feat: tools and the gate know who the run is for #35

Merged

bjoern merged 1 commit from feat/caller-context into main 2026-10-23 18:36:38 +02:00

Conversation 1 Commits 1 Files changed 13 +430 -15

scarlet commented 2026-10-23 18:12:28 +02:00

Member

Copy link

This is the fourth step of the library track Shikigami's runtime needs: "Caller context" in its PROJECT_PLAN (Shikigami ADR 0021; ADR 0022 needs the gate to decide by the run's profile). It adds an opaque caller state that every tool call and the tool-call gate read, so a tool knows the familiar, chat and run it works for without being built around them. It is opt-in: with no state set, nothing changes for Orihon, Kagura or Tsumugi.

What's in

AgentOptions.CallerState (object?)

• The agent hands it unchanged to every call (ToolInvocationContext.CallerState) and to the gate (ToolTurnReview.CallerState). It never looks inside.
• It is read once per tool turn, before the turn is announced. The gate and every call it allows see one object, even if a tool or an event handler changes the options mid-turn, so a call can never run under a state the gate didn't review. A change applies from the next turn.
• Clone() copies the reference. A CreateSubAgent sub-agent shares the object unless its configure callback sets another. It is in the options registry (AgentOwnOptions, and the every-option fixture).

Reading it back

• GetCallerState<T>() on both records returns the state as its own type, or as a type it derives from or implements.
• It throws InvalidOperationException when there is no state ("set AgentOptions.CallerState to the Run its tools and gate read") or when the state is another type ("is a Run, not a String").

SubAgentTool — this was open in the track's notes, and I chose this; easy to reverse if you'd rather.

• A delegated sub-agent works for the run that called it, so it gets the calling run's state. Its own options' state is used only when that run has none.
• Why: the tool's base options are shared by every run it serves, so a per-run state can only come from the call.

The critical-section contract

• ITool.InvokeAsync's doc now says what the loop already did: a tool that returns after the run's token is cancelled (finishing a write it must not leave half done) has its answer recorded, the run ends as cancelled, and the calls after it are answered as not run.
• For a blind model's images the doc is narrower: the describer gets the cancelled token, so a describer that honours it leaves them undescribed.

One behaviour fix the review found

• A cancel that landed in the last allowed round, after its last call returned, used to end the run as MaxIterationsReached, and OnMaxRoundsReached was offered more rounds for a cancelled run.
• The loop now checks the token before the cap hook, so such a run ends as cancelled in both modes: ChatAsync throws, or it returns Cancelled with ReturnResult.
• This is a row in "Upgrading from 0.3", since a 0.3 host could see that run end differently.

Docs

• README "Who the run is for", a subsection of Authoring custom tools, covers:
  • the example;
  • read once per turn;
  • one options object per concurrent run, because the agent keeps the instance it was given;
  • the DI route: CreateSubAgent(o => o.CallerState = run, sp.GetServices<ITool>()), since a sub-agent starts with no tools.
• Bullets in Gating, Sub-agents and the cancel section; the cap hook section; Highlights; the Upgrading intro and row; the ToolInvocationContext paragraph and Tool<TParams>.ExecuteAsync's param doc.

Not in this step

• The steering pull hook (L4) is the next PR. After it come cache controls (L3a, L3b) and hardening (L5a, L5b).
• AgentSnapshot (the cap hook's view) carries no caller state. No consumer needs it, and the hook closes over its own run.

Verification

• The whole solution passes 1660/1660, in local time and under TZ=UTC: core 1415, Agents 238 (+14), Imaging 7. The build has 0 warnings.

• CallerStateTests (8 tests, one a theory of 4 rows):

  • every call and the gate see the caller's own object, checked across two turns and three calls (Assert.Same, counts pinned first);
  • a state changed between two chats reaches the second chat;
  • a state changed by a tool during a turn leaves the rest of that turn as the gate reviewed it, and reaches the next turn;
  • with no state, both see null and reading one gives the exact message;
  • a state reads back as itself, a base type or an interface, and not as another type;
  • CreateSubAgent shares the state unless configure replaces it;
  • a DI agent gets its run's state through a sub-agent given the registered tools;
  • SubAgentTool across all four combinations: calling run with or without a state, the tool's options with or without one. The base options are left untouched.

• Cancellation:

  • Throw mode: a tool that finishes despite the cancel keeps its answer, and the next call is answered as not run.
  • Throw mode, last allowed round: the run throws the caller's token, and the cap hook is never asked.
  • ReturnResult mode, the same case: Cancelled, the closing event says so, the hook isn't asked, and the round sits in Rounds with no cut-off round or partial.

• Mutation probes: 13 sites, 13 killed, 0 survived. The sites:

  • each context losing the state;
  • the call reading the options anew instead of the turn's value;
  • the cap check removed;
  • Clone dropping the state;
  • SubAgentTool ignoring the run, preferring its own options, or dropping the fallback;
  • both GetCallerStates cast instead of checking;
  • an exact-type check;
  • both messages.

  They ran before the second pass. Its fixes were docs and one test, and add no production logic.

• Review (read-only workflow; every count is from its saved JSON):

  • First pass: 12 findings — 9 confirmed, 2 plausible, 1 refuted.
    • Taken: the per-call read the gate never reviewed; the cancel at the cap; the blind-mode image wording; one options object per run and the DI route; a missing mid-run test; the stale ToolInvocationContext paragraph and param doc; the Upgrading list; the test summary; the Highlights wrap.
    • Refuted: "a DI agent cannot get a per-run state". CreateSubAgent gives it one; its doc point is covered.
  • Second pass over the fixes: 2 findings, both confirmed and taken. The DI recipe gave a tool-less sub-agent; it now hands over the registered tools, and a test pins it. The cap change needed its Upgrading row.

Notes

• Merge order: none. Shikigami pins the merged commit when its runtime slice (2c) bumps the pointer.
• Other consumers are unaffected. The state is opt-in, and the records gain optional init members. The cap change applies only to a run whose token was already cancelled.

🤖 Generated with Claude Code

This is the fourth step of the library track Shikigami's runtime needs: "Caller context" in its PROJECT_PLAN (Shikigami ADR 0021; ADR 0022 needs the gate to decide by the run's profile). It adds an **opaque caller state that every tool call and the tool-call gate read**, so a tool knows the familiar, chat and run it works for without being built around them. It is opt-in: with no state set, nothing changes for Orihon, Kagura or Tsumugi. ## What's in **`AgentOptions.CallerState`** (`object?`) - The agent hands it unchanged to every call (`ToolInvocationContext.CallerState`) and to the gate (`ToolTurnReview.CallerState`). It never looks inside. - It is **read once per tool turn**, before the turn is announced. The gate and every call it allows see one object, even if a tool or an event handler changes the options mid-turn, so a call can never run under a state the gate didn't review. A change applies from the next turn. - `Clone()` copies the reference. A `CreateSubAgent` sub-agent shares the object unless its configure callback sets another. It is in the options registry (`AgentOwnOptions`, and the every-option fixture). **Reading it back** - `GetCallerState<T>()` on both records returns the state as its own type, or as a type it derives from or implements. - It throws `InvalidOperationException` when there is no state ("set AgentOptions.CallerState to the Run its tools and gate read") or when the state is another type ("is a Run, not a String"). **`SubAgentTool`** — this was open in the track's notes, and I chose this; easy to reverse if you'd rather. - A delegated sub-agent works for the run that called it, so it gets **the calling run's state**. Its own options' state is used only when that run has none. - Why: the tool's base options are shared by every run it serves, so a per-run state can only come from the call. **The critical-section contract** - `ITool.InvokeAsync`'s doc now says what the loop already did: a tool that returns after the run's token is cancelled (finishing a write it must not leave half done) has its answer recorded, the run ends as cancelled, and the calls after it are answered as not run. - For a blind model's images the doc is narrower: the describer gets the cancelled token, so a describer that honours it leaves them undescribed. **One behaviour fix the review found** - A cancel that landed in the last allowed round, after its last call returned, used to end the run as `MaxIterationsReached`, and `OnMaxRoundsReached` was offered more rounds for a cancelled run. - The loop now checks the token before the cap hook, so such a run ends as cancelled in both modes: `ChatAsync` throws, or it returns `Cancelled` with `ReturnResult`. - This is a row in "Upgrading from 0.3", since a 0.3 host could see that run end differently. **Docs** - README "Who the run is for", a subsection of Authoring custom tools, covers: - the example; - read once per turn; - one options object per concurrent run, because the agent keeps the instance it was given; - the DI route: `CreateSubAgent(o => o.CallerState = run, sp.GetServices<ITool>())`, since a sub-agent starts with no tools. - Bullets in Gating, Sub-agents and the cancel section; the cap hook section; Highlights; the Upgrading intro and row; the `ToolInvocationContext` paragraph and `Tool<TParams>.ExecuteAsync`'s param doc. ## Not in this step - **The steering pull hook (L4)** is the next PR. After it come cache controls (L3a, L3b) and hardening (L5a, L5b). - **`AgentSnapshot` (the cap hook's view) carries no caller state.** No consumer needs it, and the hook closes over its own run. ## Verification - The whole solution passes **1660/1660**, in local time and under `TZ=UTC`: core 1415, Agents 238 (+14), Imaging 7. The build has 0 warnings. - **`CallerStateTests`** (8 tests, one a theory of 4 rows): - every call and the gate see the caller's own object, checked across two turns and three calls (`Assert.Same`, counts pinned first); - a state changed between two chats reaches the second chat; - a state changed by a tool during a turn leaves the rest of that turn as the gate reviewed it, and reaches the next turn; - with no state, both see `null` and reading one gives the exact message; - a state reads back as itself, a base type or an interface, and not as another type; - `CreateSubAgent` shares the state unless configure replaces it; - a DI agent gets its run's state through a sub-agent given the registered tools; - `SubAgentTool` across all four combinations: calling run with or without a state, the tool's options with or without one. The base options are left untouched. - **Cancellation:** - Throw mode: a tool that finishes despite the cancel keeps its answer, and the next call is answered as not run. - Throw mode, last allowed round: the run throws the caller's token, and the cap hook is never asked. - `ReturnResult` mode, the same case: `Cancelled`, the closing event says so, the hook isn't asked, and the round sits in `Rounds` with no cut-off round or partial. - **Mutation probes:** 13 sites, **13 killed**, 0 survived. The sites: - each context losing the state; - the call reading the options anew instead of the turn's value; - the cap check removed; - `Clone` dropping the state; - `SubAgentTool` ignoring the run, preferring its own options, or dropping the fallback; - both `GetCallerState`s cast instead of checking; - an exact-type check; - both messages. They ran before the second pass. Its fixes were docs and one test, and add no production logic. - **Review** (read-only workflow; every count is from its saved JSON): - **First pass: 12 findings** — 9 confirmed, 2 plausible, 1 refuted. - Taken: the per-call read the gate never reviewed; the cancel at the cap; the blind-mode image wording; one options object per run and the DI route; a missing mid-run test; the stale `ToolInvocationContext` paragraph and param doc; the Upgrading list; the test summary; the Highlights wrap. - Refuted: "a DI agent cannot get a per-run state". `CreateSubAgent` gives it one; its doc point is covered. - **Second pass** over the fixes: **2 findings, both confirmed and taken.** The DI recipe gave a tool-less sub-agent; it now hands over the registered tools, and a test pins it. The cap change needed its Upgrading row. ## Notes - **Merge order:** none. Shikigami pins the merged commit when its runtime slice (2c) bumps the pointer. - **Other consumers are unaffected.** The state is opt-in, and the records gain optional init members. The cap change applies only to a run whose token was already cancelled. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

scarlet added 1 commit 2026-10-23 18:12:28 +02:00

feat: tools and the gate know who the run is for ... 95318deef1

AgentOptions.CallerState reaches every tool call and the tool-call gate,
read once per turn; a delegated sub-agent works with the calling run's
state. A cancel in the last allowed round now ends the run as cancelled
instead of out of rounds.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

forgejo-actions commented 2026-10-23 18:19:02 +02:00

Copy link

Summary

Summary

Generated on:	10/23/2026 - 16:19:02
Parser:	MultiReport (3x Cobertura)
Assemblies:	3
Classes:	136
Files:	116
Line coverage:	96.3% (4698 of 4877)
Covered lines:	4698
Uncovered lines:	179
Coverable lines:	4877
Total lines:	12097
Branch coverage:	93.6% (3057 of 3265)
Covered branches:	3057
Total branches:	3265
Method coverage:	Feature is only available for sponsors

Coverage

OpenRouter.Net - 98.1%

Name	Line	Branch
OpenRouter.Net	98.1%	95.8%
OpenRouter.Net.Client.CachingOpenRouterClient	100%	96.1%
OpenRouter.Net.Client.CachingOpenRouterClient.CachedListing	100%
OpenRouter.Net.Client.ChatCompletionStreamAccumulator	100%	100%
OpenRouter.Net.Client.ChatCompletionStreamAccumulator.ChoiceState	100%	100%
OpenRouter.Net.Client.ChatCompletionStreamAccumulator.ProviderFieldFold	100%	100%
OpenRouter.Net.Client.ChatCompletionStreamAccumulator.ReasoningSegment	100%	100%
OpenRouter.Net.Client.ChatCompletionStreamAccumulator.ToolCallState	100%	100%
OpenRouter.Net.Client.OpenRouterClient	100%	99%
OpenRouter.Net.Client.OpenRouterClient<TRequest, TResponse>	100%	99%
OpenRouter.Net.Client.OpenRouterClient	100%	99%
OpenRouter.Net.Client.OpenRouterClientOptions	100%
OpenRouter.Net.Client.OpenRouterRequestLoggingHandler	78.7%	62.5%
OpenRouter.Net.Client.RetryOptions	100%	100%
OpenRouter.Net.Client.StreamResultOptions	100%
OpenRouter.Net.Contracts.IOpenRouterClient	100%	100%
OpenRouter.Net.Extensions.ServiceCollectionExtensions	100%	100%
OpenRouter.Net.Internal.AssistantContent	91.6%	75%
OpenRouter.Net.Internal.AssistantContentJsonConverter	75%	64.2%
OpenRouter.Net.Internal.ContentPartListConverter	85.7%	66.6%
OpenRouter.Net.Internal.DecimalStringJsonConverter	85.7%	87.5%
OpenRouter.Net.Internal.DecisionAnswerJsonConverter	100%	100%
OpenRouter.Net.Internal.DecisionContentJsonConverter	100%
OpenRouter.Net.Internal.DecisionQuestionJsonConverter	100%	100%
OpenRouter.Net.Internal.DecisionWire	100%	94.4%
OpenRouter.Net.Internal.EnumChoiceLabels.Map	100%
OpenRouter.Net.Internal.EnumChoiceLabels	100%	100%
OpenRouter.Net.Internal.ErrorParser	100%	75%
OpenRouter.Net.Internal.FailureKindMap	100%	100%
OpenRouter.Net.Internal.JsonOptions	100%
OpenRouter.Net.Internal.JsonPointer	100%
OpenRouter.Net.Internal.JsonSchemaRefs	100%	100%
OpenRouter.Net.Internal.JsonSchemaRefs.Pass	100%	100%
OpenRouter.Net.Internal.ModelIdJsonConverter	100%	50%
OpenRouter.Net.Internal.NumberOrStringJsonConverter	100%	100%
OpenRouter.Net.Internal.PercentileCutoffsJsonConverter	93.3%	93.1%
OpenRouter.Net.Internal.ProviderSortConfigJsonConverter	94%	95.8%
OpenRouter.Net.Internal.RawDecisionQuestionJsonConverter	100%
OpenRouter.Net.Internal.RetryPolicy	90.9%	84.7%
OpenRouter.Net.Internal.RetryPolicy	90.9%	84.7%
OpenRouter.Net.Internal.SchemaTooDeepException	100%
OpenRouter.Net.Internal.SseEventReader	100%	88.8%
OpenRouter.Net.Internal.StallWatchdog	100%	100%
OpenRouter.Net.Internal.StreamOutcomes	100%	100%
OpenRouter.Net.Internal.StreamSession	100%	100%
OpenRouter.Net.Internal.TolerantStringEnumConverter	100%	98.1%
OpenRouter.Net.Internal.ToolChoiceJsonConverter	61.7%	46.1%
OpenRouter.Net.Internal.TooManyRefsFollowedException	100%
OpenRouter.Net.Internal.UnknownDecisionAnswerJsonConverter	100%
OpenRouter.Net.Models.Common.ApiError	100%	100%
OpenRouter.Net.Models.Common.CacheControl	100%
OpenRouter.Net.Models.Common.ModelId	95.1%	92.9%
OpenRouter.Net.Models.Common.QuantizationExtensions	100%	100%
OpenRouter.Net.Models.Common.Result	100%	100%
OpenRouter.Net.Models.Common.Result.Failure	100%	100%
OpenRouter.Net.Models.Common.Result.Success	100%
OpenRouter.Net.Models.Common.Result	100%	100%
OpenRouter.Net.Models.Content.AudioPart	100%
OpenRouter.Net.Models.Content.ImagePart	100%
OpenRouter.Net.Models.Content.TextPart	100%
OpenRouter.Net.Models.Decisions.ChoiceAnswer	100%	100%
OpenRouter.Net.Models.Decisions.ChoiceAnswer	100%	100%
OpenRouter.Net.Models.Decisions.ChoiceAnswer	100%	100%
OpenRouter.Net.Models.Decisions.ChoiceKey	100%
OpenRouter.Net.Models.Decisions.ChoiceQuestion	100%
OpenRouter.Net.Models.Decisions.DecisionAnswer	100%
OpenRouter.Net.Models.Decisions.DecisionContent	100%	90.9%
OpenRouter.Net.Models.Decisions.DecisionKey	100%
OpenRouter.Net.Models.Decisions.DecisionQuestion	100%	100%
OpenRouter.Net.Models.Decisions.DecisionQuestionSet	100%	100%
OpenRouter.Net.Models.Decisions.DecisionsRequest	97.7%	97.6%
OpenRouter.Net.Models.Decisions.DecisionsResponse	100%	93.3%
OpenRouter.Net.Models.Decisions.NoulAnswer	100%
OpenRouter.Net.Models.Decisions.NoulQuestion	100%
OpenRouter.Net.Models.Decisions.OpenRouterClientDecisionsExtensions	100%	83.3%
OpenRouter.Net.Models.Decisions.RawDecisionQuestion	100%	100%
OpenRouter.Net.Models.Decisions.ScoreAnswer	100%	100%
OpenRouter.Net.Models.Decisions.ScoreQuestion	100%
OpenRouter.Net.Models.Decisions.UnknownDecisionAnswer	100%	100%
OpenRouter.Net.Models.Messages.AssistantMessage	100%	81.2%
OpenRouter.Net.Models.Messages.DeveloperMessage	100%
OpenRouter.Net.Models.Messages.MessageJson	100%	100%
OpenRouter.Net.Models.Messages.SystemMessage	100%
OpenRouter.Net.Models.Messages.ToolMessage	100%
OpenRouter.Net.Models.Messages.UserMessage	100%
OpenRouter.Net.Models.Requests.ChatCompletionRequest	95.1%	94.8%
OpenRouter.Net.Models.Requests.JsonSchemaStrictness	99.3%	100%
OpenRouter.Net.Models.Requests.JsonSchemaStrictness.Checker	100%	100%
OpenRouter.Net.Models.Requests.ModelListQuery	100%	100%
OpenRouter.Net.Models.Requests.PercentileCutoffs	100%	100%
OpenRouter.Net.Models.Requests.ProviderPreferences	100%	100%
OpenRouter.Net.Models.Requests.ProviderSortConfig	100%	100%
OpenRouter.Net.Models.Requests.RequestPlugin	100%
OpenRouter.Net.Models.Requests.ResponseFormat	100%
OpenRouter.Net.Models.Requests.StrictSchemaProblem	100%
OpenRouter.Net.Models.Requests.ToolCall	100%
OpenRouter.Net.Models.Requests.ToolChoice	100%
OpenRouter.Net.Models.Requests.ToolDefinition	100%
OpenRouter.Net.Models.Responses.AssistantDelta	100%	100%
OpenRouter.Net.Models.Responses.ChatCompletionChunk	100%	100%
OpenRouter.Net.Models.Responses.ChatCompletionResponse	100%	100%
OpenRouter.Net.Models.Responses.Choice	100%	100%
OpenRouter.Net.Models.Responses.StructuredOutput	100%	100%
OpenRouter.Net.OpenRouterException	100%
System.Text.RegularExpressions.Generated	83.3%	53.8%
System.Text.RegularExpressions.Generated.RunnerFactory
System.Text.RegularExpressions.Generated.RunnerFactory.Runner

OpenRouter.Net.Agents - 91.7%

Name	Line	Branch
OpenRouter.Net.Agents	91.7%	86.6%
OpenRouter.Net.Agents.Agent	98.4%	92.6%
OpenRouter.Net.Agents.Agent.StreamedRound	100%	98.6%
OpenRouter.Net.Agents.AgentOptions	100%	100%
OpenRouter.Net.Agents.AgentResult	100%	50%
OpenRouter.Net.Agents.CallerStates	100%	100%
OpenRouter.Net.Agents.Extensions.ServiceCollectionExtensions	88.2%	100%
OpenRouter.Net.Agents.Gating.ToolCallGates	100%	100%
OpenRouter.Net.Agents.Gating.ToolCallGates.PerCallGate	100%	100%
OpenRouter.Net.Agents.Gating.ToolCallVerdict	100%
OpenRouter.Net.Agents.Gating.ToolTurnReview	100%
OpenRouter.Net.Agents.RoundDetail	100%	75%
OpenRouter.Net.Agents.Tools.FileSystem.CopyTool	42.1%	28.5%
OpenRouter.Net.Agents.Tools.FileSystem.DeleteTool	57.1%	50%
OpenRouter.Net.Agents.Tools.FileSystem.DiffTool	83.3%	74.2%
OpenRouter.Net.Agents.Tools.FileSystem.ListDirectoryTool	68%	61.1%
OpenRouter.Net.Agents.Tools.FileSystem.MoveTool	55%	33.3%
OpenRouter.Net.Agents.Tools.FileSystem.ReadFileTool	73.6%	50%
OpenRouter.Net.Agents.Tools.FileSystem.SearchTool	67.5%	70.8%
OpenRouter.Net.Agents.Tools.FileSystem.WriteFileTool	75%	50%
OpenRouter.Net.Agents.Tools.ITool	100%
OpenRouter.Net.Agents.Tools.SubAgent.SubAgentTool	96.1%	69.5%
OpenRouter.Net.Agents.Tools.Tool	100%	100%
OpenRouter.Net.Agents.Tools.Tool	90%	50%
OpenRouter.Net.Agents.Tools.ToolInvocationContext	100%
OpenRouter.Net.Agents.Tools.ToolMessageExtensions	0%
OpenRouter.Net.Agents.Tools.ToolResult	100%	100%
OpenRouter.Net.Agents.Tools.ToolSchema	100%	100%
OpenRouter.Net.Agents.Tools.Workspace	100%	91.6%

OpenRouter.Net.Imaging - 81.8%

Name	Line	Branch
OpenRouter.Net.Imaging	81.8%	59.3%
OpenRouter.Net.Imaging.ImageEncodeOptions	90.9%	75%
OpenRouter.Net.Imaging.ImageEncoder	80.3%	57.1%

<!-- coverage-comment --> # Summary <details open><summary>Summary</summary> ||| |:---|:---| | Generated on: | 10/23/2026 - 16:19:02 | | Parser: | MultiReport (3x Cobertura) | | Assemblies: | 3 | | Classes: | 136 | | Files: | 116 | | **Line coverage:** | 96.3% (4698 of 4877) | | Covered lines: | 4698 | | Uncovered lines: | 179 | | Coverable lines: | 4877 | | Total lines: | 12097 | | **Branch coverage:** | 93.6% (3057 of 3265) | | Covered branches: | 3057 | | Total branches: | 3265 | | **Method coverage:** | [Feature is only available for sponsors](https://reportgenerator.io/pro) | </details> ## Coverage <details><summary>OpenRouter.Net - 98.1%</summary> |**Name**|**Line**|**Branch**| |:---|---:|---:| |**OpenRouter.Net**|**98.1%**|**95.8%**| |OpenRouter.Net.Client.CachingOpenRouterClient|100%|96.1%| |OpenRouter.Net.Client.CachingOpenRouterClient.CachedListing|100%|| |OpenRouter.Net.Client.ChatCompletionStreamAccumulator|100%|100%| |OpenRouter.Net.Client.ChatCompletionStreamAccumulator.ChoiceState|100%|100%| |OpenRouter.Net.Client.ChatCompletionStreamAccumulator.ProviderFieldFold|100%|100%| |OpenRouter.Net.Client.ChatCompletionStreamAccumulator.ReasoningSegment|100%|100%| |OpenRouter.Net.Client.ChatCompletionStreamAccumulator.ToolCallState|100%|100%| |OpenRouter.Net.Client.OpenRouterClient|100%|99%| |OpenRouter.Net.Client.OpenRouterClient<TRequest, TResponse>|100%|99%| |OpenRouter.Net.Client.OpenRouterClient<TResponse>|100%|99%| |OpenRouter.Net.Client.OpenRouterClientOptions|100%|| |OpenRouter.Net.Client.OpenRouterRequestLoggingHandler|78.7%|62.5%| |OpenRouter.Net.Client.RetryOptions|100%|100%| |OpenRouter.Net.Client.StreamResultOptions|100%|| |OpenRouter.Net.Contracts.IOpenRouterClient|100%|100%| |OpenRouter.Net.Extensions.ServiceCollectionExtensions|100%|100%| |OpenRouter.Net.Internal.AssistantContent|91.6%|75%| |OpenRouter.Net.Internal.AssistantContentJsonConverter|75%|64.2%| |OpenRouter.Net.Internal.ContentPartListConverter|85.7%|66.6%| |OpenRouter.Net.Internal.DecimalStringJsonConverter|85.7%|87.5%| |OpenRouter.Net.Internal.DecisionAnswerJsonConverter|100%|100%| |OpenRouter.Net.Internal.DecisionContentJsonConverter|100%|| |OpenRouter.Net.Internal.DecisionQuestionJsonConverter|100%|100%| |OpenRouter.Net.Internal.DecisionWire|100%|94.4%| |OpenRouter.Net.Internal.EnumChoiceLabels.Map<TEnum>|100%|| |OpenRouter.Net.Internal.EnumChoiceLabels<TEnum>|100%|100%| |OpenRouter.Net.Internal.ErrorParser|100%|75%| |OpenRouter.Net.Internal.FailureKindMap|100%|100%| |OpenRouter.Net.Internal.JsonOptions|100%|| |OpenRouter.Net.Internal.JsonPointer|100%|| |OpenRouter.Net.Internal.JsonSchemaRefs|100%|100%| |OpenRouter.Net.Internal.JsonSchemaRefs.Pass|100%|100%| |OpenRouter.Net.Internal.ModelIdJsonConverter|100%|50%| |OpenRouter.Net.Internal.NumberOrStringJsonConverter|100%|100%| |OpenRouter.Net.Internal.PercentileCutoffsJsonConverter|93.3%|93.1%| |OpenRouter.Net.Internal.ProviderSortConfigJsonConverter|94%|95.8%| |OpenRouter.Net.Internal.RawDecisionQuestionJsonConverter|100%|| |OpenRouter.Net.Internal.RetryPolicy|90.9%|84.7%| |OpenRouter.Net.Internal.RetryPolicy<T>|90.9%|84.7%| |OpenRouter.Net.Internal.SchemaTooDeepException|100%|| |OpenRouter.Net.Internal.SseEventReader|100%|88.8%| |OpenRouter.Net.Internal.StallWatchdog|100%|100%| |OpenRouter.Net.Internal.StreamOutcomes|100%|100%| |OpenRouter.Net.Internal.StreamSession|100%|100%| |OpenRouter.Net.Internal.TolerantStringEnumConverter<T>|100%|98.1%| |OpenRouter.Net.Internal.ToolChoiceJsonConverter|61.7%|46.1%| |OpenRouter.Net.Internal.TooManyRefsFollowedException|100%|| |OpenRouter.Net.Internal.UnknownDecisionAnswerJsonConverter|100%|| |OpenRouter.Net.Models.Common.ApiError|100%|100%| |OpenRouter.Net.Models.Common.CacheControl|100%|| |OpenRouter.Net.Models.Common.ModelId|95.1%|92.9%| |OpenRouter.Net.Models.Common.QuantizationExtensions|100%|100%| |OpenRouter.Net.Models.Common.Result|100%|100%| |OpenRouter.Net.Models.Common.Result.Failure<T>|100%|100%| |OpenRouter.Net.Models.Common.Result.Success<T>|100%|| |OpenRouter.Net.Models.Common.Result<T>|100%|100%| |OpenRouter.Net.Models.Content.AudioPart|100%|| |OpenRouter.Net.Models.Content.ImagePart|100%|| |OpenRouter.Net.Models.Content.TextPart|100%|| |OpenRouter.Net.Models.Decisions.ChoiceAnswer|100%|100%| |OpenRouter.Net.Models.Decisions.ChoiceAnswer<TEnum>|100%|100%| |OpenRouter.Net.Models.Decisions.ChoiceAnswer<TEnum>|100%|100%| |OpenRouter.Net.Models.Decisions.ChoiceKey<TEnum>|100%|| |OpenRouter.Net.Models.Decisions.ChoiceQuestion|100%|| |OpenRouter.Net.Models.Decisions.DecisionAnswer|100%|| |OpenRouter.Net.Models.Decisions.DecisionContent|100%|90.9%| |OpenRouter.Net.Models.Decisions.DecisionKey<TAnswer>|100%|| |OpenRouter.Net.Models.Decisions.DecisionQuestion|100%|100%| |OpenRouter.Net.Models.Decisions.DecisionQuestionSet|100%|100%| |OpenRouter.Net.Models.Decisions.DecisionsRequest|97.7%|97.6%| |OpenRouter.Net.Models.Decisions.DecisionsResponse|100%|93.3%| |OpenRouter.Net.Models.Decisions.NoulAnswer|100%|| |OpenRouter.Net.Models.Decisions.NoulQuestion|100%|| |OpenRouter.Net.Models.Decisions.OpenRouterClientDecisionsExtensions|100%|83.3%| |OpenRouter.Net.Models.Decisions.RawDecisionQuestion|100%|100%| |OpenRouter.Net.Models.Decisions.ScoreAnswer|100%|100%| |OpenRouter.Net.Models.Decisions.ScoreQuestion|100%|| |OpenRouter.Net.Models.Decisions.UnknownDecisionAnswer|100%|100%| |OpenRouter.Net.Models.Messages.AssistantMessage|100%|81.2%| |OpenRouter.Net.Models.Messages.DeveloperMessage|100%|| |OpenRouter.Net.Models.Messages.MessageJson|100%|100%| |OpenRouter.Net.Models.Messages.SystemMessage|100%|| |OpenRouter.Net.Models.Messages.ToolMessage|100%|| |OpenRouter.Net.Models.Messages.UserMessage|100%|| |OpenRouter.Net.Models.Requests.ChatCompletionRequest|95.1%|94.8%| |OpenRouter.Net.Models.Requests.JsonSchemaStrictness|99.3%|100%| |OpenRouter.Net.Models.Requests.JsonSchemaStrictness.Checker|100%|100%| |OpenRouter.Net.Models.Requests.ModelListQuery|100%|100%| |OpenRouter.Net.Models.Requests.PercentileCutoffs|100%|100%| |OpenRouter.Net.Models.Requests.ProviderPreferences|100%|100%| |OpenRouter.Net.Models.Requests.ProviderSortConfig|100%|100%| |OpenRouter.Net.Models.Requests.RequestPlugin|100%|| |OpenRouter.Net.Models.Requests.ResponseFormat|100%|| |OpenRouter.Net.Models.Requests.StrictSchemaProblem|100%|| |OpenRouter.Net.Models.Requests.ToolCall|100%|| |OpenRouter.Net.Models.Requests.ToolChoice|100%|| |OpenRouter.Net.Models.Requests.ToolDefinition|100%|| |OpenRouter.Net.Models.Responses.AssistantDelta|100%|100%| |OpenRouter.Net.Models.Responses.ChatCompletionChunk|100%|100%| |OpenRouter.Net.Models.Responses.ChatCompletionResponse|100%|100%| |OpenRouter.Net.Models.Responses.Choice|100%|100%| |OpenRouter.Net.Models.Responses.StructuredOutput|100%|100%| |OpenRouter.Net.OpenRouterException|100%|| |System.Text.RegularExpressions.Generated|83.3%|53.8%| |System.Text.RegularExpressions.Generated.RunnerFactory||| |System.Text.RegularExpressions.Generated.RunnerFactory.Runner||| </details> <details><summary>OpenRouter.Net.Agents - 91.7%</summary> |**Name**|**Line**|**Branch**| |:---|---:|---:| |**OpenRouter.Net.Agents**|**91.7%**|**86.6%**| |OpenRouter.Net.Agents.Agent|98.4%|92.6%| |OpenRouter.Net.Agents.Agent.StreamedRound|100%|98.6%| |OpenRouter.Net.Agents.AgentOptions|100%|100%| |OpenRouter.Net.Agents.AgentResult|100%|50%| |OpenRouter.Net.Agents.CallerStates|100%|100%| |OpenRouter.Net.Agents.Extensions.ServiceCollectionExtensions|88.2%|100%| |OpenRouter.Net.Agents.Gating.ToolCallGates|100%|100%| |OpenRouter.Net.Agents.Gating.ToolCallGates.PerCallGate|100%|100%| |OpenRouter.Net.Agents.Gating.ToolCallVerdict|100%|| |OpenRouter.Net.Agents.Gating.ToolTurnReview|100%|| |OpenRouter.Net.Agents.RoundDetail|100%|75%| |OpenRouter.Net.Agents.Tools.FileSystem.CopyTool|42.1%|28.5%| |OpenRouter.Net.Agents.Tools.FileSystem.DeleteTool|57.1%|50%| |OpenRouter.Net.Agents.Tools.FileSystem.DiffTool|83.3%|74.2%| |OpenRouter.Net.Agents.Tools.FileSystem.ListDirectoryTool|68%|61.1%| |OpenRouter.Net.Agents.Tools.FileSystem.MoveTool|55%|33.3%| |OpenRouter.Net.Agents.Tools.FileSystem.ReadFileTool|73.6%|50%| |OpenRouter.Net.Agents.Tools.FileSystem.SearchTool|67.5%|70.8%| |OpenRouter.Net.Agents.Tools.FileSystem.WriteFileTool|75%|50%| |OpenRouter.Net.Agents.Tools.ITool|100%|| |OpenRouter.Net.Agents.Tools.SubAgent.SubAgentTool|96.1%|69.5%| |OpenRouter.Net.Agents.Tools.Tool<TParams>|100%|100%| |OpenRouter.Net.Agents.Tools.Tool<TParams>|90%|50%| |OpenRouter.Net.Agents.Tools.ToolInvocationContext|100%|| |OpenRouter.Net.Agents.Tools.ToolMessageExtensions|0%|| |OpenRouter.Net.Agents.Tools.ToolResult|100%|100%| |OpenRouter.Net.Agents.Tools.ToolSchema|100%|100%| |OpenRouter.Net.Agents.Tools.Workspace|100%|91.6%| </details> <details><summary>OpenRouter.Net.Imaging - 81.8%</summary> |**Name**|**Line**|**Branch**| |:---|---:|---:| |**OpenRouter.Net.Imaging**|**81.8%**|**59.3%**| |OpenRouter.Net.Imaging.ImageEncodeOptions|90.9%|75%| |OpenRouter.Net.Imaging.ImageEncoder|80.3%|57.1%| </details>

bjoern merged commit b786f4af17 into main 2026-10-23 18:36:38 +02:00

bjoern deleted branch feat/caller-context 2026-10-23 18:36:38 +02:00

bjoern referenced this pull request from a commit 2026-10-23 18:36:40 +02:00

Merge pull request 'feat: tools and the gate know who the run is for' (#35) from feat/caller-context into main

Sign in to join this conversation.

Reviewers

No reviewers

Labels

Clear labels

No items

No labels

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

2 participants

Notifications

Subscribe

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

TeamAI/OpenRouter.Net!35

No description provided.