You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository was archived by the owner on May 18, 2026. It is now read-only.
Copy file name to clipboardExpand all lines: .claude-plugin/plugin.json
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
{
2
2
"name": "claude-agent-sdk",
3
-
"description": "Build autonomous AI agents with Claude Agent SDK. TypeScript v0.2.121 | Python v0.1.69. API reference for query(), hooks, subagents, MCP, permissions, sandbox, structured outputs, and sessions.",
3
+
"description": "Build autonomous AI agents with Claude Agent SDK. TypeScript v0.2.123 | Python v0.1.71. API reference for query(), hooks, subagents, MCP, permissions, sandbox, structured outputs, and sessions.",
Copy file name to clipboardExpand all lines: README.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,7 +2,7 @@
2
2
3
3
A self-updating Claude Code skill for building AI agents with the Claude Agent SDK — covering both [TypeScript](https://github.com/anthropics/claude-agent-sdk-typescript) and [Python](https://github.com/anthropics/claude-agent-sdk-python).
await q.getContextUsage(); // Get context window usage breakdown by category — returns SDKControlGetContextUsageResponse (v0.2.121)
537
+
await q.getContextUsage(); // Get context window usage breakdown by category — returns SDKControlGetContextUsageResponse (v0.2.123)
538
538
await q.readFile(path, { maxBytes?, encoding?: 'utf-8' | 'base64' }); // Read a file from the session filesystem (gated by same read-permission rules as Read tool); returns SDKControlReadFileResponse | null. Use 'base64' for binary files like images.
Both SDKs received version bumps: TypeScript 0.2.121 → 0.2.123 and Python 0.1.69 → 0.1.71. The update and both research agents completed successfully. The typecheck step failed initially due to a recurring false-positive (stale-comma in the Python import resolution check), which was resolved by 1 mend run; verification then passed 28/28 checks on attempt 2. No new known issues were added today; research focused on auditing new version changes and updating documentation references.
| Typecheck | failed → resolved | 13s | False-positive SyntaxError in import check; 1 mend run fixed it |
17
+
| Verify | success | 184s | Passed 28/28 on attempt 2 after mending |
18
+
| Report | running | — ||
19
+
20
+
## Monitor
21
+
22
+
-**Changes detected**: yes
23
+
- TypeScript SDK version bump: 0.2.121 → 0.2.123 (npm)
24
+
- Python SDK version bump: 0.1.69 → 0.1.71 (PyPI)
25
+
- No issue state changes
26
+
- No new bug issues detected
27
+
28
+
## Update Agent
29
+
30
+
**TypeScript**: 0.2.121 → 0.2.123
31
+
32
+
Files modified:
33
+
-`SKILL-typescript.md` — version references updated to 0.2.123; `planModeInstructions` added to V2 supported options list; changelog highlights extended to v0.2.123
34
+
-`SKILL.md`, `README.md` — version references updated
35
+
-`templates/typescript/package.json` — bumped to `@anthropic-ai/claude-agent-sdk@0.2.123`
36
+
-`rules/claude-agent-sdk-ts.md` — version references updated
37
+
-`scripts/check-versions.sh` — version pinned updated
38
+
-`.claude-plugin/plugin.json` — version references updated
39
+
-`agent/state.json` — TS version + lastAuditedVersion updated
40
+
41
+
**Python**: 0.1.69 → 0.1.71
42
+
43
+
Files modified:
44
+
-`SKILL-python.md` — all v0.1.69 references updated to v0.1.71 (AssistantMessage fields, ResultMessage fields, AgentDefinition fields, @tool annotations, feature matrix)
45
+
-`templates/python/pyproject.toml` — bumped to `claude-agent-sdk>=0.1.71`
46
+
-`rules/claude-agent-sdk-py.md` — version references updated
47
+
-`agent/state.json` — PY version updated
48
+
49
+
**Verification**: Passed 28/28 checks on attempt 2. 1 mend run was needed to fix a typecheck false-positive (see Errors section).
50
+
51
+
## Research
52
+
53
+
### TypeScript Research (TS v0.2.121 → 0.2.123)
54
+
55
+
- Issues scanned through #236 (no new issues above prior scan boundary)
56
+
- No new Known Issues added
57
+
- Documentation update: added `planModeInstructions` to V2 API supported options list in SKILL-typescript.md
58
+
- All previously tracked issues reviewed; no state changes detected
59
+
60
+
### Python Research (PY v0.1.69 → 0.1.71)
61
+
62
+
- Issues scanned through #776 (no new issues above prior scan boundary)
63
+
- No new Known Issues added
64
+
- Documentation updates: version attribution for `AssistantMessage.message_id/stop_reason/session_id/uuid`, `ResultMessage.model_usage/permission_denials/errors/uuid`, and `AgentDefinition.background/effort/permissionMode` fields updated to reflect v0.1.71
65
+
-`lastAuditedVersion` remains at 0.1.56 (full audit boundary; incremental version audit completed)
66
+
67
+
## Errors
68
+
69
+
### Typecheck — Exit Code 1 (resolved by mending)
70
+
71
+
**Last output:**
72
+
```
73
+
OK: query_with_tools.py — valid syntax
74
+
OK: sandbox_config.py — valid syntax
75
+
OK: session_management.py — valid syntax
76
+
OK: structured_output.py — valid syntax
77
+
OK: subagents_orchestration.py — valid syntax
78
+
79
+
=== Python import resolution check ===
80
+
File "<string>", line 1
81
+
from claude_agent_sdk import (,AgentDefinition,ClaudeAgentOptions,...
82
+
^
83
+
SyntaxError: invalid syntax
84
+
FAIL: Some template imports don't resolve
85
+
FAIL: Cannot import: (
86
+
87
+
=========================================
88
+
Passed: 13
89
+
Failed: 2
90
+
=========================================
91
+
92
+
TEMPLATE CHECK FAILED — 2 issue(s)
93
+
```
94
+
95
+
**Likely cause**: Recurring false-positive — stale comma artifact in the auto-generated Python import check command (leading `,` after `(`). Not a real code error.
96
+
97
+
**Resolution**: 1 mend run fixed the generated import check; verify passed 28/28 on attempt 2.
98
+
99
+
**Next action**: None required — this is a known recurring false-positive pattern.
100
+
101
+
## Cost
102
+
103
+
| Agent | Cost | Turns |
104
+
|-------|------|-------|
105
+
| Update | $0.42 | 61 |
106
+
| Mending (×1) | $0.42 | 32 |
107
+
| Research (TS) | $2.46 | 95 |
108
+
| Research (PY) | $1.67 | 63 |
109
+
| Report | N/A | — |
110
+
|**Total**|**$4.97**|**251**|
111
+
112
+
## State
113
+
114
+
Current tracked state after today's run:
115
+
116
+
-**TypeScript SDK version**: 0.2.123
117
+
-**Python SDK version**: 0.1.71
118
+
-**TS last scanned issue**: #236
119
+
-**PY last scanned issue**: #776
120
+
-**TS tracked issues**: 65 (issues #106–#236 across anthropics/claude-agent-sdk-typescript)
121
+
-**PY tracked issues**: 79 (issues #10–#776 across anthropics/claude-agent-sdk-python)
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4&size=40){kind=avatar}
0 commit comments