Repository navigation
Initial Python SDK import - #1
Merged
Merged
Conversation
The tests are passing but CI was failing due to missing Codecov token. Set fail_ci_if_error to false since coverage upload is optional.
dicksontsai
approved these changes
Jun 12, 2025
Collaborator
There was a problem hiding this comment.
Is this supposed to exist but be empty?
|
|
||
| [project] | ||
| name = "claude-code-sdk" | ||
| version = "0.0.10" |
Collaborator
There was a problem hiding this comment.
Any reason we're starting at 0.0.10 vs. another 0.0.xx in particular?
golfballnut
pushed a commit
to golfballnut/claude-agent-sdk-python
that referenced
this pull request
Oct 18, 2025
Created comprehensive ClickUp + Supabase integration design: ClickUp Architecture: - 3-list data distribution (Golf Courses, Contacts, Outreach Activities) - 33 custom fields specified across 3 lists - Outreach task = command center (sales never leaves task) - Rich description shows ALL contacts with complete context - Subtasks for multi-touch sequences - Custom views for filtering by segment Outreach Task Template: - Complete description format with all 4-7 contacts - Company intelligence section - 5 conversation starters ranked by AI - Sequence plan (Email anthropics#1-3, LinkedIn, Phone) - Edge case handling notes - Ready-to-send email draft Supabase Schema (Migration 005): - outreach_activities table (campaign tracking) - outreach_communications table (complete audit trail) - outreach_sequences table (automation state) - opt_out_log table (compliance - immutable) - contact_changes table (job changes, email changes) - 4 helper functions for common operations - 4 analytics views for reporting Edge Case Playbook: - 10 critical scenarios documented - Detection → Action → Recovery for each - Supabase + ClickUp actions specified - Compliance handling (opt-outs) - Attribution tracking (what works) - Prevention strategies Key Innovation: Outreach task description contains ALL contacts with email/phone/LinkedIn so sales team has complete context without clicking to other lists. Ready to implement: Field specs, migrations, and templates complete. 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
golfballnut
pushed a commit
to golfballnut/claude-agent-sdk-python
that referenced
this pull request
Oct 29, 2025
…cking, webhooks Fixed 3 critical bugs causing 100% enrichment failure rate: Bug anthropics#1: Contact Aggregation Logic - Changed from REPLACE to MERGE strategy for fallback contacts - Agent 2.1 (LinkedIn) and 2.2 (Perplexity) now accumulate contacts - Lowered threshold from 2+ to 1+ contacts (proceed if ANY found) - Only raises exception if 0 contacts from all sources - Impact: Beach Buddy (1 contact) and Bear Lake (1 contact) now succeed Bug anthropics#2: Missing course_id in Failures - Added course_id to exception handler result dict - Enables webhook firing even on enrichment failures - Allows error tracking in ClickUp and database status updates - Impact: All courses now tracked, even partial failures Bug anthropics#3: Incorrect Cost Tracking - Fixed Agent 1 cost reading from wrong variable - Was: course_data.get("cost") (Agent 2's cost) - Now: url_result.get("cost") (Agent 1's cost) - Impact: Accurate budget tracking per agent Tested against production logs showing 3 failed courses. Expected: All should now complete with 1+ contacts. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
golfballnut
pushed a commit
to golfballnut/claude-agent-sdk-python
that referenced
this pull request
Oct 31, 2025
Created /business-context/ documentation capturing Links Choice B2B business model, service offerings, customer segmentation, and enrichment requirements. Key additions: - Company profile: Processing advantage (80% look-new recycling) - Service offerings by course tier (Tier 1-4 classification) - ICP: Tier 2 Premium Private CC (sweet spot) - Qualification scoring: 10-point system - Decision hierarchy: Authority mapping by service type - Data priorities: Water hazards (anthropics#1), range size, tier - Enhanced LLM prompt template: 7 required sections Transforms enrichment from contact discovery to opportunity qualification. 🤖 Generated with Claude Code Co-Authored-By: Claude <noreply@anthropic.com>
golfballnut
pushed a commit
to golfballnut/claude-agent-sdk-python
that referenced
this pull request
Oct 31, 2025
…try point Strategic shift based on market feedback: - Range ball opportunities (BUY/SELL/BOTH) now primary entry vs retrieval - Director of Golf elevated to primary contact (90% reachable, faster decisions) - Retrieval repositioned as expansion service (6-12 months post-entry) Key Changes: - NEW: entry-point-strategy.md - comprehensive buy/sell framework - UPDATE: data-priorities.md - range ball classification now anthropics#1 priority - UPDATE: workflow-mapping.md - new service recommendation logic (buy/sell first) - UPDATE: high-end-courses.md - reordered services, ball purchase anthropics#1 - UPDATE: low-end-courses.md - range sales anthropics#1 (50% savings message) - UPDATE: pricing-strategy.md - added ball purchase pricing ($0.15-0.25/ball) - UPDATE: decision-hierarchy.md - Director of Golf = primary entry contact - UPDATE: ideal-customer-profile.md - BOTH opportunities highest priority Why: - Retrieval crowded ("many companies calling daily"), low perceived value - Range balls: faster close (1-2 weeks vs 4-8), less competitive - BUY entry = zero friction (we pay them first), 80% upsell to full circle - BOTH opportunities = dual revenue streams, strongest lock-in Impact: - Priority matrix: BOTH (40%), High-pain SELL (30%), Premium BUY (20%) - Expected conversion: 60% close on purchase, 80% upsell to BOTH - Enrichment workflow now classifies and routes by opportunity type 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
ashwin-ant
added a commit
that referenced
this pull request
Jul 22, 2026
…ight (#1103) ## Summary Fixes #1088. A `result` frame marks the end of one **turn**, not the end of the **run**: a background Task keeps running past it and still needs stdin for hook and SDK-MCP control responses. `Query.wait_for_result_and_end_input()` closed stdin on the *first* result frame, which broke everything a still-running subagent needed afterwards: - its SDK-MCP tool calls failed with exactly **`"Stream closed"`** (the error reported in #1088), and - its **PreToolUse hooks were silently bypassed** — built-in tools kept executing with no hook callback delivered, so deny-gate hooks stopped gating. ## Reproduction Reproduced end-to-end against the live CLI (2.1.206) with `query()` + a PreToolUse hook + an in-process SDK-MCP server whose tool sleeps 12s, called from a `run_in_background: true` Task. Observed timeline on `main`: ``` [19.3s] parent turn ends → ResultMessage #1 → SDK closes stdin (task still running) [25s+] subagent's ToolSearch calls execute with NO PreToolUse callback (hooks silently bypassed) [~25s] subagent calls the SDK-MCP tool → tool_result is_error=true: "Stream closed" (×2 retries) [47.9s] ResultMessage #2 arrives (task completion wakes the parent for a follow-up turn) ``` The second result frame is the key observation: result frames are per-turn, so closing stdin on the first one is the bug. (On current CLI, two *sequential foreground* subagents — the issue's literal scenario — no longer emit intermediate result frames; background tasks are the deterministic trigger.) ## Fix Track in-flight tasks from the `task_started` / `task_notification` / terminal `task_updated` lifecycle frames (using the existing `TERMINAL_TASK_STATUSES`, whose docstring already prescribes exactly this clearing behavior), and only treat a result frame as run-ending when no tasks are in flight. Why not the issue's first suggestion (keep stdin open until `close()` whenever hooks/SDK-MCP are registered): the CLI in stream-json mode only exits on stdin EOF, so that would hang one-shot `query()` forever. The narrower rule preserves prompt closure: - no background tasks → behavior unchanged (first result still closes stdin; existing tests cover this), - background task in flight → stdin stays open; its completion wakes the parent for a follow-up turn that ends in another result frame, which closes stdin (this also makes *chained* background tasks work), - early process exit → the reader's `finally` still unblocks the waiter, so no new hang mode is introduced. ## Tests - `test_result_with_inflight_task_keeps_stdin_open` (parametrized over both drain frames: `task_notification` and terminal `task_updated` patch) — asserts stdin stays open across an intermediate result and closes on the first result with no tasks in flight. **Fails on current main**, passes with the fix. - `test_track_task_lifecycle_unit` — add/non-terminal/terminal/unknown-id/missing-id transitions. - Full suite: 1059 passed, 5 skipped (asyncio + trio); ruff and mypy clean. - E2E re-run of the reproduction against the live CLI with the fix: hook fires for the background subagent's calls, the SDK-MCP tool executes and returns its result, stdin closes exactly at the final result frame, run exits normally. Used AI assistance; reviewed and tested by me. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: shihyayou <shihyayouyou@gmail.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Co-authored-by: Ashwin Bhat <ashwin@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
claude code python sdk import