Match opencode core 'task' tool behavior for metadata consistency:
1. Model fallback: When categoryModel/task.model/resumeModel is undefined,
fall back to parentContext.model so subagent metadata always includes
model info. Thread parentContext into executeSyncContinuation for parity.
2. Task ID consistency: unstable-agent-task was missing taskId and
backgroundTaskId in metadata. background_output used inconsistent
snake_case 'task_id' vs camelCase 'taskId' elsewhere. Standardize on
camelCase: taskId = sessionID (resume id), backgroundTaskId = bg task id.
Update text output blocks to use buildTaskMetadataBlock helper.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
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>
Sed-based bulk replace only touched hyphenated IDs (claude-opus-4-6)
but the tutorial prose and comparison tables used the dotted human
form 'Claude Opus 4.6' / 'Opus 4.6'. Sync those occurrences to 4.7
in:
- docs/guide/installation.md (model families table + Sisyphus tutorial)
- docs/guide/agent-model-matching.md (recommended-model table)
- docs/guide/overview.md (three references to Opus default)
Without this commit, users following the installation guide would be
told Sisyphus 'strongly recommends Opus 4.6' while the plugin itself
already routes to Opus 4.7.
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
After the package was renamed from oh-my-opencode to oh-my-openagent,
the bin entry only had 'oh-my-opencode'. Users running:
npm install -g oh-my-openagent
could not invoke 'oh-my-openagent' from the command line.
Add 'oh-my-openagent' as a second bin entry pointing to the same
bin/oh-my-opencode.js entry point. Both aliases now work.
Fixes#3482
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.
When oh-my-openagent is loaded by opencode 1.4.6+, both sides ship zod v4
but as two separate instances. zod v4 uses instance-identity checks
(schema._zod.def) that fail across module boundaries, causing:
TypeError: undefined is not an object (evaluating 'n._zod.def')
Fix:
- Add --external zod to the plugin bundle build command so the plugin
resolves zod from opencode's runtime instead of embedding its own copy
- Move zod from dependencies to peerDependencies (^4.0.0) so package
managers know to deduplicate on a single shared instance
- Keep zod in devDependencies so local build/test continues to work
The plugin dist/index.js no longer contains node_modules/zod/v4 internals.
Fixes#3479
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.
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.
YeonGyu-Kim