Structured plans (with ## TODOs section) use strict numbered-label
parsing. Simple plans (without sections) fall back to regex checkbox
counting. This fixes 9 test failures from the #3066 merge.
prompt-builder.ts now includes project-level skills from
.opencode/skills/ when building delegated session prompts.
5007 tests pass, tsc clean.
Closes#2687
agent-config-handler.ts now registers custom agents from
~/.config/opencode/agents/ into the task subagent registry.
5005 tests pass, tsc clean.
Closes#2689
handler.ts now catches ContextLengthError/prompt-too-long errors and
stops continuation instead of retrying with an even larger context.
91 tests pass, tsc clean.
Closes#2462
model-selection.ts now separates model selection from variant/reasoning
tier, so agent model overrides don't lock the variant.
34 tests pass, 5009 total, tsc clean.
Closes#3163
Added await for session ready state before sending prompt in
background-agent/manager.ts. Also improved image resizer error handling.
132 tests pass, tsc clean.
Closes#2932
Built-in agents (Sisyphus, Hephaestus, Atlas) now include explicit
identity section in their system prompts, matching custom agent behavior.
12 agent identity tests pass, 266 total pass, tsc clean.
Closes#2964
Added 'trusted' option to expandEnvVars. Skill MCPs are user-controlled
and now bypass the security allowlist. 3 files changed.
TDD verified. tsc clean.
Closes#3168
Changed PACKAGE_NAME from 'oh-my-openagent' to 'oh-my-opencode' in
auto-update-checker/constants.ts to match package.json. This fixes
getCachedVersion() returning null, causing 'unknown' in version toast.
TDD: red-green confirmed. 39 tests pass, tsc clean.
Closes#3129
When Read tool is disabled (attachment mode), the agent prompt now
instructs to analyze the attached content directly instead of
trying to use Read. 3 new tests, 55 total pass.
Closes#3033
All 5 continuation paths now send variant as top-level body field:
- boulder-continuation-injector.ts
- ralph-loop/continuation-prompt-injector.ts
- todo-continuation-enforcer/continuation-injection.ts
- unstable-agent-babysitter-hook.ts
- session-recovery/resume.ts
Plus type/helper updates in atlas, todo-continuation-enforcer,
unstable-agent-babysitter, and session-recovery.
TDD: 18 regression tests added, all pass. tsc clean.
Windows editors often save UTF-8 files with a BOM (Byte Order Mark: \uFEFF).
When this is present, jsonc-parser reports InvalidSymbol at offset 0 because
the BOM is not valid JSON/JSONC syntax.
This commit strips the BOM before parsing, fixing issues #3164 where Windows
users report their opencode.jsonc file fails to parse even though it appears
to start with a valid '{' character.
Fixes: #3164
Co-authored-by: Jobdori <agent@yeongyu.kim>
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
Display names with parentheses like 'Atlas (Plan Executor)' cause HTTP
header validation errors in x-opencode-agent-name. This was blocking
Atlas/Prometheus from working via /start-work and auto-retry.
Changes:
- Display names: parens -> dashes ('Atlas - Plan Executor')
- Hooks (start-work, no-hephaestus-non-gpt, no-sisyphus-gpt): use
config keys ('atlas', 'sisyphus', 'hephaestus') for agent API fields
- auto-retry: use config key instead of display name for promptAsync
- agent-override-protection: handle dash-suffix normalization
- Updated all test expectations to match new format
Closes#3138
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)
/start-work is the "execute this plan with atlas" command.
Previously, if the user's current session agent was sisyphus (or any
non-prometheus/non-atlas agent), the hook would keep that agent instead
of switching to atlas. This caused sisyphus to execute the plan.
Fix: unconditionally select atlas (when registered) or sisyphus (fallback).
The current session agent is irrelevant to /start-work's intent.
Adds regression test: running /start-work from a sisyphus session must
always hand off to atlas when atlas is available.
- install.test.ts: save and restore globalThis.fetch in beforeEach/afterEach
to prevent leaking a mock fetch (without .preconnect) into subsequent test files
- provider.test.ts: guard against originalFetch missing .preconnect when captured
from a leaked mock (defensive null-safe binding)
- discovery.test.ts: add writable:true to all Object.defineProperty fetch assignments
so downstream plain assignments (globalThis.fetch = ...) are not silently ignored
Root cause: install.test.ts set globalThis.fetch = mock(...) inside test bodies
without restoring it, leaving a mock fetch (no .preconnect method) that caused
provider.test.ts refresh tests to throw TypeError at the fetchMock construction
Prevent ZWSP sort prefixes from leaking into stored agent names, config
key lookups, and override-protection normalization. Ensures prefixed
list-display names resolve correctly throughout the pipeline.
🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode) assistance
Populate AGENT_LIST_SORT_PREFIXES for sisyphus/hephaestus/prometheus/atlas
so the TUI agent list renders in canonical order. Update dependent tests
to use getAgentListDisplayName() instead of hardcoded display strings.
🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode) assistance
- provider.test.ts: reset discovery cache before/after refresh tests to prevent
cross-test contamination via module-level discoveryCache singleton
- completion-promise-session-negative.test.ts: update negative test case to use
non-oracle agent (hephaestus) since oracle tool_result VERIFIED detection was
intentionally added in 56f2a9df
Bug fixes:
1. OAuth token refresh (#3149): buildHttpRequestInit() now attempts silent refresh
via refresh_token before triggering full browser re-auth. Added refresh() method
to McpOAuthProvider. Includes test isolation fix for discovery mock.
2. Quota error STOP (#3126): Added STOP_MESSAGE_PATTERNS in model-error-classifier
that take precedence over RETRYABLE_MESSAGE_PATTERNS. Message-only quota errors
now non-retryable. Runtime-fallback: quota_exceeded with 'retrying in' signal
still triggers fallback (provider-managed auto-retry). Restored removed patterns.
3. Compaction loop (#3127): MAX_RECOVERY_ATTEMPTS=3 cap + additional suppression
guard from opencode session in degradation monitor.
Also: refactored extractAutoRetrySignal to auto-retry-signal.ts, new regression
tests for quota classifier and compaction degradation monitor.
Extract hephaestus into agentConfig before prometheus so the config
handler naturally assembles agents in the canonical order instead of
relying solely on reorderAgentsByPriority to fix the wrong intermediate
order. Also fix test data that had atlas/prometheus swapped and add
missing hephaestus to agent-config-integration test lists.
Tool return values contained CTAs ("Use background_output to check") that
caused models to immediately poll instead of waiting for <system-reminder>
notifications. Unified all 5 tool return messages with explicit "Do NOT call
background_output now" guard, added pre-notification warning to BackgroundOutput
tool description, and strengthened Background Result Collection sections across
all 3 Sisyphus prompt variants (default, gpt-5-4, main) with BLOCKING
anti-pattern enforcement.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Add MAX_RECOVERY_ATTEMPTS (3) guard to post-compaction degradation recovery.
On models like Kimi/Minimax that repeatedly generate no-text responses,
the recovery loop would trigger indefinitely as each compaction reset the
recovery counter via onSessionCompacted.
The recovery count now persists across compaction cycles per session and
is only reset on session deletion (clear()), not on every compaction.
YeonGyu-Kim