Rho SDK changelog

This changelog covers the embeddable rho-sdk crate.

5.5.0 (2026-09-21)

Features

• xai: add grok-4.7 and toggle fast serving with /fast (#1237) (b45f01c)

5.4.1 (2026-09-21)

Bug Fixes

• compaction: honor provider usage at automatic thresholds (#1224) (2b0fdf5)

5.4.0 (2026-09-10)

Features

• computer: add opt-in desktop control through Cua Driver (#1200) (8fb622a)

Bug Fixes

• codex: preserve encrypted reasoning across model switches (#1198) (2a37242)
• sdk: keep tool history paired when cancelling agents (#1199) (d8a2e87)

5.3.0 (2026-09-06)

Features

• questionnaire: allow explicit timed fallback answers (#1184) (3f66de5)

Bug Fixes

• codex: preserve compaction summaries across model switches (#1181) (af9e72e)
• tui: keep agent notifications distinct from human messages (#1182) (ab689b5)

5.2.1 (2026-09-05)

Bug Fixes

• runtime: reconcile background notifications before completion (#1166) (b5630f6)

Performance Improvements

• runtime: speed up session replay and streamed rendering (#1163) (242460c)

5.2.0 (2026-09-04)

Features

• openai: forward mid-turn steering over the Codex websocket on gpt-6-astra (#1150) (3628bda)
• openai: send reasoning changes as configuration_update on gpt-6-astra (#1149) (7928476)
• rho-sdk: run async tool calls as detached jobs (#1151) (ed4c276)

5.1.2 (2026-09-03)

Bug Fixes

• compaction: /compact always shrinks context on large-window models (#1132) (d7522b6)

5.1.1 (2026-08-30)

Bug Fixes

• sdk: stop burst-replayed proxy streams from inflating tok/s (#1103) (d4e88ae)

5.1.0 (2026-08-30)

Features

• sdk: put the requested capability on after_tool_use (#1090) (90f1a0e)
• tui: add /side overlay for frozen-context asides (#1094) (3ebbdf9)

5.0.0 (2026-08-27)

⚠ BREAKING CHANGES

• rho-sdk removes RunEvent::ProviderActivity and the PROVIDER_ACTIVITY_* constants, collapses ProviderStreamResetReason retryable variants into RetryableFailure { kind, retry_after }, removes ModelCallMetrics::output_tokens_per_second, adds revision to RunEvent::Failed, folds ContextEstimated into StepStarted, and replaces the stringly generation-output-token carriers with a typed ModelCallMetrics::generation_output_tokens metric and ModelEvent::GenerationOutputTokens variant. rho-providers adds ProviderId::OpenAiCompatible for config-defined hosts, folds CustomProviderOptions into CustomProviderSpec (removing the _with_lookup/ _with_options funnels), makes providers() include custom hosts (removing visible_providers), removes deprecated registry API-base re-exports and ProviderRuntime::same_family, and drops the CredentialStore parameter from OpenAiProvider::new_with_identity. rho-tools removes the edit_file tool-name alias, the write_file frontmatter alias, and the EditToolKind type alias.

Code Refactoring

• pay down all NEXT_MAJOR debt for the next major, net -986 lines (#1062) (0e17bdb)

4.2.0 (2026-08-21)

Features

• acp: let hosts set reasoning through thought_level (#1015) (5cda8e8)

4.1.1 (2026-08-20)

Bug Fixes

• tui: stop openai-compatible cost jumping on submit (#1008) (51f881f)

4.1.0 (2026-08-17)

Features

• xai: let grok generate and edit images in the conversation (#967) (47c03c1)

4.0.1 (2026-08-15)

Bug Fixes

• session: v1 upgrades no longer write an unloadable transcript (#939) (1dc1002)

4.0.0 (2026-08-12)

⚠ BREAKING CHANGES

• hooks: AuthorizationDenialKind and ApprovalAuditDecision gain a hook variant. Both are #[non_exhaustive], so only exhaustive matches written before this change need updating.
• xai: ModelEvent::WebSearch and RunEvent::WebSearch now carry a name field so hosts can distinguish web_search from x_search.

Features

• add advisor mode with a selectable advisor model (#752) (13c1ebb)
• config: mid-session edit tool, advisor, and auto preference (#840) (423d026)
• hooks: add typed lifecycle hooks (#668) (4a69c3d)
• openai: add fast mode (#610) (8c5cd6d)
• permission: rename Auto to Bypass and add classifier Auto (#870) (3192daa)
• providers: add native Google Gemini support (#430) (34ef307)
• providers: add Qwen Token Plan OpenAI-compatible provider (#738) (6aa6df2)
• providers: use OpenAI server-side compaction for codex and api-key (#514) (b18eadd)
• questionnaire: add focused default selection (#530) (47d1853)
• questionnaire: support choice descriptions (#510) (066899c)
• sdk: add embeddable Rho runtime (#262) (6fdac81)
• sdk: execute independent tool calls concurrently (#459) (0bb5a83)
• sessions: add conversation tree navigation (#474) (8abb138)
• subagents: add parent-child plain-text messaging for Rho runtime (#852) (dd25d8e)
• subagents: route background questionnaires to parent (#539) (e0cab31)
• tui: add retractable pending input (#334) (5f293a2)
• tui: redesign questionnaire with tabbed question layout (#369) (a90135a)
• tui: render read file image previews (#393) (52165ec)
• tui: show detailed activity stages (#403) (267a47b)
• tui: show model output token rate (#623) (a5aa688)
• usage: add durable request ledger (#381) (0502b99)
• workflow: add deterministic DAG workflows (#680) (77f36f9)
• xai: support hosted x_search tool (#647) (cd0c897)

Bug Fixes

• exclude reasoning tokens from throughput (#819) (d261b5b)
• kimi: use provider-native K3 reasoning (#402) (5453cdc)
• metrics: include reasoning latency in output rate (#632) (7f7fa39)
• openai: align Codex Responses wire contracts (#644) (76cf855)
• poolside: publish final stream usage snapshot (#516) (d51ebab)
• providers: show bounded error diagnostics (#344) (e3fc489)
• providers: surface rate-limit reset time and /limits pointer (#733) (b9371fc)
• sdk: commit turn history on provider failure (#739) (b4158ab)
• sdk: recover failed 1.17.1 release packaging (#587) (224189e)
• sdk: recover failed 1.32.0 release packaging (#792) (a782145)
• sdk: retry retryable provider failures instead of failing the run (#401) (b2867da)
• sdk: serialize identical concurrent approval requests to prompt once (#469) (45b2b0a)
• sdk: stabilize compaction release benchmark (#561) (8364edc)
• skills: enforce manual skill invocation (#453) (4f6f043)
• subagents: run multi-agent batches in parallel (#544) (7dd6706)
• tools: allow file paths outside workspace (#537) (8a3cc24)
• tools: scrub provider credential env vars from child processes (#502) (6d66913)
• tui: open approval prompts at the start and default to deny (#636) (59efc07)
• tui: report generation token throughput (#803) (4772f68)
• tui: report herdr blocked during questionnaire (#500) (1dcdbe9)
• tui: show codex fast mode and report tier fallback (#663) (177043f)
• tui: show hosted x_search tool cards (#662) (4381667)
• tui: stabilize live stream tool cards and markdown previews (#595) (752794f)

Performance Improvements

• optimize orchestration and session hot paths (#603) (62aa8f5)
• reduce hot-path allocations and redundant I/O (#280) (c18e582)
• sdk: avoid duplicate history clone during compaction (#276) (79e3926)

3.0.0 (2026-08-11)

⚠ BREAKING CHANGES

• hooks: AuthorizationDenialKind and ApprovalAuditDecision gain a hook variant. Both are #[non_exhaustive], so only exhaustive matches written before this change need updating.
• xai: ModelEvent::WebSearch and RunEvent::WebSearch now carry a name field so hosts can distinguish web_search from x_search.

Features

• add advisor mode with a selectable advisor model (#752) (13c1ebb)
• config: mid-session edit tool, advisor, and auto preference (#840) (423d026)
• hooks: add typed lifecycle hooks (#668) (4a69c3d)
• openai: add fast mode (#610) (8c5cd6d)
• providers: add native Google Gemini support (#430) (34ef307)
• providers: add Qwen Token Plan OpenAI-compatible provider (#738) (6aa6df2)
• providers: use OpenAI server-side compaction for codex and api-key (#514) (b18eadd)
• questionnaire: add focused default selection (#530) (47d1853)
• questionnaire: support choice descriptions (#510) (066899c)
• sdk: add embeddable Rho runtime (#262) (6fdac81)
• sdk: execute independent tool calls concurrently (#459) (0bb5a83)
• sessions: add conversation tree navigation (#474) (8abb138)
• subagents: add parent-child plain-text messaging for Rho runtime (#852) (dd25d8e)
• subagents: route background questionnaires to parent (#539) (e0cab31)
• tui: add retractable pending input (#334) (5f293a2)
• tui: redesign questionnaire with tabbed question layout (#369) (a90135a)
• tui: render read file image previews (#393) (52165ec)
• tui: show detailed activity stages (#403) (267a47b)
• tui: show model output token rate (#623) (a5aa688)
• usage: add durable request ledger (#381) (0502b99)
• workflow: add deterministic DAG workflows (#680) (77f36f9)
• xai: support hosted x_search tool (#647) (cd0c897)

Bug Fixes

• exclude reasoning tokens from throughput (#819) (d261b5b)
• kimi: use provider-native K3 reasoning (#402) (5453cdc)
• metrics: include reasoning latency in output rate (#632) (7f7fa39)
• openai: align Codex Responses wire contracts (#644) (76cf855)
• poolside: publish final stream usage snapshot (#516) (d51ebab)
• providers: show bounded error diagnostics (#344) (e3fc489)
• providers: surface rate-limit reset time and /limits pointer (#733) (b9371fc)
• sdk: commit turn history on provider failure (#739) (b4158ab)
• sdk: recover failed 1.17.1 release packaging (#587) (224189e)
• sdk: recover failed 1.32.0 release packaging (#792) (a782145)
• sdk: retry retryable provider failures instead of failing the run (#401) (b2867da)
• sdk: serialize identical concurrent approval requests to prompt once (#469) (45b2b0a)
• sdk: stabilize compaction release benchmark (#561) (8364edc)
• skills: enforce manual skill invocation (#453) (4f6f043)
• subagents: run multi-agent batches in parallel (#544) (7dd6706)
• tools: allow file paths outside workspace (#537) (8a3cc24)
• tools: scrub provider credential env vars from child processes (#502) (6d66913)
• tui: open approval prompts at the start and default to deny (#636) (59efc07)
• tui: report generation token throughput (#803) (4772f68)
• tui: report herdr blocked during questionnaire (#500) (1dcdbe9)
• tui: show codex fast mode and report tier fallback (#663) (177043f)
• tui: show hosted x_search tool cards (#662) (4381667)
• tui: stabilize live stream tool cards and markdown previews (#595) (752794f)

Performance Improvements

• optimize orchestration and session hot paths (#603) (62aa8f5)
• reduce hot-path allocations and redundant I/O (#280) (c18e582)
• sdk: avoid duplicate history clone during compaction (#276) (79e3926)

2.0.0 (2026-08-10)

⚠ BREAKING CHANGES

• hooks: AuthorizationDenialKind and ApprovalAuditDecision gain a hook variant. Both are #[non_exhaustive], so only exhaustive matches written before this change need updating.
• xai: ModelEvent::WebSearch and RunEvent::WebSearch now carry a name field so hosts can distinguish web_search from x_search.

Features

• add advisor mode with a selectable advisor model (#752) (13c1ebb)
• config: mid-session edit tool, advisor, and auto preference (#840) (423d026)
• hooks: add typed lifecycle hooks (#668) (4a69c3d)
• openai: add fast mode (#610) (8c5cd6d)
• providers: add native Google Gemini support (#430) (34ef307)
• providers: add Qwen Token Plan OpenAI-compatible provider (#738) (6aa6df2)
• providers: use OpenAI server-side compaction for codex and api-key (#514) (b18eadd)
• questionnaire: add focused default selection (#530) (47d1853)
• questionnaire: support choice descriptions (#510) (066899c)
• sdk: add embeddable Rho runtime (#262) (6fdac81)
• sdk: execute independent tool calls concurrently (#459) (0bb5a83)
• sessions: add conversation tree navigation (#474) (8abb138)
• subagents: route background questionnaires to parent (#539) (e0cab31)
• tui: add retractable pending input (#334) (5f293a2)
• tui: redesign questionnaire with tabbed question layout (#369) (a90135a)
• tui: render read file image previews (#393) (52165ec)
• tui: show detailed activity stages (#403) (267a47b)
• tui: show model output token rate (#623) (a5aa688)
• usage: add durable request ledger (#381) (0502b99)
• workflow: add deterministic DAG workflows (#680) (77f36f9)
• xai: support hosted x_search tool (#647) (cd0c897)

Bug Fixes

• exclude reasoning tokens from throughput (#819) (d261b5b)
• kimi: use provider-native K3 reasoning (#402) (5453cdc)
• metrics: include reasoning latency in output rate (#632) (7f7fa39)
• openai: align Codex Responses wire contracts (#644) (76cf855)
• poolside: publish final stream usage snapshot (#516) (d51ebab)
• providers: show bounded error diagnostics (#344) (e3fc489)
• providers: surface rate-limit reset time and /limits pointer (#733) (b9371fc)
• sdk: commit turn history on provider failure (#739) (b4158ab)
• sdk: recover failed 1.17.1 release packaging (#587) (224189e)
• sdk: recover failed 1.32.0 release packaging (#792) (a782145)
• sdk: retry retryable provider failures instead of failing the run (#401) (b2867da)
• sdk: serialize identical concurrent approval requests to prompt once (#469) (45b2b0a)
• sdk: stabilize compaction release benchmark (#561) (8364edc)
• skills: enforce manual skill invocation (#453) (4f6f043)
• subagents: run multi-agent batches in parallel (#544) (7dd6706)
• tools: allow file paths outside workspace (#537) (8a3cc24)
• tools: scrub provider credential env vars from child processes (#502) (6d66913)
• tui: open approval prompts at the start and default to deny (#636) (59efc07)
• tui: report generation token throughput (#803) (4772f68)
• tui: report herdr blocked during questionnaire (#500) (1dcdbe9)
• tui: show codex fast mode and report tier fallback (#663) (177043f)
• tui: show hosted x_search tool cards (#662) (4381667)
• tui: stabilize live stream tool cards and markdown previews (#595) (752794f)

Performance Improvements

• optimize orchestration and session hot paths (#603) (62aa8f5)
• reduce hot-path allocations and redundant I/O (#280) (c18e582)
• sdk: avoid duplicate history clone during compaction (#276) (79e3926)

1.17.3 (2026-08-08)

Bug Fixes

• exclude reasoning tokens from throughput (#819) (d261b5b)

1.17.2 (2026-08-07)

Bug Fixes

• tui: report generation token throughput (#803) (4772f68)

1.17.1 (2026-08-07)

Bug Fixes

• sdk: recover failed 1.32.0 release packaging (#792) (a782145)

1.17.0 (2026-08-06)

Features

• add advisor mode with a selectable advisor model (#752) (13c1ebb)

1.16.0 (2026-08-04)

Features

• providers: add Qwen Token Plan OpenAI-compatible provider (#738) (6aa6df2)

1.15.2 (2026-08-04)

Bug Fixes

• sdk: commit turn history on provider failure (#739) (b4158ab)

1.15.1 (2026-08-03)

Bug Fixes

• providers: surface rate-limit reset time and /limits pointer (#733) (b9371fc)

1.15.0 (2026-08-02)

Features

• workflow: add deterministic DAG workflows (#680) (77f36f9)

1.14.0 (2026-07-31)

Features

• hooks: add typed lifecycle hooks (#668) (4a69c3d)

1.13.1 (2026-07-30)

Bug Fixes

• tui: show codex fast mode and report tier fallback (#663) (177043f)
• tui: show hosted x_search tool cards (#662) (4381667)

1.13.0 (2026-07-30)

Features

• xai: support hosted x_search tool (#647) (cd0c897)

Bug Fixes

• openai: align Codex Responses wire contracts (#644) (76cf855)

1.12.2 (2026-07-29)

Bug Fixes

• tui: open approval prompts at the start and default to deny (#636) (59efc07)

1.12.1 (2026-07-28)

Bug Fixes

• metrics: include reasoning latency in output rate (#632) (7f7fa39)

1.12.0 (2026-07-28)

Features

• tui: show model output token rate (#623) (a5aa688)

1.11.0 (2026-07-28)

Features

• openai: add fast mode (#610) (8c5cd6d)

Performance Improvements

• optimize orchestration and session hot paths (#603) (62aa8f5)

1.10.3 (2026-07-27)

Bug Fixes

• tui: stabilize live stream tool cards and markdown previews (#595) (752794f)

1.10.2 (2026-07-27)

Bug Fixes

• sdk: recover failed 1.17.1 release packaging (#587) (224189e)

1.10.1 (2026-07-26)

Bug Fixes

• sdk: stabilize compaction release benchmark (#561) (8364edc)

1.10.0 (2026-07-25)

Features

• subagents: route background questionnaires to parent (#539) (e0cab31)

Bug Fixes

• subagents: run multi-agent batches in parallel (#544) (7dd6706)
• tools: allow file paths outside workspace (#537) (8a3cc24)

1.9.0 (2026-07-24)

Features

• questionnaire: add focused default selection (#530) (47d1853)

1.8.0 (2026-07-23)

Features

• providers: use OpenAI server-side compaction for codex and api-key (#514) (b18eadd)
• questionnaire: support choice descriptions (#510) (066899c)

Bug Fixes

• poolside: publish final stream usage snapshot (#516) (d51ebab)

1.7.2 (2026-07-22)

Bug Fixes

• tools: scrub provider credential env vars from child processes (#502) (6d66913)
• tui: report herdr blocked during questionnaire (#500) (1dcdbe9)

1.7.1 (2026-07-22)

Bug Fixes

• sdk: serialize identical concurrent approval requests to prompt once (#469) (45b2b0a)

1.7.0 (2026-07-22)

Features

• sessions: add conversation tree navigation (#474) (8abb138)

1.6.0 (2026-07-21)

Features

• sdk: execute independent tool calls concurrently (#459) (0bb5a83)

Bug Fixes

• skills: enforce manual skill invocation (#453) (4f6f043)

1.5.0 (2026-07-20)

Features

• providers: add native Google Gemini support (#430) (34ef307)

1.4.0 (2026-07-20)

Features

• tui: show detailed activity stages (#403) (267a47b)

Bug Fixes

• kimi: use provider-native K3 reasoning (#402) (5453cdc)
• sdk: retry retryable provider failures instead of failing the run (#401) (b2867da)

1.3.0 (2026-07-18)

Features

• tui: render read file image previews (#393) (52165ec)

1.2.0 (2026-07-17)

Features

• tui: redesign questionnaire with tabbed question layout (#369) (a90135a)
• usage: add durable request ledger (#381) (0502b99)

1.1.0 (2026-07-16)

Features

• tui: add retractable pending input (#334) (5f293a2)

Bug Fixes

• providers: show bounded error diagnostics (#344) (e3fc489)

1.0.2 (2026-07-15)

Performance Improvements

• reduce hot-path allocations and redundant I/O (#280) (c18e582)

1.0.1 (2026-07-15)

Performance Improvements

• sdk: avoid duplicate history clone during compaction (#276) (79e3926)

1.0.0 (2026-07-15)

Features

• sdk: add embeddable Rho runtime (#262) (6fdac81)