You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/first-second-parity-audit.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -95,7 +95,7 @@ Anthropic API 和 conversation:
95
95
- Request construction now also applies the official ToolSearch enablement gates before emitting beta `defer_loading` / `tool_reference` shapes: Haiku models, `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`, falsy `ENABLE_TOOL_SEARCH`, `ENABLE_TOOL_SEARCH=auto:100`, unset ToolSearch behind non-first-party `ANTHROPIC_BASE_URL`, and `ENABLE_TOOL_SEARCH=auto` requests below the deferred-tool size threshold all fall back to standard inline tool schemas; explicit `ENABLE_TOOL_SEARCH=true` can still opt a custom gateway back in. Auto mode now uses the Anthropic `/v1/messages/count_tokens` endpoint when the client supports it, subtracts the official fixed tool overhead, falls back to Haiku message-create usage when count-tokens fails, and then falls back to the official character threshold when token counting is unavailable, including `auto:N` percentages, 1M context suffixes, and ant-only context-window overrides.
96
96
- Deferred tool token counts in ToolSearch auto mode are now memoized in-process by the official deferred tool name list key, including both successful counts and unavailable/null-equivalent results.
97
97
- MCP tools now follow the official deferred-tool rule: they are deferred unless explicitly marked `always_load`, Anthropic tool schema serialization emits `defer_loading` for MCP tools, ToolSearch auto token counting includes MCP tools as loaded schemas, and configured MCP toolset attach/close invalidates the in-process deferred-tool token-count cache.
98
-
- ToolSearch deferred tool announcements now support the official ant `deferred_tools_delta` attachment path: the runner diffs deferred tools against prior delta attachments, persists a new attachment, API normalization renders added/removed tool reminders, and ant delta mode skips the ephemeral `<available-deferred-tools>` prepend.
98
+
- ToolSearch deferred tool announcements now support the official `deferred_tools_delta` attachment path when `USER_TYPE=ant` or settings `advanced.tengu_glacier_2xr`/`advanced.tenguGlacier2xr` is enabled: the runner diffs deferred tools against prior delta attachments, persists a new attachment, API normalization renders added/removed tool reminders, and delta mode skips the ephemeral `<available-deferred-tools>` prepend.
99
99
- When ToolSearch is inactive for a request, API message normalization strips historical `tool_reference` blocks from user `tool_result` content and replaces pure-reference results with the official placeholder text, while preserving history scanning before stripping so discovered tools can still be loaded when ToolSearch is active.
100
100
- Anthropic request tool conversion now preserves contract-level `strict`, `eager_input_streaming`, `cache_control`, and API-level `defer_loading` hints from deferred tool definitions, with `always_load` overriding `should_defer`; it also falls back from `description` to `prompt` to `searchHint` when building API tool descriptions. Runner request construction preserves these fields for tools such as `Task`.
101
101
- Tool validation now appends an official-style schema-not-sent recovery hint when an undiscovered deferred tool is invoked with invalid typed input and `ToolSearch` is available, including compact-boundary discovered-tool metadata so already loaded tools do not get a false hint.
@@ -117,7 +117,7 @@ The following items remain incomplete and must not be treated as done:
117
117
- Auto mode / YOLO classifier: transcript construction, two-stage classifier, XML/tool-use parsing, prompt dump, denial circuit breaker, model gating, and fallback behavior.
- Full filesystem permission parity gaps that remain: skill-scope allow suggestions, remaining local/local-jsx slash-command execution wiring beyond the currently covered no-query builtins, command permission UI/SDK surfacing, forked/remote/MCP/bundled SkillTool behavior and remaining plugin SkillTool UI/SDK polish beyond current metadata preservation, skill prompt shell injection, complete auto-memory override policy, and deeper platform-specific Windows/WSL bypass handling.
120
-
- Full tool execution parity gaps that remain: complete hook runtime policy beyond the current settings command hook path, MCP elicitation, complete SDK control event surface beyond current progress NDJSON, full deferred/lazy tool discovery beyond current local registry BM25 search, remaining ToolSearch model/env/proxy edge gates, remaining `ENABLE_TOOL_SEARCH=auto` edge behavior such as official token-count VCR, remaining deferred-tool pool-change analytics/telemetry and non-ant delta feature-gate details, mid-call cancellation for concrete tools, background task behavior, telemetry, and concrete tool-specific semantics.
120
+
- Full tool execution parity gaps that remain: complete hook runtime policy beyond the current settings command hook path, MCP elicitation, complete SDK control event surface beyond current progress NDJSON, full deferred/lazy tool discovery beyond current local registry BM25 search, remaining ToolSearch model/env/proxy edge gates, remaining `ENABLE_TOOL_SEARCH=auto` edge behavior such as official token-count VCR, remaining deferred-tool pool-change analytics/telemetry, mid-call cancellation for concrete tools, background task behavior, telemetry, and concrete tool-specific semantics.
121
121
- Complete Anthropic API parity gaps that remain: dynamic beta-header latching for any remaining provider-specific feature gates beyond prompt-cache/cache-editing/strict-output/1M-context requests, ant-only dump gating and remote `/issue` submission integration beyond the current local context summary, full official cost tracker/session restore lifecycle beyond current transcript usage restore, post-handshake streaming failure semantics, deeper gateway/proxy auth and routing behavior beyond static custom headers, first-party/Bedrock/Vertex/Foundry client setup, deeper OAuth account/profile lifecycle beyond request-time refresh retry, fast-mode retry/cooldown semantics, persistent unattended retry heartbeats, full prompt-cache editing lifecycle, and provider-specific cache behavior.
122
122
- Full conversation/query loop: stop hooks, compact/auto-compact, token budget escalation, resume, SDK JSON/NDJSON control events, status updates, rate-limit handling, model switch breadcrumbs, side questions.
123
123
- Full settings parity gaps that remain: complete Zod-equivalent validation messages, full remote managed-settings watcher/non-daemon background refresh lifecycle beyond current turn-start and daemon-heartbeat refresh, remaining forked agent/frontmatter execution and UI edge cases beyond current policy metadata filtering, complete marketplace TUI/UI/background lifecycle beyond current local/settings/directory/file/URL catalog/git/github/npm cache manifest load, URL catalog cache fallback, git/github fetch/pull cache refresh, npm pack cache refresh, and background watcher/continuous app-state sync beyond current turn-start local settings reload.
0 commit comments