pulsareon/dstalk
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
17 Commits 1 Branch 0 Tags
47082376efaddd1897243204e57ead39eaac6a97
Commit Graph

6 Commits

Author SHA1 Message Date
XiuChengWu
47082376ef Wave 10: deep audits of 5 unaudited plugins, smoke regression set (W13.1-W13.6)
Some checks failed
CI / Determine matrix (push) Has been cancelled
Details
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
Details 
- 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
XiuChengWu
58869abc15 Wave 9: fix audit findings, harden ABI, deduplicate config (W12.1-W12.6)
Some checks failed
CI / Determine matrix (push) Has been cancelled
Details
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
Details 
- W12.1 context_plugin (engineer-zhou): wrap C ABI surface in try/catch,
  add OOM-safe strdup_message_fields helper, make g_max_tokens drive
  message-count trim (option A).
- W12.2 config refactor (architect-lin): introduce
  plugins/config/include/toml_parse.h to eliminate 74-line parser
  duplication; config_plugin delegates to host->config_get/set,
  collapsing the dual-store data island; ConfigStore::get() now copies
  via thread_local std::string to remove c_str() dangling under
  concurrent set(). Zero ABI changes.
- W12.3 CLI command parsing (engineer-zhao): guard /clear and /context
  on missing session service; refactor /file dispatch so bare
  /file write hits usage instead of unknown-command.
- W12.4 build path unification (devops-hu): set per-target
  RUNTIME_OUTPUT_DIRECTORY on dstalk-cli; remove stale
  build/dstalk-cli/dstalk-cli.exe so build/bin/ is the sole binary.
- W12.5 STATUS.md auto-refresh (engineer-li): run W11.6 script to
  regenerate STATUS from live profile/group data.
- W12.6 plugin-abi.md (writer-deng): add §8 exception safety across
  ABI boundary and §9 string return lifetime; reference real
  audit-found violations as anti-examples.

Verified: cmake build 0 error 0 warning, ctest 4/4 pass.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2026-05-27 09:19:17 +08:00
XiuChengWu
bb2e8c0220 Wave 8: tech-debt audits, core unit tests, CLI pipe input (W11.1-W11.7)
Some checks failed
CI / Determine matrix (push) Has been cancelled
Details
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
Details 
- 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
XiuChengWu
004a81db96 Wave 7: collaboration framework hardening (W10.1-W10.4)
Some checks failed
CI / Determine matrix (push) Has been cancelled
Details
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
Details 
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
XiuChengWu
5766938524 Wave 5+6: plugin ABI hardening, build modernization, ABI/security docs
Some checks failed
CI / Determine matrix (push) Has been cancelled
Details
CI / ${{ matrix.os }} / ${{ matrix.build_type }} (push) Has been cancelled
Details 
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
XiuChengWu
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