
58
|
-
|
59
|
-
### ✅ Already Implemented
|
60
|
-
- Rich output/emoji/spinner UX (unified for search, analysis, file ops)
|
61
|
-
- Modular agent/blueprint system
|
62
|
-
- Interactive CLI mode (basic)
|
63
|
-
- Approval mode for git ops and some agent actions
|
64
|
-
- Syntax-highlighted code output
|
65
|
-
- Project-level instruction auto-loading (e.g., CODEY.md)
|
66
|
-
- Slash commands: `/help`, `/compact`, `/model`, `/approval`, `/history`, `/clear`, `/clearhistory` (basic)
|
67
|
-
- Persistent session logging/audit trail
|
68
|
-
- Full-context mode for large refactor/analysis
|
69
|
-
- Writable root/sandboxing CLI/config support
|
70
|
-
- Command suggestions/typeahead/autocomplete (CLI and slash commands)
|
71
|
-
- Session/history management and overlays
|
72
|
-
- Model selection overlay and CLI/agent-specific support
|
73
|
-
- Help and onboarding overlays
|
74
|
-
- Desktop notification support (optional)
|
75
|
-
- Dangerous auto-approve flag/UX
|
76
|
-
- Output formatting/full stdout option
|
77
|
-
- Image input (CLI/UX, future-proof)
|
78
|
-
|
79
|
-
### ⚠️ Partially Implemented
|
80
|
-
- Approval modes (full-auto, interactive, granular gating for all agent/file/code actions)
|
81
|
-
- Directory sandboxing (not enforced everywhere, no network controls)
|
82
|
-
- CLI/config file support (not unified or live-reloadable)
|
83
|
-
- Version control integration (git ops for suggest mode only)
|
84
|
-
|
85
|
-
### ❌ Not Yet Implemented
|
86
|
-
- Auto dependency install for generated code
|
87
|
-
- Automatic context/project file injection
|
88
|
-
- Plan/changelog file maintenance
|
89
|
-
- User feedback/correction loop
|
90
|
-
- Streaming token-by-token CLI output
|
91
|
-
- Non-interactive/CI/headless mode
|
92
|
-
- Multimodal input (screenshots/diagrams)
|
93
|
-
- Atomic commit/rollback for all agent actions
|
94
|
-
- Safety/ZDR org restrictions
|
95
|
-
|
96
|
-
---
|
97
|
-
|
98
|
-
### Implementation Roadmap
|
99
|
-
- [ ] Approval modes for all agent/file/code actions
|
100
|
-
- [ ] Directory/network sandboxing for all agent execution
|
101
|
-
- [ ] Auto dependency install for generated code
|
102
|
-
- [ ] Automatic context injection for prompts
|
103
|
-
- [ ] Plan/changelog file maintenance
|
104
|
-
- [ ] User feedback/correction loop
|
105
|
-
- [ ] Streaming CLI output
|
106
|
-
- [ ] Non-interactive/CI/headless mode
|
107
|
-
- [ ] Multimodal input support
|
108
|
-
- [ ] Atomic commit/rollback for all agent actions
|
109
|
-
- [ ] Safety/ZDR org restrictions
|
110
|
-
|
111
|
-
---
|
80
|
+
## Onboarding Tips
|
112
81
|
|
113
|
-
|
82
|
+
- Try `/codesearch <keyword> <path> <max_results>` (e.g. `/codesearch recursion . 5`)
|
83
|
+
- Try `/semanticsearch <keyword>` for semantic code search with rich result boxes, result counts, and spinner
|
84
|
+
- Use `/help` for slash commands, `/model` to switch models, `/approval` for approval mode
|
85
|
+
- Use arrow keys for history, Ctrl+C to quit, Esc to interrupt
|
86
|
+
- See the main README for advanced onboarding and blueprint discovery
|
114
87
|
|
115
88
|
---
|
116
89
|
|
117
90
|
## TODO
|
118
91
|
|
119
92
|
- [x] Implement interactive/approval mode for agent actions
|
120
|
-
- [
|
121
|
-
- [
|
122
|
-
- [x] Enable automatic plan/changelog file updates
|
123
|
-
- [x] Add project-level instruction auto-loading (e.g., `CODEY.md`)
|
93
|
+
- [ ] Enable automatic plan/changelog file updates
|
94
|
+
- [ ] Add project-level instruction auto-loading (e.g., `CODEY.md`)
|
124
95
|
- [ ] Improve file/directory context awareness and context injection
|
96
|
+
- [ ] Unify and enhance rich output formatting (boxes, emojis, result summaries)
|
125
97
|
- [ ] Add user feedback/correction loop
|
126
|
-
- [
|
98
|
+
- [ ] Add persistent session logging/audit trail
|
127
99
|
- [ ] Implement summarization logic for `/compact` slash command
|
128
100
|
- [ ] Implement model switching for `/model` slash command
|
129
101
|
- [ ] Implement approval toggle for `/approval` slash command
|