feat(skills): channels grid + integrations card polish; tolerant Composio trigger decode#1112
Merged
Merged
Conversation
Contributor
📝 WalkthroughWalkthroughThis PR updates Composio/connect modal copy and toolkit display names, refactors the Skills page to separate Channels and add iMessage support with accompanying tests, tightens USD thresholds to treat <= $0.01 as zero for budget/usage logic and promo banner visibility, and adds resilient Serde deserializers and tests for Composio active trigger fields. ChangesComposio Integration UI & Skills Page refactor
Budget & Usage threshold adjustments
Composio trigger deserialization robustness (Rust)
Estimated code review effort🎯 4 (Complex) | ⏱️ ~45 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Review rate limit: 4/5 reviews remaining, refill in 12 minutes. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
app/src/hooks/useUsageState.ts (1)
79-104:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winAlign
isRateLimitedwith the new near-zero threshold semantics.
usagePct10h/budget flags now treat<= 0.01as zero, butisRateLimitedstill usesfiveHourCapUsd > 0(Line 103). For tiny caps, this can still mark users as rate-limited while other state says effectively zero budget.Suggested fix
const isRateLimited = teamUsage !== null && !teamUsage.bypassCycleLimit && - teamUsage.fiveHourCapUsd > 0 && + teamUsage.fiveHourCapUsd > 0.01 && teamUsage.cycleLimit5hr >= teamUsage.fiveHourCapUsd;🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@app/src/hooks/useUsageState.ts` around lines 79 - 104, Update isRateLimited to use the same near-zero threshold as the other budget checks: change the fiveHourCapUsd condition in isRateLimited (currently checking fiveHourCapUsd > 0) to use > 0.01, keeping the rest of the logic (!teamUsage.bypassCycleLimit and cycleLimit5hr >= fiveHourCapUsd) unchanged so tiny caps are treated as zero-consistent with usagePct10h and budget flags.
🧹 Nitpick comments (1)
src/openhuman/composio/types.rs (1)
245-264: ⚡ Quick winPlease add regression tests for the new tolerant trigger decoding path.
This path now handles multiple upstream shapes; adding focused tests for string/object variants (especially mixed-key
stateobjects) will protect against silent regressions.Example tests to add
+ #[test] + fn active_trigger_deserializes_string_and_object_fields() { + let raw = json!({ + "id": {"id": "trg_1"}, + "slug": {"slug": "GMAIL_NEW_GMAIL_MESSAGE"}, + "toolkit": {"slug": "gmail", "name": "Gmail"}, + "connectionId": {"id": "conn_1"}, + "state": {"state": "ACTIVE", "id": "meta_ignored"} + }); + let t: ComposioActiveTrigger = serde_json::from_value(raw).unwrap(); + assert_eq!(t.id, "trg_1"); + assert_eq!(t.slug, "GMAIL_NEW_GMAIL_MESSAGE"); + assert_eq!(t.toolkit, "gmail"); + assert_eq!(t.connection_id, "conn_1"); + assert_eq!(t.state.as_deref(), Some("ACTIVE")); + }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@src/openhuman/composio/types.rs` around lines 245 - 264, Add focused regression tests that exercise the tolerant trigger decoding path in types.rs by covering both string and object variants for fields using de_string_or_object and de_opt_string_or_object (notably the struct fields trigger_config and state), including mixed-key/state-as-object cases and combinations (e.g., state as string, state as object, trigger_config present/absent). Write tests that deserialize representative JSON payloads into the target struct and assert the resulting id/slug/toolkit/connection_id/trigger_config/state values match expectations; include negative cases where malformed shapes should fail if appropriate. Place tests near existing serde tests for composio types and reference the deserializers de_string_or_object and de_opt_string_or_object so future changes to those functions will be covered. Ensure tests are deterministic and cover both Option::None and Some(...) branches for state.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/openhuman/composio/types.rs`:
- Around line 52-53: The loop that picks a string from JSON fields uses a
priority order ["slug","id","name","key","value","state"] which can pick
metadata keys before the actual "state" or "value"; update the selection logic
in the deserialization code that contains the for key in ["slug", "id", "name",
"key", "value", "state"] construct so it prefers "state" and "value" (or
explicitly matches the exact intended field) before metadata keys (or switch to
exact-key matching rather than first-found priority), and apply the same fix at
the other occurrence around lines 259-264 to ensure correct deserialization of
state strings.
---
Outside diff comments:
In `@app/src/hooks/useUsageState.ts`:
- Around line 79-104: Update isRateLimited to use the same near-zero threshold
as the other budget checks: change the fiveHourCapUsd condition in isRateLimited
(currently checking fiveHourCapUsd > 0) to use > 0.01, keeping the rest of the
logic (!teamUsage.bypassCycleLimit and cycleLimit5hr >= fiveHourCapUsd)
unchanged so tiny caps are treated as zero-consistent with usagePct10h and
budget flags.
---
Nitpick comments:
In `@src/openhuman/composio/types.rs`:
- Around line 245-264: Add focused regression tests that exercise the tolerant
trigger decoding path in types.rs by covering both string and object variants
for fields using de_string_or_object and de_opt_string_or_object (notably the
struct fields trigger_config and state), including mixed-key/state-as-object
cases and combinations (e.g., state as string, state as object, trigger_config
present/absent). Write tests that deserialize representative JSON payloads into
the target struct and assert the resulting
id/slug/toolkit/connection_id/trigger_config/state values match expectations;
include negative cases where malformed shapes should fail if appropriate. Place
tests near existing serde tests for composio types and reference the
deserializers de_string_or_object and de_opt_string_or_object so future changes
to those functions will be covered. Ensure tests are deterministic and cover
both Option::None and Some(...) branches for state.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 6618d92a-9ca4-4bea-99e2-903fe6de3cd8
⛔ Files ignored due to path filters (2)
Cargo.lockis excluded by!**/*.lockapp/src-tauri/Cargo.lockis excluded by!**/*.lock
📒 Files selected for processing (7)
app/src/components/composio/ComposioConnectModal.tsxapp/src/components/composio/toolkitMeta.tsxapp/src/components/skills/skillIcons.tsxapp/src/hooks/useUsageState.tsapp/src/pages/Home.tsxapp/src/pages/Skills.tsxsrc/openhuman/composio/types.rs
…grid coverage, prefer state/value keys in tolerant decoder
- Update Skills Notion test for the trimmed modal copy ("Connect your Notion account.").
- Add Skills.channels-grid test covering ChannelTile rendering, setup-modal open, and absence of the Channels chip.
- Address CodeRabbit feedback: `de_opt_string_or_object` now prefers `state`/`value` keys before slug/id metadata.
- Add Rust unit tests for ComposioActiveTrigger string + object payloads.
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
app/src/pages/__tests__/Skills.channels-grid.test.tsx (1)
60-63: ⚡ Quick winAvoid scoping these tests with
.rounded-2xl.Both lookups depend on a styling class, so a visual-only refactor will break the suite even if the UI still works. Please switch to a semantic hook on the card and query that instead.
As per coding guidelines,
app/src/**/*.test.{ts,tsx}: Prefer testing behavior over implementation details.Also applies to: 80-83
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@app/src/pages/__tests__/Skills.channels-grid.test.tsx` around lines 60 - 63, The tests currently scope the card using a styling class via channelsHeading.closest('.rounded-2xl') and then call within(channelsCard as HTMLElement); replace this brittle selector with a semantic hook on the card (e.g., an accessible role/aria-label or existing data-testid like "channels-card") and query that element (e.g., getByRole/getByLabelText/getByTestId) instead, then pass the found element into within(...) using the same within$ variable; make the same replacement for the other occurrence that mirrors lines 80-83 so no tests rely on the '.rounded-2xl' styling class.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@app/src/pages/__tests__/Skills.channels-grid.test.tsx`:
- Around line 60-63: The tests currently scope the card using a styling class
via channelsHeading.closest('.rounded-2xl') and then call within(channelsCard as
HTMLElement); replace this brittle selector with a semantic hook on the card
(e.g., an accessible role/aria-label or existing data-testid like
"channels-card") and query that element (e.g.,
getByRole/getByLabelText/getByTestId) instead, then pass the found element into
within(...) using the same within$ variable; make the same replacement for the
other occurrence that mirrors lines 80-83 so no tests rely on the '.rounded-2xl'
styling class.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: b7fa655d-a47d-4b4f-bad4-c3e48baa5806
📒 Files selected for processing (3)
app/src/pages/__tests__/Skills.channels-grid.test.tsxapp/src/pages/__tests__/Skills.third-party-notion-debug-tools.test.tsxsrc/openhuman/composio/types.rs
🚧 Files skipped from review as they are similar to previous changes (1)
- src/openhuman/composio/types.rs
… ignore unreachable BUILT_IN_SKILLS branches - Drop dead `ConnectionBadge`/`isMessagingId` import (the channel branch in renderGroup is gone now that channels render via ChannelTile). - Mark the unreachable per-id BUILT_IN_SKILLS branches in renderGroup with v8 ignore so diff-cover doesn't count code that can't fire while the list is empty. - Extend the channels-grid test with parameterized cases for connected / connecting / error states so the ChannelTile className branches are covered. - New Skills.discovered-skills test renders user / project / legacy scope rows, asserts the scope-color mapping, that Uninstall only surfaces on user-scope, and that View opens the detail drawer.
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
app/src/pages/Skills.tsx (1)
570-729: 💤 Low valueMissing explicit return for
channelkind inrenderGroupmap.The
items.mapcallback handles'builtin'and'discovered'kinds but has no explicit case for'channel'. While channels are filtered out viaotherGroups(line 550), if one ever slips through due to a future refactor, the callback would implicitly returnundefined, rendering nothing silently.Consider adding an explicit defensive case:
🛡️ Defensive fix
); } + // Channels are rendered in a dedicated card above; skip if one leaks through. + if (item.kind === 'channel') { + return null; + } + return null; // Exhaustive fallback })}🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@app/src/pages/Skills.tsx` around lines 570 - 729, The map callback over items (items.map) currently handles 'builtin' and 'discovered' but lacks an explicit branch for item.kind === 'channel', which can lead to an implicit undefined return; add a defensive case for channel inside the same map (or a final else) that explicitly returns either a UnifiedSkillCard representing the channel (using item.id, item.icon, item.name, item.description and navigate(item.route!)) or returns null while logging a warning (e.g., console.warn('[skills] unexpected channel item', { id: item.id })) so the intent is explicit and no implicit undefined is rendered; update the code paths that set secondaryActions/onCtaClick accordingly.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@app/src/pages/__tests__/Skills.channels-grid.test.tsx`:
- Around line 35-41: The current mocks point to the wrong module and are dead —
remove the vi.mock calls that target the unused module paths and instead add a
mock for the actual API used by Skills.tsx: mock the skillsApi module so that
skillsApi.listSkills is stubbed (resolve to an empty list or fixture) and also
mock skillsApi.installSkill if the test expects it; ensure the test imports use
the mock by creating a vi.mock for the real skillsApi module and providing
listSkills and installSkill fakes so the component effect
(skillsApi.listSkills()) is driven by the test rather than the real API.
---
Nitpick comments:
In `@app/src/pages/Skills.tsx`:
- Around line 570-729: The map callback over items (items.map) currently handles
'builtin' and 'discovered' but lacks an explicit branch for item.kind ===
'channel', which can lead to an implicit undefined return; add a defensive case
for channel inside the same map (or a final else) that explicitly returns either
a UnifiedSkillCard representing the channel (using item.id, item.icon,
item.name, item.description and navigate(item.route!)) or returns null while
logging a warning (e.g., console.warn('[skills] unexpected channel item', { id:
item.id })) so the intent is explicit and no implicit undefined is rendered;
update the code paths that set secondaryActions/onCtaClick accordingly.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: da4ce6f8-ce70-4473-ae77-65d48a5ef933
📒 Files selected for processing (3)
app/src/pages/Skills.tsxapp/src/pages/__tests__/Skills.channels-grid.test.tsxapp/src/pages/__tests__/Skills.discovered-skills.test.tsx
CodeRabbit flagged the `lib/skills/*` mocks as dead — Skills.tsx imports from `services/api/skillsApi`, so swap to the matching factory (mirrors Skills.discovered-skills.test.tsx) to keep listSkills off the network.
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
app/src/pages/__tests__/Skills.channels-grid.test.tsx (1)
122-128: ⚡ Quick winPrefer behavior assertions over container class-name matching here.
expect(telegramTile.className).toMatch(...)is brittle to style refactors and ties the test to Tailwind internals. Assert observable status/CTA semantics instead (accessible name/text), which is what users actually experience.Suggested refactor
- expect(telegramTile.className).toMatch(classPattern); + expect(telegramTile).toHaveAccessibleName( + new RegExp(`Telegram.*${labelPattern.source}`, 'i') + ); + if (status === 'connected') { + expect(telegramTile).toHaveAccessibleName(/Manage/i); + } else { + expect(telegramTile).toHaveAccessibleName(/Setup/i); + }As per coding guidelines: "Prefer testing behavior over implementation details; use existing helpers from
app/src/test/before adding new harness code".🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@app/src/pages/__tests__/Skills.channels-grid.test.tsx` around lines 122 - 128, The test is asserting on the DOM className (telegramTile.className) which is brittle; replace that with behavior-focused assertions: locate the Telegram tile via the existing telegramTile variable (found with within(...).getByRole('button', ...)) and assert its accessible semantics instead — e.g., that the button's accessible name/text matches labelPattern (using toHaveAccessibleName or checking .textContent), that any status is exposed via aria attributes (aria-pressed/aria-checked/aria-disabled) or that the expected CTA/button state is present, and/or assert that clicking the button triggers the expected handler; remove the classPattern assertion and prefer existing test helpers from app/src/test/ for accessibility assertions.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@app/src/pages/__tests__/Skills.channels-grid.test.tsx`:
- Around line 122-126: The test calls within(channelsCard as HTMLElement) after
const channelsCard = screen.getByRole(...).closest('.rounded-2xl') but closest
can return null; add an explicit non-null guard before using within to produce a
clear failure. Locate the channelsCard variable in the test and add a check
(e.g., expect(channelsCard).not.toBeNull() or if (!channelsCard) throw new
Error(...)) immediately after the closest(...) call, then safely cast
channelsCard to HTMLElement before calling within(...) to find telegramTile via
getByRole.
---
Nitpick comments:
In `@app/src/pages/__tests__/Skills.channels-grid.test.tsx`:
- Around line 122-128: The test is asserting on the DOM className
(telegramTile.className) which is brittle; replace that with behavior-focused
assertions: locate the Telegram tile via the existing telegramTile variable
(found with within(...).getByRole('button', ...)) and assert its accessible
semantics instead — e.g., that the button's accessible name/text matches
labelPattern (using toHaveAccessibleName or checking .textContent), that any
status is exposed via aria attributes (aria-pressed/aria-checked/aria-disabled)
or that the expected CTA/button state is present, and/or assert that clicking
the button triggers the expected handler; remove the classPattern assertion and
prefer existing test helpers from app/src/test/ for accessibility assertions.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 52c3267d-4386-41ac-809f-f5967d79cdaa
📒 Files selected for processing (1)
app/src/pages/__tests__/Skills.channels-grid.test.tsx
jwalin-shah
added a commit
to jwalin-shah/openhuman
that referenced
this pull request
May 5, 2026
* feat(remotion): Ghosty character library with transparent MOV variants (tinyhumansai#1059) Co-authored-by: WOZCODE <contact@withwoz.com> * feat(composio/gmail): sync into memory tree (Slack-parity) (tinyhumansai#1056) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(scheduler-gate): throttle background AI on battery / busy CPU (tinyhumansai#1062) * fix(core,cef): run core in-process and stop orphaning CEF helpers on Cmd+Q (tinyhumansai#1061) * ci: add dedicated staging release workflow (tinyhumansai#1066) * fix(sentry): Rust source context + per-release deploy marker (tinyhumansai#405) (tinyhumansai#1067) * fix(welcome): re-enable OAuth buttons with focus/timeout recovery (tinyhumansai#1049) (tinyhumansai#1069) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(dependencies): update pnpm-lock.yaml and Cargo.lock for package… (tinyhumansai#1082) * fix(onboarding): personalize welcome agent greeting with user identity (tinyhumansai#1078) * fix(chat): make agent message bubbles fit content width (tinyhumansai#1083) * Feat/dmg checks (tinyhumansai#1084) * fix(linux): Add X11 platform flags to .deb package launcher (tinyhumansai#1087) Co-authored-by: unn-Known1 <unn-known1@users.noreply.github.com> * fix(sentry): auto-send React events; collapse core→tauri for desktop (tinyhumansai#1086) Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> * fix(cef): run blank reload guard on the CEF UI thread (tinyhumansai#1092) * fix(app): reload webview instead of restart_app in dev mode (tinyhumansai#1068) (tinyhumansai#1071) * fix(linux): deliver X11 ozone flags via custom .desktop template (tinyhumansai#1091) * fix(webview-accounts): retry data-dir purge so CEF handle race doesn't leak cookies (tinyhumansai#1076) (tinyhumansai#1081) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> * fix(webview/slack): media perms + deep-link isolation (tinyhumansai#1074) (tinyhumansai#1080) Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> * ci(release): split staging vs production workflows; promote staging tags (tinyhumansai#1094) * Update release-staging.yml (tinyhumansai#1097) * chore(staging): v0.53.5 * chore(staging): v0.53.6 * ci(staging): cut staging from main; add act local-debug helper (tinyhumansai#1099) * chore(staging): v0.53.7 * fix(ci): correct sentry-cli download URL and trap scope (tinyhumansai#1100) * chore(staging): v0.53.8 * feat(chat): forward thread_id to backend for KV cache locality (tinyhumansai#1095) * fix(ci): bump pinned sentry-cli to 3.4.1 (2.34.2 was never published) (tinyhumansai#1102) * chore(staging): v0.53.9 * fix(ci): drop bash trap in upload_sentry_symbols.sh; inline cleanup (tinyhumansai#1103) * chore(staging): v0.53.10 * refactor(session): flatten session_raw/, switch md to YYYY_MM_DD (tinyhumansai#1098) * Add full Composio managed-auth toolkit catalog (tinyhumansai#1093) * ci: add diff-aware 80% coverage gate (Vitest + cargo-llvm-cov) (tinyhumansai#1104) * feat(scripts): pnpm work + pnpm debug for agent-driven workflows (tinyhumansai#1105) * ci: pull pnpm into CI image, drop redundant setup steps (tinyhumansai#1107) * docs: add Cursor Cloud specific instructions to AGENTS.md (tinyhumansai#1106) Co-authored-by: Cursor Agent <cursoragent@cursor.com> * chore(staging): v0.53.11 * docs: surface 80% coverage gate and scripts/debug runners (tinyhumansai#1108) * feat(app): show Composio integrations as sorted icon grid on Skills (tinyhumansai#1109) Co-authored-by: Cursor Agent <cursoragent@cursor.com> * feat(composio): client-side trigger enable/disable toggles (tinyhumansai#1110) * feat(skills): channels grid + integrations card polish; tolerant Composio trigger decode (tinyhumansai#1112) * chore(staging): v0.53.12 * feat(home): early-bird banner + assistant→agent terminology (tinyhumansai#1113) * feat(updater): in-app auto-update with auto-download + restart prompt (tinyhumansai#677) (tinyhumansai#1114) * chore(claude): add ship-and-babysit slash command (tinyhumansai#1115) * feat(home): EarlyBirdyBanner + agent terminology + LinkedIn enrichment model pin (tinyhumansai#1118) * fix(chat): single onboarding thread in sidebar after wizard (tinyhumansai#1116) Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Steven Enamakel <senamakel@users.noreply.github.com> * fix: filter out global namespace from citation chips (tinyhumansai#1124) Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: senamakel-droid <281415773+senamakel-droid@users.noreply.github.com> * feat(nav): enable Memory tab in BottomTabBar (tinyhumansai#1125) * feat(memory): singleton ingestion + status RPC + UI pill (tinyhumansai#1126) * feat(human): mascot tab with viseme-driven lipsync (staging only) (tinyhumansai#1127) * Fix CEF zombie processes on full app close and restart (tinyhumansai#1128) Co-authored-by: senamakel-droid <281415773+senamakel-droid@users.noreply.github.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> * Update issue templates for GitHub issue types (tinyhumansai#1146) * feat(human): expand mascot expressions and tighten reply-speech state machine (tinyhumansai#1147) * feat(memory): ingestion pipeline + tree-architecture docs + ops/schemas split (tinyhumansai#1142) * feat(threads): surface live subagent work in parent thread (tinyhumansai#1122) (tinyhumansai#1159) * fix(human): keep mascot mouth animating when TTS ships no viseme data (tinyhumansai#1160) * feat(composio): consume backend markdownFormatted for LLM output (tinyhumansai#1165) * fix(subagent): lazy-register toolkit actions filtered out of fuzzy top-K (tinyhumansai#1162) * feat(memory): user-facing long-term memory window preset (tinyhumansai#1137) (tinyhumansai#1161) * fix(tauri-shell): proactively kill stale openhuman RPC on startup (tinyhumansai#1166) * chore(staging): v0.53.13 * fix(composio): per-action tool consumes backend markdownFormatted (tinyhumansai#1167) * fix(threads): persist selectedThreadId across reloads (tinyhumansai#1168) * feat(memory_tree): switch embed model to bge-m3 (1024-dim, 8K context) (tinyhumansai#1174) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(agent): drop redundant [Memory context] recall injection (tinyhumansai#1173) * chore(memory_tree): drop body-read timeouts on Ollama HTTP calls (tinyhumansai#1171) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(transcript): emit thread_id + fix orchestrator missing cost (tinyhumansai#1169) * fix(composio/gmail): phase out html2md, prefer text/plain MIME part (tinyhumansai#1170) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(tools): markdown output for internal tool results (tinyhumansai#1172) * feat(security): enforce prompt-injection guard before model and tool execution (tinyhumansai#1175) * fix(cef): popup paint dies after first frame — skip blank-page guard for popups (tinyhumansai#1079) (tinyhumansai#1182) Co-authored-by: Steven Enamakel <31011319+senamakel@users.noreply.github.com> * chore(sentry): rename OPENHUMAN_SENTRY_DSN → OPENHUMAN_CORE_SENTRY_DSN (tinyhumansai#1186) * feat(remotion): add yellow mascot character with all animation variants (tinyhumansai#1193) Co-authored-by: Neel Mistry <neelmistry@Neels-MacBook-Pro.local> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor(composio): hide raw connection ID, derive friendly label (tinyhumansai#1153) (tinyhumansai#1185) Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> * fix(windows): align install.ps1 MSI with per-machine scope (tinyhumansai#913) (tinyhumansai#1187) Co-authored-by: Cursor <cursoragent@cursor.com> * fix(tauri): deterministic CEF teardown on full app close (tinyhumansai#1120) (tinyhumansai#1189) Co-authored-by: Cursor <cursoragent@cursor.com> * fix(composio): cap Gmail HTML body before strip (crash mitigation) (tinyhumansai#1191) Co-authored-by: Cursor <cursoragent@cursor.com> * fix(auth): stop stale chat threads after signup (tinyhumansai#1192) Co-authored-by: Cursor <cursoragent@cursor.com> * feat(sentry): staging-only "Trigger Sentry Test" button (tinyhumansai#1072) (tinyhumansai#1183) * chore(staging): v0.53.14 * chore(staging): v0.53.15 * feat(composio): format trigger slugs into human-readable labels (tinyhumansai#1129) (tinyhumansai#1179) Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> * fix(ui): hide unsupported permission UI on non-macOS for Screen Intelligence (tinyhumansai#1194) Co-authored-by: Cursor <cursoragent@cursor.com> * chore(tauri-shell): retire embedded Gmail webview-account flow (tinyhumansai#1181) * feat(onboarding): replace welcome-agent bot with react-joyride walkthrough (tinyhumansai#1180) * chore(release): v0.53.16 * fix(threads): preserve selectedThreadId on cold-boot identity hydration (tinyhumansai#1196) * feat(core): version/shutdown/update RPCs + mid-thread integration refresh (tinyhumansai#1195) * fix(mascot): swap to yellow mascot via @remotion/player (tinyhumansai#1200) * feat(memory_tree): cloud-default LLM, queue priority, entity filter, Memory tab UI (tinyhumansai#1198) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Persist turn state + restore conversation history on cold-boot (tinyhumansai#1202) * feat(mascot): floating desktop mascot via native NSPanel + WKWebView (macOS) (tinyhumansai#1203) * fix(memory/tree): emit summary children as Obsidian wikilinks (tinyhumansai#1210) Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(tools): coding-harness baseline primitives (tinyhumansai#1205) (tinyhumansai#1208) * docs: add Codex PR checklist for remote agents --------- Co-authored-by: Steven Enamakel <31011319+senamakel@users.noreply.github.com> Co-authored-by: WOZCODE <contact@withwoz.com> Co-authored-by: sanil-23 <sanil@vezures.xyz> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: Cyrus Gray <144336577+graycyrus@users.noreply.github.com> Co-authored-by: CodeGhost21 <164498022+CodeGhost21@users.noreply.github.com> Co-authored-by: oxoxDev <164490987+oxoxDev@users.noreply.github.com> Co-authored-by: Mega Mind <146339422+M3gA-Mind@users.noreply.github.com> Co-authored-by: Gaurang Patel <ptelgm.yt@gmail.com> Co-authored-by: unn-Known1 <unn-known1@users.noreply.github.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Steven Enamakel <senamakel@users.noreply.github.com> Co-authored-by: Steven Enamakel's Droid <enamakel.agent@tinyhumans.ai> Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com> Co-authored-by: senamakel-droid <281415773+senamakel-droid@users.noreply.github.com> Co-authored-by: YellowSnnowmann <167776381+YellowSnnowmann@users.noreply.github.com> Co-authored-by: Neil <neil@maha.xyz> Co-authored-by: Neel Mistry <neelmistry@Neels-MacBook-Pro.local> Co-authored-by: obchain <167975049+obchain@users.noreply.github.com> Co-authored-by: Jwalin Shah <jshah1331@gmail.com>
AusAgentSmith
pushed a commit
to AusAgentSmith/openhuman
that referenced
this pull request
May 23, 2026
…osio trigger decode (tinyhumansai#1112)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
ComposioActiveTriggerdeserialization tolerant of upstream API shape drift (e.g.toolkitarriving as an object instead of a string), fixing the runtimeCouldn't load triggers: ... invalid type: map, expected a stringerror in the modal.Problem
composio_list_triggersstarted failing at runtime because Composio now returns objects (e.g.toolkit: { slug: ... }) where our struct expected plain strings, blocking the trigger toggles inside the connect modal.Solution
ChannelTilemirrorsComposioConnectorTilestyling (12×12 icon, name, status label, sage outline when connected) so Channels and Integrations look like one cohesive surface.de_string_or_object/de_opt_string_or_objecthelpers insrc/openhuman/composio/types.rsaccept either a string or an object (extractingslug/id/name/key), applied toComposioActiveTrigger'sid,slug,toolkit,connection_id, andstatefields.Submission Checklist
Impact
Summary by CodeRabbit
New Features
Improvements
Tests