Add helper that picks primary model with fallback to a secondary model
(e.g., categoryModel → parentContext.model). Enforces consistent
{providerID, modelID} shape.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Addresses review feedback on #3486:
1. claude-thinking-legacy-alias now matches both claude-opus-4-6-thinking
and claude-opus-4-7-thinking, canonicalizing both to claude-opus-4-7.
The previous diff retargeted the regex to 4-7 only, which dropped
backward compatibility for users still pinned to the 4-6 thinking
suffix.
2. MODEL_TO_CATEGORY_MAP keeps the claude-opus-4-6 to unspecified-high
entry alongside the new 4-7 entry. The map is order-independent from
MODEL_VERSION_MAP, so preserving the 4-6 key avoids relying on a
specific migration ordering for legacy agent configs.
3. Fix stale 'Claude Opus 4.6' labels and BDD test comments that the
sed-based bump missed.
Syncs the README translations, CONTRIBUTING, docs/reference,
docs/guide, docs/examples JSONC configs, and the hierarchical
src/**/AGENTS.md files with the model version bump already landed
in the source and migration commits.
MODEL_VERSION_MAP now chains the legacy claude-opus-4-5 entry straight
to claude-opus-4-7 and adds an explicit claude-opus-4-6 to 4-7 bump
path, letting existing user configs upgrade on next load without an
intermediate 4-6 stop.
MODEL_TO_CATEGORY_MAP picks up claude-opus-4-7 as the canonical
unspecified-high model (prior 4-6 entry is covered by the chained
version map above, so legacy hardcoded configs still resolve).
Migration tests rewritten to reflect the chained 4-5 to 4-7 behavior
and the new 4-6 to 4-7 bump path, including the sidecar-union
scenario.
Updates the canonical Anthropic Opus model in every fallback chain
(sisyphus, oracle, prometheus, metis, momus, visual-engineering,
ultrabrain, deep, artistry, unspecified-high), the unspecified-high
category default, the think-mode HIGH_VARIANT_MAP, the Claude Code
alias map, the claude-thinking legacy alias, the context-limit GA
regex, and event.ts fallback strings.
Widens supportsCachedAnthropicLimit to accept both claude-*-4-6 and
claude-*-4-7 so the 1M context cache still applies across the bump.
Regenerates the bundled model-capabilities snapshot from models.dev
and the model-fallback snapshot to match the new source output.
The previous PR #3481 only added a not.toContain check but left the
final toContain assertion still expecting task(session_id=...).
Also updates dynamic-agent-core-sections.ts and verification-reminders.ts
which still had session_id format after the refactor.
Several places still emitted task(session_id=...) after the refactor:
- src/hooks/atlas/verification-reminders.ts: 2 occurrences
- src/agents/dynamic-agent-core-sections.ts: buildNonClaudePlannerSection prompt
Tests updated to match: atlas index.test.ts and dynamic-agent-prompt-builder.test.ts
verification-reminders.ts was updated to use task(task_id=...) but the
'should ignore extracted session ids' test still expected the old
task(session_id=...) format, causing a consistent CI failure on dev.
Fixes the pre-existing test failure unrelated to any code changes.
GitHub Copilot proxies Anthropic's API but does not support
output_config.effort: "max" (same constraint as Anthropic OAuth).
Previously the anthropic-effort hook early-returned for github-copilot
provider, skipping all effort clamping. Users on github-copilot/claude-opus-4.6
with variant=max got HTTP 400 'invalid_reasoning_effort'.
Fix: Remove the github-copilot early return. Treat github-copilot as a
constrained provider (alongside Anthropic OAuth), clamping max→high.
Rename isAnthropicOAuth→isConstrainedProvider to reflect the broader scope.
Fixes the remaining user report from #3429.
Address review feedback: add updateBackgroundTaskMarker() calls to
three additional terminal paths in BackgroundManager that were missing
marker cleanup, which could leave stale "active" markers and prevent
CLI run mode from exiting:
- processKey() startTask error handler
- handleEvent() session error (non-retryable)
- pruneStaleTasksAndNotifications() stale task cleanup
Closes#3452
When using `opencode run`, the process exits prematurely if the main
agent dispatches background subtasks. The CLI completion checker relies
on `session.children()` + `session.status()` APIs which cannot see
tasks in "pending" state (no session created yet) or tasks whose
sessions are momentarily idle between operations.
This fix bridges BackgroundManager state to the CLI completion checker
using the existing run-continuation-state marker system:
- Add "background-task" continuation marker source
- BackgroundManager writes/clears markers on task lifecycle events
(launch, cancel, complete, crash)
- CLI completion checker blocks exit when marker is active
- Fix todo-continuation-enforcer to also check "pending" task status
Closes#3452
When replace_plan is true (default), the native plan agent was demoted to
subagent but remained visible in the agent picker. This caused Sisyphus to
route planning to the native plan agent instead of Prometheus.
Add hidden: true to buildPlanDemoteConfig(), consistent with how the build
agent is hidden when default_builder_enabled is false.
The opencode-config-agents-reader.test.ts was using mock.module() which
permanently replaced the module in bun's module cache, causing state
pollution in downstream tests (plugin-detection, write-omo-config,
config-loader). Replaced with spyOn() pattern that properly restores
in afterEach.
Blocking fixes:
- B1: Return empty restrictions for unknown/custom agents instead of
EXPLORATION_AGENT_DENYLIST, allowing custom agents full tool access
- B2: Use Object.create(null) consistently across all 5 agent-loading
result objects to prevent prototype pollution
- B3: Add code comment documenting custom agent bash access trust model
- B4: Mock getOpenCodeConfigDir in opencode-config-agents-reader tests
to prevent global config dir leakage
Non-blocking fixes:
- N1: Use resolveAgentDefinitionPaths with project boundary enforcement
in opencode-config-agents-reader for path containment
- N2: Add session-scoped 30s TTL cache to resolveCallableAgents to
avoid redundant SDK IPC calls per tool invocation
- N3: Extract shared parseToolsConfig into src/shared/parse-tools-config.ts
replacing 4 duplicated local implementations
- N4: Add .min(1) to AgentDefinitionPathSchema rejecting empty paths
- N5: Add resolve-agent-definition-paths.test.ts covering tilde expansion,
relative paths, boundary enforcement, and null containmentDir
- N6: Validate agent mode against allowed values instead of bare type
assertion in opencode-config-agents-reader
Addresses cubic-dev-ai P1 review: Object.hasOwn() alone doesn't prevent
a crafted '__proto__' agent name from mutating the result object's
prototype chain. Using Object.create(null) eliminates inherited properties
entirely, making both the hasOwn checks and property assignments safe.
Addresses cubic-dev-ai review: using 'in' on plain objects can skip valid
agent names that match inherited properties (toString, constructor, etc.).
Switched both occurrences in opencode-config-agents-reader.ts to
Object.hasOwn() for safe own-property checks.
- Case-insensitive .md extension stripping for agent name extraction
- Resolve project agent_definitions paths relative to config dir (.opencode/)
- Use getOpenCodeConfigDir() to respect OPENCODE_CONFIG_DIR/XDG_CONFIG_HOME
- First-write-wins semantics for both inline and definition-file agents
so project-level agents always take precedence over global-level
Dev added 4 tests (#2852, model variant, category-derived overrides) that
referenced the old mockCtx constant. Our branch replaced it with a
createMockCtx() factory. Replace all 4 references.
- Modified agent-config-handler.ts to load and integrate both new agent sources
- Added loadAgentDefinitions() and readOpencodeConfigAgents() calls in loading phase
- Integrated both sources into agent precedence chains (both Sisyphus-enabled and disabled paths)
- Added detailed logging for new agent sources
- Added filtering logic to respect disabled_agents configuration
- Extended agent-config-handler.test.ts with 7 new integration tests
- All tests passing (18/18 integration, 65/65 loader suite)
Wave 3 of agent definitions enhancement complete.
Wave 1 of agent definitions enhancement (PR #2299):
Schema & Configuration:
- Add agent_definitions field to oh-my-opencode config schema
- Support list of file paths to .md or .json agent definition files
- Add to PARTIAL_STRING_ARRAY_KEYS for Set-union merge semantics
- Implement eager path resolution in loadPluginConfig() before merging
Path Resolution:
- Create resolve-agent-definition-paths.ts helper
- User-level paths resolve from ~/.config/opencode/ (no containment)
- Project-level paths resolve from project root (with containment check)
- Homedir expansion, absolute/relative path handling
JSON Agent Loader:
- Create parseJsonAgentFile() for .json/.jsonc agent definitions
- Validate required fields (name, prompt)
- Support tools as string (comma-separated) or array
- Map model via mapClaudeModelToOpenCode()
- Comprehensive test suite (7 test cases, all passing)
Type Extensions:
- Extend AgentScope: add 'definition-file' and 'opencode-config'
- Add AgentJsonDefinition interface for JSON agent schema
All automated checks passing:
- lsp_diagnostics clean on all changed files
- json-agent-loader.test.ts: 7/7 passing
- Full typecheck: zero new errors
- QA evidence saved to .sisyphus/evidence/
- #3354: Coerce data.name to String in loadSkillFromPath/loadSkillFromPathAsync
to prevent crash when YAML parses numeric skill names (e.g., name: 12306)
- #3416: Add required run_in_background parameter to all task() examples in
ultrawork prompts (default, gpt, gemini, planner) to match tool schema
- #3379/#3417/#3418/#3337/#3335: Strip ZWSP (U+200B) before agent name
comparisons in agent-tool-restrictions, sync-prompt-sender, tool-execute-after,
tool-execute-before, oracle-verification-detector, call-omo-agent,
recovery-prompt-config, and agent-variant to prevent ZWSP-prefixed display
names from breaking exact-match lookups
- shell-env: detect Git Bash via MSYSTEM env var when SHELL is unset (#3366)
On some Git Bash installations SHELL is not set but MSYSTEM (MINGW64/MSYS)
is always present. Check MSYSTEM before PSModulePath to avoid emitting
PowerShell syntax in bash shells.
- session-state: resolve legacy agent names in resolveRegisteredAgentName (#3272)
Historical sessions stored agent names like 'Sisyphus (Ultraworker)' which
don't match the current registered format. Fall back to getAgentConfigKey
for legacy/parenthesized name resolution before returning the raw name.
- config-migration: skip backup when file content is unchanged (#3222)
Compare serialized config with existing file content before creating a
timestamped .bak file. Only create backup when the on-disk content
actually differs from the migrated content.
The update checker was using strict string comparison (===) to compare
current and latest versions. This caused false-positive update notifications
when versions were semantically equal but had different string representations
(e.g., with/without 'v' prefix, different formatting).
Changed to use compareVersions() which properly parses and compares
semver versions, handling 'v' prefixes and other variations correctly.
Fixes: incorrect 'v3.17.2 available' notifications when already on latest version
In OpenCode web multi-workspace mode, skill_mcp spawned stdio child
processes inherited process.cwd() instead of the session's workspace
directory. Pass toolContext.directory through SkillMcpClientInfo to
StdioClientTransport's cwd parameter.
In OpenCode plugin sandbox, existsSync fails across different hook
contexts (config vs chat.message) because each runs in an isolated
virtual filesystem. Add writtenInCurrentProcess flags to track cache
writes at the process level, eliminating spurious Model Cache Not
Found toast warnings.
Closes#3412
YeonGyu-Kim