The placeholder ANTHROPICS_API_KEY (with trailing S) silently failed:
the auth layer reads ANTHROPIC_API_KEY, so anyone copying .env.example
to .env and pasting their key would see gnoma never pick it up, with
no clear error.
Also surfaces vars that already work but weren't templated:
GOOGLE_API_KEY (alternative to GEMINI_API_KEY), GNOMA_PROVIDER and
GNOMA_MODEL (config overrides), and the two subprocess sandbox bypass
footguns (GNOMA_AGY_BYPASS_PERMISSIONS, GNOMA_CODEX_BYPASS_SANDBOX),
left commented out so they don't accidentally turn on.
provider/openai:
- Fix doubled tool call args (argsComplete flag): Ollama sends complete
args in the first streaming chunk then repeats them as delta, causing
doubled JSON and 400 errors in elfs
- Handle fs: prefix (gemma4 uses fs:grep instead of fs.grep)
- Add Reasoning field support for Ollama thinking output
cmd/gnoma:
- Early TTY detection so logger is created with correct destination
before any component gets a reference to it (fixes slog WARN bleed
into TUI textarea)
permission:
- Exempt spawn_elfs and agent tools from safety scanner: elf prompt
text may legitimately mention .env/.ssh/credentials patterns and
should not be blocked
tui/app:
- /init retry chain: no-tool-calls → spawn_elfs nudge → write nudge
(ask for plain text output) → TUI fallback write from streamBuf
- looksLikeAgentsMD + extractMarkdownDoc: validate and clean fallback
content before writing (reject refusals, strip narrative preambles)
- Collapse thinking output to 3 lines; ctrl+o to expand (live stream
and committed messages)
- Stream-level filter for model pseudo-tool-call blocks: suppresses
<<tool_code>>...</tool_code>> and <<function_call>>...<tool_call|>
from entering streamBuf across chunk boundaries
- sanitizeAssistantText regex covers both block formats
- Reset streamFilterClose at every turn start
vikingowl