b2b381b9b3
W21: anthropic Stream+Tools + --prompt batch + sanitizer fix + plugin unit tests (W21.1-W21.6)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
CI / Sanitizer (ASan+UBSan) / ubuntu-24.04 (push) Has been cancelled
- W21.1: ci-sanitize preset 独立 Linux-clang + ci-threadsan (TSan)
- W21.2: anthropic tool_use content_block 解析 + configure 缓存 tools_json
- W21.3: --prompt 非交互批处理模式
- W21.4: session auto-save 失败告警 + 当前目录 fallback
- W21.5: smoke 补 tool_calls 边界用例 4 块 12 断言
- W21.6: anthropic 11 块 78 CHECK + deepseek 12 块 78 CHECK
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-27 20:40:58 +08:00
20ead86e88
W20: Tool Calling 闭环 + Stream+Tools + 回归测试 + session auto-save + ASan CI (W20.1-W20.6)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
CI / Sanitizer (ASan+UBSan) / ubuntu-24.04 (push) Has been cancelled
- W20.1: CLI tool_calls→execute→result→re-call 循环（5轮上限）
- W20.2: deepseek 流式 tool_calls 增量解析（configure 缓存，无 ABI break）
- W20.3: plugin_loader 回归测试 5 块 32 断言（路径/原子性/mock 日志）
- W20.4: plugin_loader ABI 契约校验（name/version/on_init 字段验证）
- W20.5: ASan/UBSan CMake preset + CI sanitizer job（PR-only Linux）
- W20.6: session auto-save（on_shutdown 写 %APPDATA%/dstalk/session.json）
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-27 20:15:00 +08:00
3250b5a8bf
W19: plugin_loader hardening — ABI try/catch, path validation, atomic IDs, CLI exit codes (W19.1-W19.5)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
Fixes: F-18.3-1 through F-18.3-5 (all CLOSED, findings registry at zero)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-27 19:34:43 +08:00
c545d16120
W18: context cleanup + CLI fixes + loader audit + CI matrix (W18.1-W18.4)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
- W18.1 (王测+林深): Remove g_max_tokens dead API, UTF-8 bounds protection, deduplicate token counting, 0xC0/0xC1 handling, add 13 test blocks (36 checks)
- W18.2 (赵码+朱晴): Fix /context no-session error message, /status 3-state connection display
- W18.3 (曹武+徐磊): plugin_loader security audit — 9 dimensions, rating C, 1 HIGH + 2 MEDIUM findings
- W18.4 (马奔+胡桐): CI dual-platform matrix (Ubuntu clang-18 + Windows clang-cl), ccache, build timing baseline
Build 0 error, ctest 5/5 pass, metadata check clean.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-27 19:09:21 +08:00
47082376ef
Wave 10: deep audits of 5 unaudited plugins, smoke regression set (W13.1-W13.6)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
- W13.1 anthropic_plugin (architect-yang, 497 lines): rated C. 6 C ABI
functions lack try/catch (§8 violation); my_chat leaks response_body on
error path; tool_use response silently dropped.
- W13.2 deepseek_plugin (engineer-sun, 486 lines): rated C+. 7 ABI entries
unprotected including json::parse paths (malformed JSON terminates);
SSE [DONE] sentinel match brittle; ~55% code overlap with anthropic
suggests an ai_plugin_base extraction.
- W13.3 network_plugin (qa-wang, 322 lines): rated C. CRITICAL: TLS
certificate verification fully disabled (set_verify_mode never called,
default verify_none accepts any cert) — all AI traffic incl. api_key
is MITM-vulnerable. DNS resolve has no timeout; catch lacks (...).
- W13.4 lsp_plugin (architect-huang, 749 lines): rated C. CRITICAL:
guaranteed deadlock at L519-526 → L547 (g_lsp_impl_start holds mutex
then calls g_lsp_impl_stop which re-locks the same non-recursive
mutex); 7 vtable funcs unprotected; server→client requests dropped.
- W13.5 session+tools (security-cao, 264+251 lines): rated D+/D. Path
traversal in builtin_file_read/write (zero validation); global
static state in both plugins lacks mutex (UAF risk); 9 vtable funcs
lack try/catch.
- W13.6 smoke regression (qa-xu, +193 lines): 4 new cases — context
max_tokens trim, config dual-store consistency (exposes that W12.2
merge is incomplete: dstalk_config_set→config_service.get returns
null), HTTP error path no-crash, repeated init/shutdown cycle.
Verified: cmake build 0 error 0 warning, ctest 4/4 pass.
Top W14 priorities surfaced: TLS verification (W13.3), LSP deadlock
(W13.4), file-tool path traversal (W13.5), config dual-store still
broken (W13.6 R2), shared try/catch wrapper across all AI plugins.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2026-05-27 09:32:13 +08:00
bb2e8c0220
Wave 8: tech-debt audits, core unit tests, CLI pipe input (W11.1-W11.7)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
- W11.1 context_plugin audit (architect-huang): 3 findings on ABI exception
safety, strdup null checks, dead g_max_tokens variable. Rating: B.
- W11.2 config audit (engineer-chen): identified 74-line TOML parser
duplication between config_plugin and config_store, dual-store data
isolation, dangling c_str() risk. Rating: C.
- W11.3 event_bus + service_registry unit tests (qa-liu): 12 cases total,
ctest coverage 2 -> 4 targets, 100% pass.
- W11.4 CLI stdin pipe mode (engineer-zhao): isatty detection, single-shot
inference path with exit codes 0/1/2/3.
- W11.6 scripts/refresh_status.py (engineer-li): 431-line generator that
scans 16 profile.md + 5 group.md to regenerate STATUS.md.
- W11.7 destructive testing (qa-xu): 10 input scenarios PASS, found bin
copy mismatch (BUG-1) plus 3 minor UX bugs for follow-up.
Verified: cmake build 0 error, ctest 4/4 pass.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2026-05-27 09:06:25 +08:00
004a81db96
Wave 7: collaboration framework hardening (W10.1-W10.4)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
Pure agents/ documentation work — first contributions from 4
previously-idle members (yang/li/zhu/xu).
- W10.1 yang: WORKFLOW §11-§13 — collaboration state machine
(9 states / 16 transitions), 10-item acceptance checklist,
7-scenario failure rollback playbook (+227 lines)
- W10.2 li: agents/STATUS.md — live roster + group + Wave
progress snapshot (65 lines)
- W10.3 zhu: agents/PROMPT_TEMPLATE.md — subagent prompt
template with 6 anti-patterns + 1 worked example +
4-step pre-dispatch checklist (193 lines)
- W10.4 xu: agents/POSTMORTEM.md — 5 incident records
(PM-001 stale-obj, PM-002 boost-json, PM-003 cross-DLL-heap,
PM-004 loader-fail-fast, PM-005 push-force) + 7 defensive
rules (172 lines)
No code changes. WORKFLOW.md §9 has a pointer to the new
PROMPT_TEMPLATE.md. STATUS.md updated to reflect W10.1
completion (yang status flipped working→idle).
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2026-05-27 05:52:02 +08:00
4433218853
Add multi-agent collaboration system with 16-person team and two-tier governance
...
- agents/README.md documents company principles (first principles + practical
delivery), 6-stage collaboration flow, and two-tier governance: CEO has
highest priority and final say; work groups self-govern internally for
staffing, scheduling, technical choices within CEO-defined boundaries.
- 16 employees recruited to match CPU physical core count, enabling up to
16 subagents to run in parallel. Each profile.md has independent name,
background, strengths, weaknesses, and performance log.
- Roles: 1 CEO, 3 architects (lin/yang/huang), 5 engineers (zhao/chen/li/
zhou/sun), 3 QA (wang/liu/xu), 2 DevOps (ma/hu), 1 designer (zhu),
1 writer (deng), 1 security (cao).
- Five working groups defined under agents/groups/: grp-quality-core,
grp-ai-plugins, grp-cli-ux (B3), grp-build-matrix, grp-security-audit.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2026-05-27 05:13:12 +08:00
