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
852e2cac08
W17: close 9 audit findings — atomic pointers, SSE robustness, leak fix, verification (W17.1-W17.4)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
- W17.1 (曹武): Verify F-13.3-1/2/3 all fixed by W14.1, close 3 findings (1 CRITICAL + 1 HIGH + 1 MEDIUM)
- W17.2 (赵码): Fix F-13.2-3 SSE [DONE] sentinel trimming + F-13.2-4 g_host/g_http/g_config atomic pointers in deepseek_plugin
- W17.3 (王测): Verify 4 W14 findings (F-13.1-1/4, F-13.2-1/2) + F-11.7-2 confirmed fixed, close 5 findings
- W17.4 (马奔): Fix F-13.1-2 response_body leak on error path + F-13.1-3 g_host/g_http atomic pointers in anthropic_plugin
Build 0 error, ctest 4/4 pass, metadata check clean.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-27 18:56:12 +08:00
f010af6c07
W15: conflict resolution — E7 CRITICAL gate, T11/T18 audit refs, §5 metadata check, PROMPT_TEMPLATE Fixes (W15.4-W15.9)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
- W15.4 (杨帆): §11/§14 cross-reference audit — PASS-WITH-NOTES, 3 fixes needed
- W15.5 (王测): §14 internal consistency — PASS-WITH-NOTES, 4 fixes needed
- W15.6 (胡桐): self-check script + YAML verification — PASS
- W15.7 (杨帆): Add E7 (no OPEN CRITICAL) to EXPRESS conditions, update T11 to include §14.4 A1-A4, add T18 finding status in §14.5
- W15.8 (王测): Fix findings-registry Close Date, add historical finding time-limit rule, add legacy audit Findings Summary note, add Fixes annotation to PROMPT_TEMPLATE
- W15.9 (胡桐): Fix false-positive warning in check_agents_metadata.py (skip audits/ dir), add metadata check to §5
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-27 18:33:02 +08:00
0e41c8c6f6
W15: workflow improvements — EXPRESS fast-path, audit→fix closed loop, metadata self-check (W15.1-W15.3)
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
- W15.1 (杨帆): Add EXPRESS fast-path to §11 state machine (T17/T18, E1-E6 conditions, escalation safety valve)
- W15.2 (王测): Add §14 audit→fix closed loop — findings-registry.md, severity-driven auto-triage, CRITICAL blocking rule
- W15.3 (胡桐): Create scripts/check_agents_metadata.py (5-check: YAML parse, rating range, group/member refs, duplicate IDs)
- Fix YAML orphan bugs in 3 profiles: devops-hu, engineer-sun, security-cao (perf_log entries outside array)
- Pre-fill findings-registry.md with 10 historical findings from W11.1/W11.7 audits
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-27 18:19:37 +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
5766938524
Wave 5+6: plugin ABI hardening, build modernization, ABI/security docs
...
CI / Determine matrix (push) Has been cancelled
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
Wave 5 (9 parallel agents):
- W1.1 atomic diag callback + DLL handle release on shutdown (lin)
- W2.1 unify cross-DLL heap discipline (host->alloc/free/strdup) (chen)
- W2.2 secure_zero api_key on shutdown for deepseek/anthropic (cao)
- W3 CMake modernization: target-based cxx_std_20, dstalk_boost_config
INTERFACE lib, root-level RUNTIME_OUTPUT_DIRECTORY (hu)
- W4 GitHub Actions CI with dynamic Linux/Windows matrix (ma)
- W5.1 SSE buffer_body to cut peak memory ~67% on 32K streams (zhou)
- W6.1 LSP JSON-RPC frame parser hardened against header reordering (sun)
- W7 smoke test: copy plugin DLLs post-build + Boost.JSON src.hpp fix
for full 9-plugin load coverage (wang)
- W8.1 README slimmed 398->92, Diataxis docs/ skeleton (deng)
Wave 6 (6 parallel agents):
- W9.1 docs/explanation: architecture + plugin-lifecycle (deng)
- W9.3 log credential leak audit (0 vulns, audit trail in
docs/explanation/security-logging.md) (cao)
- W9.4 docs/reference/plugin-abi.md - 7-point ABI contract (lin)
- W9.6 CLI /history command + status integration (zhao)
- W9.8 plugin_loader fault tolerance: per-plugin failure no longer
aborts dstalk_init (huang)
- W9.10 host_api unit tests: tests/host_api_test.cpp, 8 cases (liu)
CEO oversight (preexisting bugs fixed during Wave 5 verification):
- lsp_plugin.cpp:449 forward decl mismatch (int vs void)
- tools_plugin.cpp:109 missing forward decl
Multi-agent collaboration framework:
- agents/WORKFLOW.md: 6-stage protocol, two-tier governance,
prompt template, technical constraints registry
Build: cmake --build 0 error / 0 warning. Tests: 2/2 100% pass.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2026-05-27 05:39:10 +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
