Commit Graph

9 Commits

Author SHA1 Message Date
YeonGyu-Kim 38b1433ff5 fix(continuation): mark resumes synthetic 2026-05-13 13:09:26 +09:00
YeonGyu-Kim 06b825dd74 fix(start-work): reuse registered opencode agent names 2026-04-08 16:18:26 +09:00
YeonGyu-Kim b4baec75d3 Merge pull request #3173 from code-yeongyu/fix/issue-3081
fix(prompt): propagate variant field in all promptAsync continuation paths (#3081)
2026-04-07 15:13:58 +09:00
YeonGyu-Kim aa528e42c0 fix: propagate variant field in all promptAsync continuation paths (#3081)
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.
2026-04-07 15:10:38 +09:00
YeonGyu-Kim f8c626086e fix(agent-names): use HTTP-header-safe display names and config keys for API calls (#3138)
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
2026-04-07 10:08:04 +09:00
YeonGyu-Kim de6c74bfb4 fix(todo-continuation): normalize agent name to config key before promptAsync (#3149)
The todo-continuation-enforcer was passing raw agent names (which could be
display names like 'Sisyphus (Ultraworker)') to promptAsync. These names
contain spaces/parentheses that violate HTTP header specs, causing the
x-opencode-agent-name header validation to fail with 'unknown error' toast.

Added normalizeAgentForPromptKey() that converts display names to config keys
(e.g., 'Sisyphus (Ultraworker)' -> 'sisyphus') before API calls.

TDD: Added regression test that verifies config key is sent to promptAsync.
2026-04-06 11:44:52 +09:00
MoerAI 2b6b08345a fix(todo-continuation-enforcer): add plan agent to DEFAULT_SKIP_AGENTS to prevent infinite loop
The todo-continuation-enforcer injects continuation prompts when
sessions go idle with pending todos. When Plan Mode agents (which are
read-only) create todo items, the continuation prompt contradicts
Plan Mode's STRICTLY FORBIDDEN directive, causing an infinite loop
where the agent acknowledges the conflict then goes idle, triggering
another injection.

Adding 'plan' to DEFAULT_SKIP_AGENTS prevents continuation injection
into Plan Mode sessions, matching the same exclusion pattern already
used for prometheus and compaction agents.

Fixes #2526
2026-03-16 11:07:28 +09:00
Maxim Harizanov 850fb0378e fix(copilot): mark internal hook injections as agent-initiated
Apply the internal initiator marker to automated continuation, recovery, babysitter, stop-hook, and hook-message injections so Copilot attribution consistently sets x-initiator=agent for system-generated prompts.
2026-02-19 13:17:02 +02:00
YeonGyu-Kim 096db59399 fix(run): inherit main-session tool permissions for continuation prompts 2026-02-18 21:10:21 +09:00