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 v0.2.116 | Python v0.1.64. API reference for query(), hooks, subagents, MCP, permissions, sandbox, structured outputs, and sessions.",
3
+
"description": "Build autonomous AI agents with Claude Agent SDK. TypeScript v0.2.117 | Python v0.1.65. 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 (v0.2.116)
532
+
await q.getContextUsage(); // Get context window usage breakdown by category — returns SDKControlGetContextUsageResponse (v0.2.117)
533
+
await q.readFile(path, { maxBytes? }); // Read a file from the session filesystem (gated by same read-permission rules as Read tool); returns SDKControlReadFileResponse | null
Both SDK versions bumped successfully (TS 0.2.116 → 0.2.117, PY 0.1.64 → 0.1.65) and the update agent applied all file changes in 154s. The TypeScript research agent failed after 334s by hitting the $3 per-run budget cap before evaluating any new issues. Python research completed successfully (60 turns, $1.72). Typecheck produced the recurring stale-comma false-positive, which the mending agent fixed in one pass; final verify passed 28/28 checks on attempt 2.
-**Mending needed**: yes — 1 mend run to fix typecheck false-positive
36
+
-**Verification**: passed on attempt 2 (28/28 checks)
37
+
38
+
No upstream release notes were available for either version bump.
39
+
40
+
## Research
41
+
42
+
### TypeScript Research — FAILED
43
+
44
+
The TS research agent terminated early after 334s by exceeding the $3 per-agent budget cap. No issues were evaluated. `lastScannedIssueNumber` remains at 236; `lastAuditedVersion` was updated to 0.2.117 by the update agent.
45
+
46
+
### Python Research — success
47
+
48
+
-**Issues evaluated**: session data unavailable (cost log has no turn breakdown per issue)
49
+
-**New Known Issues added**: none recorded in state delta
50
+
-**Issues updated**: none recorded in state delta
51
+
- The Python `lastScannedIssueNumber` remains at 776; `lastAuditedVersion` is 0.1.56 (research agent audits differ from version tracking)
52
+
53
+
> Note: The python research agent ran for 286s / 60 turns / $1.72. No new `knownIssueNumber` assignments appear in the state diff for today, suggesting all reviewed issues were already documented or skipped.
Error: Claude Code returned an error result: Reached maximum budget ($3)
70
+
at O9.readMessages (...)
71
+
```
72
+
73
+
**Likely cause**: The TS research agent hit the `maxBudgetUsd: 3` cap configured for the sub-agent. Since `lastAuditedVersion` matched `0.2.117` at start time, the agent may have been doing full re-audit work.
74
+
75
+
**Suggested fix**: Check whether the budget cap needs to be raised or whether the agent should short-circuit when `lastAuditedVersion == currentVersion` with no new issues in the scan range.
76
+
77
+
---
78
+
79
+
### typecheck — Exit code 1 (fixed by mending)
80
+
81
+
**Last output:**
82
+
```
83
+
File "<string>", line 1
84
+
from claude_agent_sdk import (,AgentDefinition,ClaudeAgentOptions,...
85
+
^
86
+
SyntaxError: invalid syntax
87
+
FAIL: Some template imports don't resolve
88
+
FAIL: Cannot import: (
89
+
90
+
Passed: 13 / Failed: 2
91
+
TEMPLATE CHECK FAILED — 2 issue(s)
92
+
```
93
+
94
+
**Likely cause**: Recurring stale-comma false-positive in the generated Python import list (leading comma after opening paren). This is a known artifact of the update agent's template manipulation.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4&size=40){kind=avatar}
0 commit comments