When users configure agents.sisyphus-junior.model, category sessions
should use that model without falling back to hardcoded
AGENT_MODEL_REQUIREMENTS. Two leaks existed:
1. Launch-time: category-resolver.ts did not check overrideModel when
deciding whether to use the hardcoded fallbackChain. Fixed by adding
overrideModel to the suppression condition.
2. Runtime retry: model-fallback hook.ts treated undefined fallbackChain
(from setSessionFallbackChain(id, undefined)) as 'no override' and
fell through to AGENT_MODEL_REQUIREMENTS on session.error/status
retry. Fixed by storing explicit empty array and checking .has()
instead of truthiness.
Tests added:
- hook.test.ts: explicit empty session fallback suppresses agent chain
- event.model-fallback-2941.test.ts: session.error does not arm retry
- category-resolver.test.ts: overrideModel suppresses fallbackChain
- tools.test.ts: sisyphusJuniorModel override assertion
When weaker models (GLM-5, MiniMax) omit the description parameter on
delegate_task, the tool now auto-generates it from the first 4 words of
the prompt instead of throwing an error.
Changes:
- Schema: description is now optional (tool.schema.string().optional())
- Runtime: auto-generates from prompt when missing/empty/whitespace
- DelegateTaskArgs.description type stays as string (guaranteed by auto-gen)
- Tests: 3 new cases - missing/empty/explicit description handling
- Metadata title set after description resolution (correct ordering)
OpenCode's fromPlugin wrapper skips Zod validation for plugin tools, so
LLMs can omit required args like description without getting an error.
When Atlas orchestrates and the model omits description, it flows through
as undefined to manager.launch() and background task notifications show
'undefined' for all completed tasks.
Two fixes:
- Add runtime validation for description in delegate-task tool (matches
existing run_in_background and load_skills validation pattern)
- Defensive fallback in notification template: use task ID when
description is missing instead of rendering 'undefined'
- Remove kimi from auto-detected unstable agents in category-resolver (only gemini/minimax remain)
- Add resolveCallID() to safely resolve callID/callId/call_id variants from tool context
- Use resolveCallID across all 5 delegate task execution paths (sync, background, unstable, continuations)
- Update writing category test to verify kimi runs sync when kimi provider is available
- Add atlas metadata preservation tests confirming tool-execute-after does not clobber metadata
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Deep category now uses gpt-5.4 as its default model across all providers
(openai, github-copilot, venice, opencode), matching Hephaestus's GPT 5.4
upgrade. The requiresModel constraint is removed since gpt-5.4 is widely
available. Adds openai/gpt-5.3-codex -> openai/gpt-5.4 config migration
for existing user configs. Deep category prompt optimized for GPT 5.4's
stronger native capabilities (leaner, less verbose).
Remove the auto-defaulting logic from PR #2420 that silently set
run_in_background=false when category/subagent_type/session_id was present.
The tool description falsely claimed 'Default: false' which misled agents
into omitting the parameter. Now the description says REQUIRED and the
validation always throws when the parameter is missing, with a clear
error message guiding the agent to retry with the correct value.
Reverts the behavioral change from #2420 while keeping the issue's
root cause (misleading description) fixed.
- Update DEFAULT_CATEGORIES to use 'openai/gpt-5.4-high' directly instead of separate model + variant
- Add helper functions (isExplicitHighModel, getExplicitHighBaseModel) to preserve explicit high models during fuzzy matching
- Update category resolver to avoid collapsing explicit high models to base model + variant pair
- Update tests to verify explicit high model handling in both background and sync modes
- Update documentation examples to reflect new configuration
🤖 Generated with OhMyOpenCode assistance
Align runtime defaults, tests, docs, and generated artifacts with the newer GPT-5.4 baseline. Keep think-mode and prompt-routing expectations consistent after the model version bump.
Allow users to set `background_task.syncPollTimeoutMs` in config to override
the default 10-minute sync subagent timeout. Affects sync task, sync continuation,
and unstable agent task paths. Minimum value: 60000ms (1 minute).
Co-authored-by: Wine Fox <fox@ling.plus>
When browserProvider is not set, agent-browser skill should NOT resolve.
Test assertions were inverted — expected 'Skills not found' but asserted the opposite.
Category-based delegation (task(category='quick')) was broken because
SISYPHUS_JUNIOR_AGENT sent 'sisyphus-junior' to session.prompt but
config.agent keys are now display names ('Sisyphus-Junior').
- Use getAgentDisplayName() for SISYPHUS_JUNIOR_AGENT constant
- Replace hardcoded 'sisyphus-junior' strings in tools.ts with constant
- Update background-output local constants to use display names
- Add remapCommandAgentFields() to translate command agent fields
- Add raw-key fallback in tool-config-handler agentByKey()
The messages() mock in 'session_id with background=false' test did not
filter by session ID, causing resolveParentContext's SDK calls for
parent-session to increment messagesCallCount. This inflated
anchorMessageCount to 4 (matching total messages), so the poll loop
could never detect new messages and always hit MAX_POLL_TIME_MS.
Fix: filter messages() mock by path.id so only target session
(ses_continue_test) increments the counter. Restore MAX_POLL_TIME_MS
from 8000 back to 2000.
- runner.test.ts: waitForEventProcessorShutdown timeout 50ms → 500ms
(50ms was consistently too tight for CI runners)
- tools.test.ts: MAX_POLL_TIME_MS 2000ms → 8000ms
(polling timed out at ~2009ms on CI due to resource contention)
The polling loop in executeUnstableAgentTask only checked session status
and message stability, never checking if the background task itself had
been interrupted. This caused the tool call to hang until MAX_POLL_TIME_MS
(10 minutes) when a task was interrupted by prompt errors.
Add manager.getTask() check at each poll iteration to break immediately
on terminal statuses (interrupt, error, cancelled), returning a clear
failure message instead of hanging.
LLMs sometimes pass load_skills as a serialized JSON string instead
of an array. Add defensive JSON.parse before validation to handle
this gracefully.
Fixes#1701
Community-reported-by: @omarmciver
Category-based delegation should always route to sisyphus-junior even if
subagent_type is mistakenly provided, matching the original behavior and
preventing accidental bypass of category routing.
Sync task completion was fragile — detecting premature stability during
brief idle periods between tool calls. Now mirrors opencode's native
SessionPrompt.loop() logic: checks assistant finish reason is terminal
(not tool-calls/unknown) and assistant.id > user.id.
Also switches sync prompt sender from blocking HTTP (promptSync) to
async fire-and-forget (promptAsync) to avoid JSON parse errors in ACP.
- Add improved type definitions for skill resolution
- Enhance executor with better type safety for delegation flows
- Add comprehensive test coverage for delegation tool behavior
- Improve code organization for skill resolver integration
🤖 Generated with assistance of OhMyOpenCode
Revert .default([]) on load_skills schema back to required, restore the runtime error for missing load_skills, and add explicit load_skills=[] to all task() examples in agent prompts that were missing it.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Remove 'prometheus' from PLAN_AGENT_NAMES so isPlanAgent() no longer
matches prometheus. The only remaining connection is model inheritance
via buildPlanDemoteConfig() in plan-model-inheritance.ts.
- Remove 'prometheus' from PLAN_AGENT_NAMES array
- Update self-delegation error message to say 'plan agent' not 'prometheus'
- Update tests: prometheus is no longer treated as a plan agent
- Update task permission: only plan agents get task tool, not prometheus
Add targeted regression tests for the exact reproduction scenario from issue #1295:
- quick category with sisyphusJuniorModel override (the reported scenario)
- user-defined custom category with sisyphusJuniorModel fallback
The underlying fix was already applied in PRs #1470 and #1556. These tests
ensure the fix does not regress.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
YeonGyu-Kim