8 Commits

Author	SHA1	Message	Date
infra-runtime-be	66e3b7edb3	feat(claude-code): route Kimi K2.6 to api.kimi.com/coding per official spec ... Kimi (Kimi-For-Coding / K2.6) was structurally unreachable from the claude-code runtime: the `kimi-` model prefix matched the `moonshot` provider, which set ANTHROPIC_BASE_URL=https://api.moonshot.ai/anthropic and projected KIMI_API_KEY -> ANTHROPIC_AUTH_TOKEN. Both are wrong per kimi.com's official Claude Code integration doc (kimi.com/code/docs/en/third-party-tools/other-coding-agents.html): - the sk-kimi-* key (KIMI_API_KEY in SSOT) authenticates ONLY against https://api.kimi.com/coding/ — the legacy api.moonshot.ai/anthropic surface 401s it (invalid_authentication_error); - that gateway authenticates with the x-api-key header, which the Anthropic SDK / claude CLI emits from ANTHROPIC_API_KEY, NOT the Bearer ANTHROPIC_AUTH_TOKEN. So a Kimi pick on claude-code 401'd every LLM call. Fix (config + minimal adapter, scoped to this template — adapter.py and config.yaml are template-local, COPY'd in the Dockerfile; zero blast radius on other runtimes): - config.yaml: repoint the existing kimi- provider entry (renamed moonshot -> kimi-coding) to base_url https://api.kimi.com/coding/ (trailing slash, per the doc) and add a new optional per-provider field `auth_token_env: ANTHROPIC_API_KEY` so the boot-time vendor-key projection writes KIMI_API_KEY into ANTHROPIC_API_KEY (x-api-key) instead of the default ANTHROPIC_AUTH_TOKEN (Bearer). Renaming the existing entry (vs adding a parallel one) keeps the kimi- model-prefix matcher working with the least change; still 7 providers total. - config.yaml: add a selectable "Kimi K2.6" model catalog entry (id kimi-for-coding — the gateway's own served-model name, mirroring the proven OpenClaw kimi-for-coding route; the gateway routes to K2.6 regardless of the wire model id). kimi-k2.5 / kimi-k2 retained as aliases hitting the same gateway for back-compat. - adapter.py: _normalize_provider parses the optional `auth_token_env` (default ANTHROPIC_AUTH_TOKEN — preserves MiniMax/GLM/DeepSeek behavior bit-for-bit); _project_vendor_auth projects into that per-provider target and is idempotent on it (explicit operator value still wins). Wire-verified before commit: POST https://api.kimi.com/coding/v1/messages with x-api-key=<SSOT KIMI_API_KEY> + anthropic-version + claude-cli UA -> HTTP 200, model=kimi-for-coding, real completion. The shipped routing produces exactly this wire shape. Tests: added 4 tests (Kimi -> ANTHROPIC_API_KEY projection, operator override idempotency, _normalize_provider auth_token_env parse, prevalidate routing matrix incl. kimi-for-coding); updated the moonshot-named fixtures/assertions to the new kimi-coding contract. Full suite 85 passed.	2026-05-16 04:56:49 -07:00
dev-lead	291f356dab	fix(adapter,tests): isolate _load_providers tests from multi-path lookup ... The 5 _load_providers tests were single-path-only: they wrote a config.yaml to tmp_path and called _load_providers(str(tmp_path)), expecting the lookup to read tmp_path/config.yaml. After the multi-path fix in #7, _load_providers also checks: 1. _CANONICAL_ADAPTER_DIR/config.yaml (= /opt/adapter/config.yaml) 2. _TEMPLATE_DIR/config.yaml (= dirname(__file__)/config.yaml) 3. ${config_path}/config.yaml (the test's tmp_path) Path 2 finds the repo's bundled config.yaml on the test runner's disk before path 3 — the tests then see the bundled providers list instead of the test's expected behavior. Two surface changes: 1. adapter.py — extract `os.path.dirname(os.path.abspath(__file__))` into a module-level `_TEMPLATE_DIR` constant, mirroring `_CANONICAL_ADAPTER_DIR`. Production behavior identical (resolved once at import). Tests can monkeypatch the module attribute to redirect the path-2 lookup. 2. tests/test_adapter_prevalidate.py — 5 _load_providers tests monkeypatch `_CANONICAL_ADAPTER_DIR` and `_TEMPLATE_DIR` to a non-existent tmp subdir, isolating the test to the workspace config_path branch they always meant to test. The 6th _load_providers test (`test_load_providers_parses_yaml_and_normalizes`) already passed because path 2 returns 7 providers and that's what that test expects — left unchanged. Verification: pytest tests/ 65/65 PASS pytest tests/test_adapter_prevalidate.py -k load_providers 6/6 PASS Closes molecule-core#129 follow-up — the unit tests were the last red on the template repo's CI. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-08 13:27:56 -07:00
Hongming Wang	a78626ced4	fix(adapter): keep setup() routing — strip prefix only at CLI invocation ... Live-test revealed a regression in PR #24's setup() strip: the wheel- default `anthropic:claude-opus-4-7` paired with an OAuth workspace (CLAUDE_CODE_OAUTH_TOKEN set, no ANTHROPIC_API_KEY) is the realistic production shape. Stripping in setup() routes those users into the `anthropic-api` provider entry, after which the CLI hangs at `initialize` because no API key env is set. Caught on workspace dd40faf8 on 2026-05-01 — banner went `provider=anthropic-api` and A2A wedged on Control request timeout. Pre-fix routing (let prefixed strings fall through to providers[0] = anthropic-oauth) is actually correct for this combo. The strip is only needed at the CLI invocation site (create_executor) where claude's `--model` arg must be a bare id. Tests: replace `test_setup_strip_routes_prefixed_anthropic_to_anthropic_api` with `test_setup_keeps_prefix_routing_oauth_for_anthropic_prefix`, which pins the inverse — prefixed model + OAuth env stays on oauth and emits no API-key warning. The 5 unit cases on `_strip_provider_prefix` plus the `create_executor` strip pins remain unchanged. 36/36 pass. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-01 16:46:54 -07:00
Hongming Wang	6ba4cc6a01	fix(adapter): strip LangChain-style provider prefix before CLI invocation ... The molecule-runtime wheel's config.py defaults model to `anthropic:claude-opus-4-7` so langchain/crewai consumers get a uniform provider:model string out of the box. The claude CLI's --model arg expects the bare model id and silently exits 1 (no stderr) on prefixed strings — root cause of the 2026-05-01 "Agent error (Exception)" mid-A2A bug. Diagnosed via strace on a live workspace: the CLI received `--model anthropic:claude-opus-4-7` and exit_group(1)'d before any non-fatal output. Add `_strip_provider_prefix` and call it in both setup() (so _resolve_provider routes anthropic:claude-X correctly to anthropic-api instead of falling back to oauth) and create_executor() (so the bare id reaches the CLI). Only known-Claude prefixes are stripped; unknown ones (openai:, bedrock:) pass through so the CLI fails loudly instead of being silently mangled. Coverage: 8 new tests — unit tests for the helper across all branches, end-to-end `create_executor` strip on dict + dataclass shapes, and a caplog-based setup() test that pins provider=anthropic-api routing after the strip (the silent-fallback failure mode this fix eliminates). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-01 16:06:53 -07:00
Hongming Wang	2b9b4306eb	fix(adapter): per-entry isolation in _load_providers + tighten _normalize_provider ... Two correctness issues spotted in self-review of c6f4912: 1. String-as-prefix typo split into character tuple. ``model_prefixes: mimo-`` (operator forgot brackets) used to iterate over characters → ``('m','i','m','o','-')``, silently routing every model id starting with 'm', 'i', or '-' through the entry. Now: non-list values coerce to empty tuple (entry survives but matches nothing — operator notices in boot banner, not via misrouted requests). 2. Single bad provider entry nuked the whole registry. _load_providers built the registry via a generator inside tuple(...). One AttributeError mid-comprehension (e.g. ``[mimo-, 123]`` — int's missing .lower()) propagated out, broad except caught it, registry silently fell back to _BUILTIN_PROVIDERS (oauth + anthropic-api only). Every third-party model would then route to anthropic-oauth — exactly the silent-fallback failure mode this PR was meant to eliminate. Now: per-entry try/except drops the bad entry with a warning, rest survives. Also: entries without a string ``name`` field are now dropped with a warning instead of silently using the placeholder ``<unnamed>`` — operator typos surface in boot logs. Tests: 28 passing (3 new regression tests covering both issues plus the no-name path). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-04-30 23:58:24 -07:00
Hongming Wang	c6f4912d09	feat(adapter): data-driven provider registry in config.yaml ... Move the model→endpoint→auth-env mapping out of hardcoded constants in adapter.py + entrypoint.sh into a single `providers:` list at the top of config.yaml. The adapter loads it at boot via _load_providers; canvas Config tab will read the same YAML for its Provider dropdown so UI and adapter never disagree on what's available. Adding a new provider becomes a one-line YAML edit — no Python or shell changes. Includes 5 third-party providers ready out of the box (Anthropic-compat endpoints, Bearer-style ANTHROPIC_AUTH_TOKEN OR ANTHROPIC_API_KEY auth): xiaomi-mimo https://api.xiaomimimo.com/anthropic minimax https://api.minimax.io/anthropic zai https://api.z.ai/api/anthropic (NEW) moonshot https://api.moonshot.ai/anthropic (NEW) deepseek https://api.deepseek.com/anthropic (NEW) Plus 7 new model entries in runtime_config.models (mimo-v2.5, MiniMax-M2, MiniMax-M2.7, GLM-4.6, GLM-4.5, kimi-k2.5, kimi-k2, deepseek-v4-pro, deepseek-v4-flash) so they show up in the Canvas Config dropdown. Operator override unchanged: ANTHROPIC_BASE_URL set as a workspace secret still wins over the registry default — the escape hatch for regional endpoints (Xiaomi token-plan-sgp, MiniMax api.minimaxi.com). entrypoint.sh: drops the `mimo-*` case mapping (adapter handles routing now). _BUILTIN_PROVIDERS retained as malformed-YAML fallback so a bare-bones workspace still boots with oauth + anthropic-api defaults. Tests: 25 passing. New coverage: - YAML parses + normalizes to expected shape - Malformed YAML falls back to builtins (warning, not raise) - Each new provider routes its model id to the right base_url - ANTHROPIC_AUTH_TOKEN alone satisfies third-party auth check - Operator-set ANTHROPIC_BASE_URL overrides registry default - Case-insensitive prefix match (MiniMax-M2 / minimax-m2.7 / GLM-4.6) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-04-30 23:29:40 -07:00
Hongming Wang	c646b8cebe	feat(adapter): raise on third-party model without ANTHROPIC_BASE_URL ... Aligns setup()'s third-party-model-without-URL handling with create_executor()'s pre-validate (#19) — both unrecoverable misconfigurations now raise ValueError at boot instead of one warning and one raising. Why: a third-party (mimo-*) model selected without ANTHROPIC_BASE_URL sends every LLM request to api.anthropic.com with a non-Anthropic key, 401-ing every prompt. Workspace boots, looks "online" via heartbeat, but is structurally broken on the user-facing path. The previous warning-only path produced the same end-user symptom as the 2026-04-30 incident (workspace looks alive, every interaction fails) just via a different misconfig shape. Symmetry: create_executor raises when ANTHROPIC_BASE_URL is set to a non-Anthropic host but no model is picked. setup() now raises when a third-party model is picked but no URL is set. Together they catch both halves of the misconfig surface at boot, before the workspace enters "online" status. Adds 4 setup() tests: - raises on third-party + no URL - passes on third-party + URL - passes on OAuth alias (sonnet) + no URL - passes on Anthropic API id (claude-*) + no URL Stubs molecule_runtime.plugins.load_plugins as a no-op so the pass-path tests run cleanly without the runtime installed. Test count: 11 (7 create_executor + 4 setup). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-04-30 22:50:25 -07:00
Hongming Wang	0d95b5098a	feat(adapter): pre-validate ANTHROPIC_BASE_URL + missing model combo ... The 2026-04-30 staging incident traced back to workspaces booting with ANTHROPIC_BASE_URL pointing at a non-Anthropic shim (MiniMax / OpenAI gateway) but no explicit model configured. The adapter silently fell back to "sonnet" — an Anthropic-native alias the upstream didn't recognize — and the SDK --print probe hung 30s before timing out. Platform's phantom-busy sweep then nuked the workspace at 10min, producing "every workspace dead" with the root cause buried in a 30s subprocess hang. Pre-validate the combo at adapter boot: when ANTHROPIC_BASE_URL host is non-Anthropic AND no explicit model is set, raise ValueError with an actionable message pointing to MODEL_PROVIDER / runtime_config.model. Also log the resolved model + base_url_host every boot so future failures explain themselves in the workspace logs without digging into the SDK subprocess. Tests live under tests/ with their own pytest.ini that anchors rootdir there — keeps pytest from importing the package __init__.py (which does the runtime-discovery relative import that requires molecule_runtime installed). 7 tests cover: misconfig raises with the right message, Anthropic-native passes, no-base-url passes, custom-url + explicit model passes, dataclass + dict shapes, unparseable URL no-crash. CI runs them on every push/PR. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-04-30 22:35:49 -07:00