| commit |
1.00 |
fix(ci): lower Linux release glibc baseline (#707) |
|
Commit message contains explicit AI assi |
2026-07-10 |
| commit |
1.00 |
fix(logging): keep verbose openai.agents DEBUG off sandbox s |
|
Commit message contains explicit AI assi |
2026-07-10 |
| pr |
0.30 |
feat: add resume session feature (Claude Code-inspired appen |
|
Technical but with minor 'inspired by' p |
2026-04-26 |
| pr |
0.30 |
fix: resolve workspace materialization race on Windows (#671 |
|
Slightly formal, but mostly technical an |
2026-07-05 |
| pr |
0.25 |
feat: add weak password detection skill (#621) |
|
Detailed changelog and domain terms; cut |
2026-07-03 |
| pr |
0.20 |
fix(agents): force tty for exec_command on Windows |
|
Long, technical explanation using domain |
2026-07-11 |
| pr |
0.20 |
fix: strip chatgpt transcript tags from agent messages |
|
Summary plus technical detail, red/green |
2026-07-10 |
| pr |
0.20 |
feat: add opt-in completion nudge |
|
Contains domain details and a concise su |
2026-07-10 |
| pr |
0.20 |
Add Configurable LLM Request Timeout via Environment Variabl |
|
Detailed, but domain-specific and reads |
2025-11-12 |
| pr |
0.20 |
Feature/configurable memory compression |
|
Detailed changelog but with domain conte |
2026-04-16 |
| pr |
0.20 |
Fix: Add macOS Docker socket detection fallback (Fixes #164) |
|
Technical, structured explanation with s |
2025-12-12 |
| pr |
0.20 |
Fix: tool events colliding across agents and status regressi |
|
Contains domain-specific issues and info |
2026-07-03 |
| pr |
0.20 |
fix: serialize vulnerability dedup check-then-write with an |
|
Domain-specific async discussion, inform |
2026-07-02 |
| pr |
0.20 |
fix(bedrock): give Claude an explicit, clamped output ceilin |
|
Technical, has error output and root cau |
2026-07-02 |
| pr |
0.15 |
feat(skills): expand llm_prompt_injection with Model DoS and |
|
Technical writing with jargon, some trun |
2026-07-11 |
| pr |
0.10 |
Add skill directory registration |
|
Technical changelog with domain details |
2026-07-12 |
| pr |
0.10 |
Allow root scan prompt options |
|
Clear domain jargon, references to test |
2026-07-10 |
| pr |
0.10 |
Allow scan agents to register extra tools |
|
Structured like human-written engineerin |
2026-07-10 |
| pr |
0.10 |
fix: skip Unix permission test on Windows (#648) |
|
Concise, domain-specific, natural tone; |
2026-07-03 |
| pr |
0.10 |
fix: prevent context-window crash from huge tool outputs |
|
Concise, colloquial fixes and TUI refere |
2026-07-11 |
| pr |
0.10 |
fix(core): compile fallback report if agent misses lifecycle |
|
Domain-specific issue with environment d |
2026-07-03 |
| pr |
0.10 |
fix: propagate sandbox proxy environment aliases |
|
Technical, domain-specific details and t |
2026-07-10 |
| pr |
0.10 |
Fix ordered-list spacing in TUI markdown renderer |
|
Human-like, domain-specific list and tes |
2026-07-10 |
| pr |
0.10 |
fix: recover from BadRequestError caused by oversized payloa |
|
Domain-specific, with examples and infor |
2026-04-20 |
| pr |
0.10 |
feat: add MiniMax as LLM provider (M3 default, with M2.7 fal |
|
Technical, concise, some template use, n |
2026-03-23 |
| pr |
0.10 |
feat: Add live tracing mode for complete audit trail |
|
Structured, technical, clear human inten |
2026-02-03 |
| pr |
0.10 |
feat: add graceful wrap-up command for agents |
|
Clear, detailed, some template but human |
2026-01-04 |
| pr |
0.10 |
Adds scan resumption capability to Strix, allowing users to |
|
Template-driven, clear, and domain-speci |
2026-01-02 |
| pr |
0.10 |
feat(prompts): add 6 new vulnerability prompt modules |
|
Technical, some template, detailed with |
2025-12-21 |
| pr |
0.10 |
security: fix token exposure, info disclosure, and path vali |
|
Domain-specific, explicit security refer |
2025-12-21 |
| pr |
0.10 |
test: add unit tests for llm/utils module |
|
Contains conversational quoting and ters |
2025-12-05 |
| pr |
0.10 |
Dane/strix resumable execution |
|
Informal note about missing code; lacks |
2025-11-20 |
| pr |
0.10 |
Add proxy support for corporate networks |
|
Human-typical explanation and usage of d |
2025-11-06 |
| pr |
0.10 |
fix(interface): clarify cached vs new input token breakdown |
|
Terse, technical, and matches typical en |
2026-07-05 |
| pr |
0.10 |
feat(config): accept GROQ_API_KEY for Groq-hosted models |
|
Detailed, uses technical jargon, and ali |
2026-07-03 |
| pr |
0.10 |
fix(tests): skip symlink test gracefully when creation is un |
|
Domain-specific, direct, and concise pro |
2026-07-03 |
| pr |
0.10 |
Fix Bedrock/Claude startup crash from forced parallel_tool_c |
|
Contains technical explanations and clea |
2026-07-03 |
| pr |
0.10 |
Add non-mutating quality check target |
|
Uses bullet points and informal notes, c |
2026-07-03 |
| pr |
0.10 |
feat: implement retry logic for restartable stream errors in |
|
Technical focus, no AI signals; logs and |
2026-07-01 |
| pr |
0.10 |
fix(proxy): recompute Content-Length when repeat_request rep |
|
Technical details, reproduction steps, h |
2026-06-29 |
| pr |
0.10 |
fix(interface): drop dead reasoning-effort branches, fix sta |
|
Technical, error-focused, with terse com |
2026-06-26 |
| pr |
0.10 |
fix: declare socksio and guard tracing init against SOCKS-pr |
|
Detailed technical bugfix writeup, human |
2026-06-26 |
| pr |
0.10 |
fix(interface): correct copy-diff classification and workspa |
|
Jargon, specific content, informal headi |
2026-06-26 |
| pr |
0.10 |
fix(core): return True when image-strip retry succeeds in st |
|
Casual, precise language, natural gramma |
2026-06-26 |
| pr |
0.10 |
fix(interface): exit cleanly on unhandled LLM BadRequestErro |
|
Describes specific fix and test context, |
2026-06-26 |
| pr |
0.10 |
Handle large exec_command output and surface scan errors as |
|
Well-structured technical PR; merges con |
2026-06-22 |
| pr |
0.10 |
Migrate task runner from Makefile to mise |
|
Human summary and change breakdown; natu |
2026-06-19 |
| pr |
0.10 |
fix(proxy): actionable errors for bad list_requests/list_sit |
|
Error-context is domain-specific, tone i |
2026-06-15 |
| pr |
0.10 |
added disposable email skill |
|
Domain-specific, structured by template, |
2026-06-11 |
| pr |
0.10 |
Fix Bedrock reasoning for adaptive-thinking models (Claude O |
|
Specific root-cause, error message, doma |
2026-06-09 |
| pr |
0.10 |
Feat/secure credentials |
|
Uses technical detail and domain terms; |
2026-06-09 |
| pr |
0.10 |
Honor LLM_TIMEOUT, expose generation params, and harden blac |
|
Direct, technical; mentions explicit mai |
2026-06-09 |
| pr |
0.10 |
Add Podman as working runtime backend |
|
Technical summary, proper jargon, not ov |
2026-05-28 |
| pr |
0.10 |
Fix memory compressor timeout fallback |
|
Casual explanation, jargon, some typos, |
2026-05-26 |
| pr |
0.10 |
perf(tui): fix CPU lockup and O(N) scans during waiting/runn |
|
Technical details, informal, with incomp |
2026-05-22 |
| pr |
0.10 |
[codex] clarify Vertex AI env vars |
|
Nuanced domain detail, technical referen |
2026-05-21 |
| pr |
0.10 |
Add Codex OAuth provider |
|
Technical summary, CLI/integration detai |
2026-05-12 |
| pr |
0.10 |
fix: update vulnerable dependencies |
|
Domain-specific explanations, test comma |
2026-05-07 |
| pr |
0.10 |
Add custom headers from the env var LLM_EXTRA_HEADERS |
|
Technical, references config/environment |
2026-05-05 |
| commit |
0.05 |
feat(report): SARIF 2.1.0 emitter for CI / code-scanning int |
|
Technical commit with domain-specific te |
2026-07-03 |
| commit |
0.05 |
Add five security skills: OAuth, AWS, prototype pollution, d |
|
Technical, uses domain terms and informa |
2026-07-03 |
| pr |
0.05 |
fix(tests): skip symlink test when Windows lacks privilege |
|
Terse, direct commit message with platfo |
2026-07-11 |
| pr |
0.05 |
perf(runtime): import local sources via single tar put_archi |
|
Short, technical, focused summary; no AI |
2026-07-11 |
| pr |
0.05 |
feat: browser-use tool migration |
|
Informal, uses jargon, natural phrasing, |
2026-03-11 |
| pr |
0.05 |
feat: dynamic skill loading tools |
|
Very terse, informal, with domain-specif |
2026-03-05 |
| pr |
0.05 |
Feat: add traces in posthog + support for 2 accounts |
|
Informal, with typos and domain context, |
2026-01-18 |
| pr |
0.05 |
feat: Firecrawl web search integration |
|
Informal, has purpose/reasoning, natural |
2025-12-30 |
| pr |
0.05 |
expand docs folder README for contributors |
|
Rich in project specifics, terse, no AI |
2026-07-02 |
| pr |
0.05 |
Add CORS misconfiguration skill (vulnerabilities) |
|
Uses domain jargon, clear structure, no |
2026-07-01 |
| pr |
0.05 |
Recompute Content-Length when repeat_request replaces body |
|
Highly technical, focused, no generic AI |
2026-07-01 |
| pr |
0.05 |
feat: add STRIX_DISABLE_FIX_AGENTS to skip dedicated fix sub |
|
Project-specific context, technical, no |
2026-06-29 |
| pr |
0.05 |
fix: prevent long scans from hanging or dying on fd exhausti |
|
Detailed, technical explanation with rep |
2026-06-29 |
| commit |
0.00 |
Use core LiteLLM dependency (#752) |
|
Terse commit message, domain-specific la |
2026-07-12 |
| commit |
0.00 |
Add dependency reporting fields (#751) |
|
Short, domain-specific commit without AI |
2026-07-12 |
| commit |
0.00 |
fix(deps): cap openai<2.45 and add litellm[proxy] so fresh i |
|
Contains a human email Git trailer, no A |
2026-07-12 |
| commit |
0.00 |
Add root scan prompt options (#750) |
|
Brief, technical commit message, no gene |
2026-07-12 |
| commit |
0.00 |
Add skill directory registration (#746) |
|
Direct and technical language, likely hu |
2026-07-12 |
| commit |
0.00 |
Allow scan agent tool registration (#733) |
|
Short, informal, and to the point, clear |
2026-07-12 |
| commit |
0.00 |
Support routed OpenAI required tool choice (#732) |
|
Brief changelog, no signals of AI phrasi |
2026-07-10 |
| commit |
0.00 |
feat(settings): add force_required_tool_choice to LlmSetting |
|
Standard conventional commit style, doma |
2026-07-10 |
| commit |
0.00 |
Address Greptile review: GCP and Auth0 recon guidance |
|
Uses domain-specific language and concis |
2026-07-04 |
| commit |
0.00 |
Add GCP and Auth0 security skills |
|
Expands technical coverage; no AI-style |
2026-07-03 |
| commit |
0.00 |
fix(providers): match google submodule imports and walk full |
|
Contains a human co-author, matches typi |
2026-07-10 |
| commit |
0.00 |
test(providers): cover wrapped bedrock import errors |
|
Terse, targeted test message without AI |
2026-07-07 |
| commit |
0.00 |
fix(providers): show vertex extra hint for wrapped import er |
|
Brief and technical, typical of human co |
2026-07-07 |
| commit |
0.00 |
fix(tui): key render cache by content string and return copi |
|
— |
2026-07-10 |
| commit |
0.00 |
fix(tui): reduce scroll stutter by throttling UI refresh and |
|
Detailed technical breakdown, natural hu |
2026-07-02 |
| commit |
0.00 |
fix(report): omit SARIF provenance for multiple repos (#726) |
|
Short and domain-specific, no signals of |
2026-07-10 |
| commit |
0.00 |
fix(container): allow configured Caido UI domains (#723) |
|
Terse fix description, standard for huma |
2026-07-10 |
| commit |
0.00 |
fix(session): use HTTPS scheme for Caido endpoint if TLS is |
|
Concise commit message with domain refer |
2026-07-10 |
| commit |
0.00 |
fix(runtime): swallow torn-down docker socket in sandbox del |
|
Technical, detailed, domain-specific tro |
2026-07-10 |
| commit |
0.00 |
fix(providers): declare bedrock + vertex extras and add prov |
|
Contains changelog and domain-specific r |
2026-07-07 |
| commit |
0.00 |
Add target list CLI option (#711) |
|
Short, informal message; lacks AI-genera |
2026-07-07 |
| commit |
0.00 |
feat(report): tag SARIF rules with STRIDE legs derived from |
|
Domain-specific details, SARIF/CWE/STRID |
2026-07-07 |
| commit |
0.00 |
test: add report writer artifact tests (#667) |
|
Direct, summary message in domain jargon |
2026-07-06 |
| commit |
0.00 |
fix(config): make env vars win over persisted JSON across al |
|
Highly technical, informal, and specific |
2026-07-06 |
| commit |
0.00 |
Update README (#705) |
|
Generic but concise 'Update README'; not |
2026-07-06 |
| commit |
0.00 |
Add LLM Prompt Injection skill (vulnerabilities) (#616) |
|
Direct, brief, task-focused; no AI signa |
2026-07-06 |
| commit |
0.00 |
fix(tui): show 'more content available' for view_request ove |
|
Concise, direct feature implementation s |
2026-07-06 |
| commit |
0.00 |
fix: report cost for streamed OpenRouter calls (#634) |
|
Terse, domain-specific; standard enginee |
2026-07-03 |
| commit |
0.00 |
fix: avoid note ID collisions (#630) |
|
Minimal, terse commit message; typical o |
2026-07-03 |
| commit |
0.00 |
fix grammer (#642) |
|
Short, contains typos; strong human indi |
2026-07-03 |
| commit |
0.00 |
fix(report): correct csv_path indentation in write_vulnerabi |
|
Detailed, but specific and technical; in |
2026-07-02 |
| commit |
0.00 |
Fix non-atomic CSV and MD writes to prevent corruption on cr |
|
Technical, concise; no AI hallmarks. |
2026-07-02 |
| commit |
0.00 |
test: add unit tests for config loader (strix/config/loader. |
|
Typical short test addition commit; huma |
2026-06-30 |
| commit |
0.00 |
Remove collection of unhandled exception error messages from |
|
Concise standard removal message; very h |
2026-06-30 |
| commit |
0.00 |
chore(deps): refresh uv.lock to latest compatible versions ( |
|
Chore commit, follows standard dep updat |
2026-06-30 |
| commit |
0.00 |
Update readme (#607) |
|
Very brief commit title; no AI hallmarks |
2026-06-30 |
| commit |
0.00 |
Readme update |
|
Minimal message; no signs of AI-generate |
2026-06-30 |
| commit |
0.00 |
fix: stop gracefully with resume hint on persistent RateLimi |
|
Technical, concise, and matches typical |
2026-06-29 |
| commit |
0.00 |
fix(core): collapse child agent initial input into a single |
|
Technical commit format; terse and domai |
2026-06-29 |
| commit |
0.00 |
Support large target repos with with bind-mount option. (#57 |
|
Detailed changelog with domain-specific |
2026-06-22 |
| commit |
0.00 |
Add configurable token / cost usage limits (#576) |
|
Technical, uses domain jargon and concre |
2026-06-22 |
| commit |
0.00 |
fix: route ollama models through ollama_chat so tool calling |
|
Standard technical commit with co-author |
2026-06-16 |
| commit |
0.00 |
Bump 1.0.3 -> 1.0.4 (#557) |
|
Version bump; no stylistic signals of AI |
2026-06-09 |
| commit |
0.00 |
Strip ANSI escapes and control bytes from terminal tool outp |
|
Terse, task-focused phrasing typical of |
2026-06-09 |
| commit |
0.00 |
Strip all images from session on vision-rejection, not just |
|
Brief, direct message; human engineering |
2026-06-09 |
| commit |
0.00 |
Swallow sandbox container races in the stream consumer (#552 |
|
Terse and technical commit title, no AI |
2026-06-09 |
| commit |
0.00 |
Make TUI quit instant by SIGKILL-ing the sandbox container ( |
|
Brief, technical, and human-written comm |
2026-06-09 |
| commit |
0.00 |
Bump 1.0.2 -> 1.0.3 (#537) |
|
Standard version bump message, not AI-ge |
2026-06-09 |
| commit |
0.00 |
Simplify cost ledger to one bucket (#531) |
|
Concise, technical commit title with no |
2026-06-08 |
| commit |
0.00 |
Use observed LiteLLM cost for LiteLLM-routed calls (#529) |
|
Detailed technical description with jarg |
2026-06-08 |
| commit |
0.00 |
Gate Reasoning(effort=...) on registry support (#528) |
|
Technical, filled with abbreviations and |
2026-06-08 |
| commit |
0.00 |
Show "Send message to resume" on the left of the status bar |
|
Short, informal commit title; no AI trai |
2026-06-08 |
| commit |
0.00 |
Use function-tool schema for non-reasoning OpenAI models |
|
Technical narrative with domain jargon; |
2026-06-08 |
| commit |
0.00 |
Bump litellm 1.83.7 -> 1.88.0 |
|
Standard library version bump, typical h |
2026-06-07 |
| commit |
0.00 |
Suppress LiteLLM stdout banner spam |
|
Technical, developer-focused explanation |
2026-06-07 |
| commit |
0.00 |
Pre-warm-up unknown-model warning + LiteLLM streaming harden |
|
Detailed, technical, informal style; dom |
2026-06-07 |
| commit |
0.00 |
Strip model-aware branches from LLM configuration |
|
Domain-specific detail, concise bullet p |
2026-06-07 |
| commit |
0.00 |
Stop exposing litellm/ prefix in user-facing model names |
|
Domain jargon and technical explanations |
2026-06-07 |
| commit |
0.00 |
Drop tool_choice for registry-unknown reasoning-effort runs |
|
Technical explanation with domain exampl |
2026-06-07 |
| commit |
0.00 |
Hint at provider prefix when bare model 401s against OpenAI |
|
Technical, focused explanation; contains |
2026-06-07 |
| commit |
0.00 |
Use validate_environment to resolve provider env var |
|
Highly technical, informal, and domain-s |
2026-06-07 |
| commit |
0.00 |
Cover bare claude-/gemini- shorthands in env mirror |
|
Addresses edge cases with technical deta |
2026-06-07 |
| commit |
0.00 |
Mirror LLM_API_KEY to provider env var (closes #504) |
|
Technical, contains code context, human |
2026-06-07 |
| commit |
0.00 |
fix: gate reasoning_effort by LiteLLM model registry (closes |
|
Standard commit prefix; no free-text to |
2026-06-07 |
| commit |
0.00 |
fix: SDK tracing leak + orphan docker on TUI quit (closes #5 |
|
Standard commit prefix; purely templated |
2026-06-07 |
| commit |
0.00 |
fix: reasoning models reject tool_choice=required; bump to 1 |
|
Brief commit message with domain specifi |
2026-05-28 |
| commit |
0.00 |
fix: PyInstaller bundle is broken (missing agents SDK data + |
|
Terse technical content, specific to rep |
2026-05-27 |
| commit |
0.00 |
Strix v1.0.0 release |
|
Release note, succinct and specific; lac |
2026-05-26 |
| commit |
0.00 |
Bump to 1.0.0 |
|
Structured changelog, terse; clear human |
2026-05-26 |
| commit |
0.00 |
Strip narrative comments and module/helper docstrings |
|
Bulleted, technical removals; domain-spe |
2026-05-26 |
| commit |
0.00 |
Tighten tool surface consistency |
|
Technical, concise summary; reflects foc |
2026-05-26 |
| commit |
0.00 |
Collapse todo tools to a single list-based form |
|
Detailed API change with informal note; |
2026-05-26 |
| commit |
0.00 |
Add TUI renderers for the seven previously-unstyled tools |
|
Technical, domain-specific description o |
2026-05-26 |
| commit |
0.00 |
Add Scarf telemetry alongside PostHog |
|
Direct, technical, references implementa |
2026-05-26 |
| commit |
0.00 |
Document the SDK-provided tools as stub dirs under strix/too |
|
Deep repo knowledge, informal tone, repo |
2026-05-26 |
| commit |
0.00 |
Surface the previously-undocumented sandbox tools and unbrea |
|
Detailed, concise, with domain-specific |
2026-05-26 |
| commit |
0.00 |
Stabilize agent-browser launch and screenshot routing |
|
Uses technical detail and informal tone |
2026-05-26 |
| commit |
0.00 |
Drop prescriptive guidance from image-rejection placeholder |
|
Direct, editing-focused, domain-aware ph |
2026-05-26 |
| commit |
0.00 |
Auto-recover when the provider rejects a view_image output |
|
Technical steps and abbreviations, not C |
2026-05-26 |
| commit |
0.00 |
Restore load_skill + surface skill catalog in system prompt |
|
Technical, references code structure and |
2026-05-25 |
| commit |
0.00 |
Clean up SDK shell tool failure modes |
|
Heavily technical, uses specific program |
2026-05-25 |
| commit |
0.00 |
Stop web_search from leaking upstream details into tool resu |
|
Details root cause and resolution in dir |
2026-05-25 |
| commit |
0.00 |
Agents graph sweep: status taxonomy, stop_agent safety, skil |
|
Structured commit-note style, specific a |
2026-05-25 |
| commit |
0.00 |
Document HTTPQL footguns on list_requests |
|
Domain-specific language, concise, not f |
2026-05-25 |
| commit |
0.00 |
Restore sitemap tools + unify proxy I/O contract |
|
Focused, technical, and domain-specific |
2026-05-25 |
| commit |
0.00 |
Proxy tool sweep: drop send_request, fix Caido SDK gotchas |
|
Technical, domain-specific changelog wit |
2026-05-25 |
| commit |
0.00 |
Align note IDs with todo IDs (6-char hex) |
|
Concise, technical summary with abbrevia |
2026-05-25 |
| commit |
0.00 |
Tighten todo + think tool contracts |
|
Direct, technical, with casual phrasing |
2026-05-24 |
| commit |
0.00 |
feat: add HTTP request smuggling skill (#405) |
|
Detailed but domain-focused; no AI hallm |
2026-05-21 |
| commit |
0.00 |
Add Docker sandbox host mappings (#488) |
|
Technical commit message and review note |
2026-05-19 |
| commit |
0.00 |
Fix MiniMax tool calling (#456) |
|
Concise, technical fix message with co-a |
2026-05-04 |
| commit |
0.00 |
perf(agent): wake on state change instead of 500ms polling ( |
|
Technical message with perf tag, domain- |
2026-05-04 |
| commit |
0.00 |
add empty-array IDOR FP and OAST source-IP SSRF FP signals ( |
|
Abbreviated, domain-specific; typical of |
2026-05-04 |
| commit |
0.00 |
Add SSTI and Header Injection vulnerability skills (#191) |
|
Direct feature description, domain jargo |
2026-05-04 |
| commit |
0.00 |
fix(llm): include system prompt tokens in memory compressor |
|
Technical fix with domain context, inclu |
2026-05-03 |
| commit |
0.00 |
feat: add Novita AI as LLM provider (#385) |
|
Commit message with GitHub trailer indic |
2026-05-03 |
| pr |
0.00 |
Use core LiteLLM dependency |
|
Well-structured PR but style is human, n |
2026-07-12 |
| pr |
0.00 |
Add dependency reporting fields |
|
Structured, technical; detailed but not |
2026-07-12 |
| pr |
0.00 |
fix(deps): cap openai<2.45 and add litellm[proxy] so fresh i |
|
Detailed technical explanation with user |
2026-07-12 |
| pr |
0.00 |
Allow root scan prompt options |
|
Technical details, no excessive formalit |
2026-07-12 |
| pr |
0.00 |
fix: reject submit-only XSS false positives |
|
Terse, domain-specific language, issues |
2026-07-12 |
| pr |
0.00 |
David max aicode patch 1 |
|
Trivial, bare commit title; typical of h |
2026-07-11 |
| pr |
0.00 |
feat(tui): add manual compact command |
|
Has concise structure and test info; no |
2026-07-07 |
| pr |
0.00 |
code sync |
|
Minimal commit message, classic human pa |
2026-07-11 |
| pr |
0.00 |
Support routed OpenAI required tool choice |
|
Detailed, domain-specific, naturally wri |
2026-07-10 |
| pr |
0.00 |
feat(settings): add force_required_tool_choice to LlmSetting |
|
Terse commits with dev abbreviations and |
2026-07-10 |
| pr |
0.00 |
Feature/skill merge idor |
|
Minimalistic, lacks AI-style phrasing or |
2026-07-10 |
| pr |
0.00 |
fix: better whitebox wiki |
|
Highly terse, minimal, no signs of AI ge |
2026-03-31 |
| pr |
0.00 |
feat: add file-based config and web api workflow |
|
Very brief commit, nothing AI-like in to |
2026-03-25 |
| pr |
0.00 |
FIX Strix fails to connect to Docker on macOS |
|
Concise, human-style commit summary; no |
2025-12-06 |
| pr |
0.00 |
Implement architectural upgrades for advanced red-teaming |
|
Plain bullet-list changelog, standard te |
2025-12-01 |
| pr |
0.00 |
fix(tui): remove double space after numbered-list marker |
|
Very technical with clear human rational |
2026-07-04 |
| pr |
0.00 |
fix: join root task sections with newlines |
|
Technical description, natural justifica |
2026-07-04 |
| pr |
0.00 |
fix(proxy): preserve existing query params when replaying re |
|
Concise, technical, with domain-specific |
2026-07-04 |
| pr |
0.00 |
fix(telemetry): stop finding() telemetry from blocking the a |
|
Informal, specific references, incomplet |
2026-07-04 |
| pr |
0.00 |
feat(skills): resolve-time path containment for load_skills |
|
Domain jargon, technical details, human- |
2026-07-04 |
| pr |
0.00 |
fix(config): atomic write + 0o600 enforcement in persist_cur |
|
Technical, with detailed steps, specific |
2026-07-04 |
| pr |
0.00 |
fix: execute tool calls emitted as plain text in interactive |
|
Domain-specific language, informal tone, |
2026-07-04 |
| pr |
0.00 |
fix(core): ensure tool_choice maps to structured object for |
|
Technical focus, error logs, and no AI-l |
2026-07-04 |
| pr |
0.00 |
test: add skills catalog loading and validation tests |
|
Bullet points, domain detail, informal a |
2026-07-04 |
| pr |
0.00 |
Add Express.js and WebSocket security skills |
|
Domain-specific listing, informal and co |
2026-07-03 |
| pr |
0.00 |
fix(todo): stop json.loads corrupting bare numeric-looking t |
|
In-depth, with code, technical jargon, a |
2026-07-03 |
| pr |
0.00 |
fix(report): keep ReDoS distinct from generic DoS in SARIF c |
|
Technical, detailed, and follows human b |
2026-07-03 |
| pr |
0.00 |
feat: add Docker network support for sandbox connections |
|
Brief, direct; no AI phrasing, domain-sp |
2026-07-01 |
| pr |
0.00 |
feat: add support for setup script execution before scans |
|
Concise, straight to the point, project- |
2026-07-01 |
| pr |
0.00 |
test: cover report helpers _parse_dedupe_response and litell |
|
Test summary is concise and human-writte |
2026-06-26 |
| pr |
0.00 |
Warn when configured LLM is not frontier-recommended |
|
— |
2026-06-26 |
| pr |
0.00 |
Testing |
|
Single word, clearly human test/placehol |
2026-06-06 |
