Source code change:
- src/shared/model-requirements.ts: prepend claude-sonnet-4-6 to metis fallback
chain so Sonnet becomes the default. Opus 4.7 max remains as the immediate
fallback for callers who want extra reasoning.
- src/shared/model-requirements.test.ts: update assertion to expect Sonnet
primary + Opus secondary.
AGENTS.md accuracy fixes (verified against source):
- Agent modes: Sisyphus/Hephaestus are 'primary' (not 'all'); Sisyphus-Junior
is 'subagent' (not 'all'). Confirmed via 'const MODE: AgentMode = ...' in
each agent file. Also clarified Prometheus has no agentSources factory and
is built via buildPrometheusAgentConfig.
- Sisyphus fallback chain: corrected order to kimi-k2.6 → k2p5 → kimi-k2.5
→ gpt-5.5 medium → glm-5 → big-pickle (was missing kimi-k2.5).
- Librarian/Explore: added missing minimax-m2.7 step between -highspeed and
claude-haiku-4-5.
- Metis chain: removed fictitious gemini-3.1-pro entry.
- Sisyphus-Junior chain: spelled out the actual fallback (was 'user-configurable').
- Temperatures: Sisyphus/Hephaestus do not set explicit temperature (model
default); Sisyphus-Junior is 0.1 via SISYPHUS_JUNIOR_DEFAULTS.
- Quick category default: gpt-5.4-mini (not gpt-5.4-mini-fast).
Team-mode corrections:
- Eligibility registry has 3 verdicts: eligible (sisyphus, atlas, sisyphus-junior),
conditional (hephaestus — needs D-36 teammate permission), hard-reject
(oracle, librarian, explore, multimodal-looker, metis, momus, prometheus).
- Schema has 11 fields, not 4: added max_messages_per_run, max_wall_clock_minutes,
max_member_turns, base_dir, message_payload_max_bytes, recipient_unread_max_bytes,
mailbox_poll_interval_ms.
- Hooks: 'team-session-events' is 4 sub-handlers in src/plugin/event.ts
(team-idle-wake-hint, team-lead-orphan-handler, team-member-error-handler,
team-member-status-handler), not a single Continuation-tier hook.
- Tier counts now show base + team-mode: ToolGuard 14/15, Transform 5/7.
- Total: 52 base hooks, 59 with team-mode.
Doc cascade for the Metis change:
- docs/guide/orchestration.md, agent-model-matching.md, installation.md
- docs/reference/configuration.md, features.md
The caller-facing description told orchestrators WHAT `deep` is but
never specified goal cardinality, so they bundled multiple goals into
one call (e.g. "fix X + merge Y + deploy Z"). The deep agent's own
prompt was already configured to refuse such bundles, but only after
they arrived. The rule now lives on the caller side: ONE goal + ONE
deliverable per call; multiple goals must fan out as parallel `deep`
calls.
- DEEP_CATEGORY_PROMPT_APPEND_GPT_5_3_CODEX preserving all DEEP knowledge (atomic task treatment, root cause bias, ambition scaled, completion bar, status sparse) plus codex-specific additions: bias to action, parallel-batch exploration, code implementation discipline, worktree safety, plan closure, pragmatic final-message format\n- resolveDeepCategoryPromptAppend now routes codex first, then 5.5, else legacy (preserves existing 5.5 and 5.4 test invariants)\n- Tests: assert codex no longer falls back to legacy, content tests mirroring the 5.5 pattern (style markers, knowledge preservation, parallel-batch framing, materially different from siblings)
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Agent names like \hephaestus\ cause 'Agent not found' errors because
sanitizeSubagentType() was only called in subagent-resolver.ts but not
in the direct manager.launch() path or background-executor.ts.
- manager.ts: strip leading/trailing backslash/quote chars from input.agent
before validation so \hephaestus\ → hephaestus
- background-executor.ts: call sanitizeSubagentType(args.subagent_type)
instead of passing raw value to manager.launch()
- agent-display-names.ts: reuse sanitizeSubagentType in stripAgentListSortPrefix
- Add unit tests for all three fix points
Fixes: sessions dying with 'Agent not found: \hephaestus\'
Root cause: bun build --target bun inlines top-level
var { spawn } = globalThis.Bun;
for every file that contains 'import { spawn } from "bun"'. On Node/Electron
where globalThis.Bun is undefined, this crashes with
Cannot destructure property 'spawn' of 'globalThis.Bun' as it is undefined.
26 source files had this import; the bundled output had 25 top-level destructures.
Fix:
- Add src/shared/bun-spawn-shim.ts: a thin wrapper that
- delegates to Bun.spawn/spawnSync when globalThis.Bun is present (real Bun)
- falls back to static ESM imports of node:child_process otherwise
- uses static 'import { spawn } from "node:child_process"' so Bun bundler
does NOT emit any globalThis.Bun destructures for this module
- Replace all 26 'from "bun"' spawn/spawnSync imports with relative paths to shim
- Replace 4 direct Bun.spawn() call sites with shim's spawn()
- Remove src/electron-compat.ts and script/prepend-electron-shim.ts (no longer needed)
- Update src/electron-compat.test.ts to assert 0 top-level globalThis.Bun destructures
Verification: grep -c '} = globalThis.Bun;' dist/index.js → 0 (was 25)
All 5921 tests pass (1 pre-existing timeout failure unrelated to this change).
Fixes#3797
Rename BackgroundTask and attempt ID fields to camelCase across background-agent consumers while moving BackgroundManager construction to a single config object.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Hephaestus 5.5 was rewritten as an outcome-first delegation contract in c3fabaaf. The deep category (spawned as sisyphus-junior under gpt-5.5) now receives a matching prose-driven category context lifted from drafts/gpt-5-5/deep.md instead of the legacy gpt-5.4-era threat-frame version.
Selection happens via a new model-aware resolvePromptAppend hook on BuiltinCategoryDefinition. When the resolved category model is gpt-5.5 the new DEEP_CATEGORY_PROMPT_APPEND_GPT_5_5 is used; older models keep the legacy DEEP_CATEGORY_PROMPT_APPEND. User prompt_append remains preserved on top of either base.
The sort shim from the previous commit enforces canonical core ordering at runtime, so ZWSP prefixes are no longer needed. Removing them eliminates the Bun.stringWidth vs terminal-width drift that broke the TUI status bar (#3259).
Drop AGENT_LIST_SORT_PREFIXES and getAgentRuntimeName from agent-display-names; switch all call sites to getAgentDisplayName. getAgentListDisplayName stays as a thin alias for external importers.
Keep stripInvisibleAgentCharacters and the ZWSP regex paths so legacy session state and configs from v3.14.0-v3.16.0 still resolve.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Commit 708891dab fixed most test expectations after the gpt-5.5 model
promotion but missed 13 tests across 6 files that still expected
openai/gpt-5.4 in DEFAULT_CATEGORIES and AGENT_MODEL_REQUIREMENTS.
Updates all remaining stale expectations to openai/gpt-5.5:
- agents/utils.test.ts: atlas/metis resolution, buildAgent category,
override.category expansion (5 tests)
- plugin-handlers/config-handler.test.ts: ultrabrain config resolution
and fallback (2 tests)
- shared/agent-variant.test.ts: sisyphus chain variant and category
fallback (2 tests)
- shared/model-capability-guardrails.test.ts: built-in requirement
model ID assertion (1 test)
- tools/look-at/multimodal-fallback-chain.test.ts: multimodal-looker
hardcoded variant metadata (1 test)
- cli/config-manager/generate-omo-config.test.ts: sisyphus model and
fallback_models expectations (2 tests)
Updates test expectations across agent, cli, shared, plugin, and tools tests
to match gpt-5.5 as the new default for oracle, hephaestus, and deep agents.
Includes snapshot updates for model-fallback tests.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Now that each of these agents ships a native gpt-5.5 prompt variant,
their default OpenAI model is bumped from gpt-5.4 to gpt-5.5. The
gpt-5.4 entries are removed from the same-provider position in each
fallback chain (a single provider doesn't need both version entries -
if gpt-5.5 isn't available there, cross-provider fallback kicks in).
- oracle.fallbackChain: gpt-5.5 high (openai) -> gemini-3.1-pro -> claude -> glm
- hephaestus.fallbackChain: gpt-5.5 medium (openai only, requiresProvider)
- deep category.fallbackChain: gpt-5.5 medium -> claude -> gemini
- deep category.config: openai/gpt-5.5 medium
No changes to sisyphus, sisyphus-junior, ultrabrain, momus, or other
agents that still point at gpt-5.4; those stay on the shared regex-
based routing in the gpt-5-4 prompt family.
The previous description (41 words) told the LLM to write 'complete AST
nodes' but did not explain that regex syntax is the #1 failure mode. It
also shipped a bug: the Python example 'def $FUNC($$$):' had a trailing
colon that the hint system actively flags as wrong.
Extract descriptions into tool-descriptions.ts and rewrite:
- Open with 'This is NOT regex' so the constraint is unmissable
- List the four regex patterns that do not work (|, .*, \\w, [a-z])
with the corrective action for each
- Tell the LLM to switch to grep when the pattern is text-shaped
- Fix the Python example (no trailing colon) and add Go and Rust rows
since the failing reports came from Go codebases
- Shorten the pattern-param description with the same anti-regex list
Also harden the LSP reference for the new test files using the
bun-types triple-slash directive already used elsewhere.
LLMs frequently call ast_grep_search with regex-style patterns like
'func.*build|BuildMode|projectReferences' instead of AST patterns. The
search silently returns zero matches with no useful feedback, so the
model retries with a different regex-shaped pattern and loops.
Extract hint generation into pattern-hints.ts and add detectors for the
four dominant misuse modes:
- regex escapes (\\w, \\d, \\s, \\b)
- character-class ranges ([a-z], [0-9])
- regex wildcards (.* .+) with no meta-vars
- pure alternation (foo|bar|baz with no structural syntax)
Heuristics are designed to be safe on valid AST patterns: bitwise OR
'$A | $B' and Rust closures '|x| x + 1' are not flagged. Language-
specific shape hints (trailing-colon Python, body-less JS/TS/Go/Rust
functions) are preserved and extended to Go and Rust.
YeonGyu-Kim