Commit Graph

53 Commits

Author SHA1 Message Date
Yichen Jiang
0a263941ef Merge branch 'worktree-llm-dynamic-config' into worktree-llm-web-config
# Conflicts:
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.i18n.yaml
#	docs/event-producer-consumer.md
#	examples/headless-agent/tests/headless.snapshot.ts
#	examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl
#	packages/llm/llm-deepseek/README.i18n.yaml
#	packages/llm/llm-deepseek/src/index.ts
#	packages/llm/llm-pi-ai/README.i18n.yaml
#	packages/llm/llm-pi-ai/src/index.ts
#	packages/llm/llm/README.i18n.yaml
#	packages/llm/llm/src/index.ts
2026-07-30 17:22:44 +08:00
Yichen Jiang
9626c15c6b test(sandbox): carry the resolved read denials through consumer policy assertions
The policy home's resolve() now stamps readDenyPaths, so every consumer
that pins the resolved shape (bash-sandbox hand-off, tool-fs stamps)
carries it, and three uncovered branches gained real tests: landlock
reporting partial enforcement for a denial it cannot express, the
policy's default under programmatic construction, and both ambient
credential paths in llm-deepseek without a mounted seam.
2026-07-30 16:11:21 +08:00
Yichen Jiang
54f95d7669 fix(llm): atomic route replacement, whole-snapshot requests, and loud credential misses
Four review findings across the seam and both adapters.

registerAdapter now returns a handle carrying replace(providers): the
candidate route set is validated in full before anything moves, so a
route another adapter owns leaves the previous registration intact, and
the swap itself is one synchronous section with no observable gap. pi-ai
uses it instead of dispose-then-register — the old shape dropped every
route when the new set conflicted, and its facts cache could then equal
the registry's, so reverting to a working configuration never re-applied.
Its registration facts are also sorted by provider, so a settings
document that merely reorders keys no longer triggers a swap.

DeepSeek's per-request snapshot now carries the credential facts, and
resolveApiKey receives it instead of re-reading the raw config: a
settings generation the resolver rejects can no longer contribute its
literal key to a request the previous generation's endpoint serves.

pi-ai only defers to the SDK's provider-native discovery when a profile
names no credential at all; a configured apiKeyEnv that misses now fails
with MISSING_CREDENTIAL naming the route and the reference, instead of
handing pi-ai undefined and letting it authenticate with an unrelated
ambient key.

The eager boot-time credential probe is gone: it could run before the
credentials service mounted and reported every failure as a missing key.
The route stays registered and browsable; the first request gives the
accurate error, whose guidance now leads with the credential store and
mentions a literal apiKey last.
2026-07-30 15:51:35 +08:00
Yichen Jiang
0d96676f35 feat(web): mount the config plane in dsh web and pin the Models page keyless
apps/cli/cordis.yml gains settings-local, credentials-local, and the bare
dormant llm-pi-ai row (manifest deps added for the resolver contract);
llm-deepseek drops its !!js apiKey inline for per-request credential
resolution. Both adapters tag apiKeyEnv role('credential-ref') so the
form mounts the credential control. The web e2e scaffold isolates a
harness home per run — an in-process boot must never touch the
developer's real ~/.dsh — and the new models-settings scenario pins the
whole loop through the shipped app: dormant directory as add vocabulary,
schema-driven editor apply landing in settings.yaml, the route
registering live (topology frame), and a write-only key landing in the
temp .env with the configured badge converging. A hermetic test-owned
reference name keeps a developer's real provider keys from flipping the
badge. schema-form joins the platform module table (seed + externals)
so client bundles share one instance.
2026-07-30 09:29:40 +08:00
Yichen Jiang
4989494e75 feat(llm): topology event and configurable-provider directory
ctx.llm gains 'llm/adapters-updated' — a payload-free registry notification
emitted at every topology commit point (adapter routes registering or
disposing, directory entries appearing or withdrawing) with contained
observers and INVARIANT rethrow — plus registerConfigurableProviders/
listConfigurableProviders, the directory of routes an adapter plugin can
activate through configuration. llm-deepseek declares deepseek-official
(whole llm-deepseek section as profile); llm-pi-ai declares the full
installed catalog under providers.<provider> even while dormant, so the
web settings surface can offer every provider before any route exists.
The invariant companion asserts the registry stays readable at each
notification.
2026-07-29 16:45:06 +08:00
Yichen Jiang
4e9916b3e5 feat(llm-pi-ai): dormant bare mount — routes live entirely in the settings plane
An empty or omitted providers dict is now the valid dormant posture: the
adapter mounts with zero routes and no catalog entries, registers routes
the moment the llm-pi-ai settings section supplies profiles, and drops
them when it empties. The TUI demo mounts the adapter bare, so adding an
openai/anthropic provider is purely a settings.yaml (or, next PR, web
form) operation with per-request apiKeyEnv credential resolution.
2026-07-29 14:56:09 +08:00
Yichen Jiang
b0a2011d95 docs: bilingual credentials/settings-consumer documentation, catalogs, and gates
New credentials data-structure page (type-equiv manifested), group README,
rewritten llm-deepseek/llm-pi-ai READMEs (dynamic configuration, dict
profiles, credential chain), capability-seams/service-role registration,
Agent Note (bilingual), demo compositions mounting settings-local +
credentials-local with no inline key plumbing, installSettingsSection
consumer helper on the settings seam (deduplicating both adapters' wiring),
jscpd symmetry markers for the provider twins, runtime-closure additions for
python/sdk-runtime, and doc-budget ceilings AGENTS.md 1750→1755 /
packages/README.md 850→865 for the structural one-line group rows.
2026-07-29 14:20:06 +08:00
Yichen Jiang
c0426142c5 feat(llm-pi-ai): route-keyed profiles with per-request resolution and in-place route swaps
providers becomes a dict keyed by provider route, so the composition base
and the llm-pi-ai settings section merge per provider and the route set is
structural; the pre-release array shape and per-profile provider field fail
loud with migration directions. The adapter reads a profiles thunk once per
operation and resolves the credential per stream call (literal apiKey, then
apiKeyEnv through ctx.credentials with an ambient env fallback, then pi-ai's
provider-native discovery), so key, endpoint, and knob changes reach the
next request without restarts. Route-set or captured-retry-policy changes
re-register the same adapter instance in one synchronous section; an invalid
settings snapshot keeps the last good profiles.
2026-07-29 13:36:29 +08:00
_Kerman
971f20b66e fix: restore message migration CI coverage 2026-07-28 14:29:54 +08:00
_Kerman
fbf87e660c refactor: identify and freeze messages at creation 2026-07-28 13:55:59 +08:00
Tianyi Cui
f6a450102e Merge updated origin/master into feat/tui-master-port 2026-07-27 23:55:53 +08:00
Tianyi Cui
8a952ab433 Merge remote-tracking branch 'origin/master' into worktree/pr628-merge-20260727
# Conflicts:
#	.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md
#	docs/architecture.i18n.yaml
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/core-data-structures/llm-streaming.md
#	docs/core-data-structures/llm-streaming.zh.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	examples/headless-agent/tests/headless.snapshot.ts
#	packages/compact/compact-basic/tests/compact-loop-repro.spec.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/src/loop.ts
#	packages/examples/agent-spine-demo/README.md
#	packages/llm/README.md
#	packages/llm/llm-deepseek/src/adapter.ts
#	packages/llm/llm-pi-ai/src/adapter.ts
#	packages/llm/llm-retry/README.md
#	packages/llm/llm/README.md
#	packages/llm/llm/src/index.ts
#	packages/llm/llm/tests/service.spec.ts
#	packages/support/llm-replay/src/index.ts
#	packages/support/llm-replay/tests/llm-replay.spec.ts
2026-07-27 22:44:43 +08:00
Turtle
6a7307de37 fix(llm-pi-ai): classify transport truncations
Personal customization replayed onto upstream master source.
2026-07-27 18:53:29 +08:00
Yichen Jiang
73e7e27799 refactor(llm): resolve model metadata together 2026-07-26 13:07:27 +08:00
Yichen Jiang
baea5018e5 fix(llm): bind reasoning resolution to adapter lifecycle 2026-07-25 22:59:45 +08:00
Yichen Jiang
478376acaf Merge remote-tracking branch 'origin/master' into worktree/llm-reasoning-effort
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml
#	docs/architecture.i18n.yaml
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	docs/core-data-structures/session.i18n.yaml
#	docs/event-producer-consumer.md
#	examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.expected.jsonl
2026-07-25 22:24:25 +08:00
Turtle
5345e93ceb Merge remote-tracking branch 'origin/master' into codex/provider-retry-policy
# Conflicts:
#	.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md
#	docs/core-data-structures/llm-streaming.i18n.yaml
#	packages/llm/llm-retry/README.md
#	packages/llm/llm-retry/src/index.ts
#	packages/llm/llm-retry/tests/retry.spec.ts
2026-07-25 16:05:05 +08:00
Turtle
b58e33268a feat(llm): add per-provider retry policies 2026-07-25 10:18:16 +08:00
Yichen Jiang
8372340f9c feat(llm): add model-specific reasoning effort controls 2026-07-25 07:47:51 +08:00
Turtle
207aab9d8d fix(llm): classify empty model completions as retryable EMPTY_RESPONSE
A well-formed provider stream that ends with finish_reason stop and zero
content blocks previously became a successful empty assistant message: the
turn completed silently, and drivers like goal-session counted the no-op
round. Both adapters now map that degenerate completion to a finish
{kind:'error'} with the new canonical EMPTY_RESPONSE code from dsh-llm, and
dsh-llm-retry adds the code to its default retryable set, so the existing
closed-step recovery path retries it and fails loud once the budget is
exhausted.

Covered by adapter unit tests, an llm-retry default-policy test, and a new
authored keyless ACP snapshot (empty-response-retry) with a deterministic
1 ms zero-jitter retry overlay.
2026-07-24 19:23:12 +08:00
Turtle
a58229187f chore(llm-pi-ai): bump pi-ai to 0.81.1 for the gpt-5.6 model catalog
pi-ai 0.80 restructured its entrypoints: the static catalog reads now
live on /providers/all as getBuiltinModels/getBuiltinProviders (keyed by
the catalog-only BuiltinProvider type, replacing KnownProvider at those
call sites), and the global streamSimple moved to /compat. The config
schema gains the new 'max' reasoning level.
2026-07-22 14:30:01 +08:00
Tianyi Cui
72c6696e4f Merge branch 'master' into worktree/routed-model-compaction-policy
# Conflicts:
#	docs/event-producer-consumer.md
2026-07-21 19:23:54 +08:00
Yichen Jiang
b6f6c58435 Merge remote-tracking branch 'origin/master' into worktree/routed-model-compaction-policy
# Conflicts:
#	.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml
#	.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md
#	.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	examples/headless-agent/tests/harness.ts
#	examples/repl-agent/cordis.yml
#	packages/compact/compact-basic/README.md
#	packages/compact/compact-basic/src/index.ts
#	packages/compact/compact-basic/tests/compact-basic.spec.ts
#	packages/compact/compact-basic/tests/loader-composition.spec.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/llm/README.md
#	packages/llm/llm-deepseek/src/adapter.ts
#	packages/llm/llm-pi-ai/src/adapter.ts
#	packages/llm/llm/README.md
#	packages/llm/llm/src/index.ts
#	scripts/gen-cordis-catalog.ts
#	website/zh-CN/api/harness/events.md
#	website/zh-CN/api/harness/llm.md
#	website/zh-CN/api/harness/token-meter.md
#	website/zh-CN/guide/config.md
2026-07-21 10:17:55 +08:00
Tianyi Cui
023cde5d82 Merge latest master into invariant service seam 2026-07-20 22:49:27 +08:00
Tianyi Cui
cc2e14f76e fix: close recovery review gaps 2026-07-20 22:11:26 +08:00
Tianyi Cui
1145ee5fc3 fix(invariants): assert runtime relationships, not API shapes 2026-07-20 19:34:19 +08:00
Yichen Jiang
cfa180c127 Resolve compaction policy per routed model 2026-07-20 15:34:00 +08:00
Tianyi Cui
3b0b0cefeb feat: implement bounded LLM request recovery 2026-07-20 03:34:19 +08:00
Tianyi Cui
941b0411d8 feat(invariants): implement package runtime checks 2026-07-20 00:38:37 +08:00
Tianyi Cui
433670a754 feat(invariants): require package-owned companions 2026-07-19 22:13:50 +08:00
Tianyi Cui
7617963474 docs(llm-pi-ai): describe usage overflow mapping
Document every context-window path returned by mapStopReason: recognized provider error wording, successful stop usage beyond the resolved window, and zero-output length stops that fill the window.

This keeps the public return contract aligned with usage-based overflow classification without duplicating the provider-specific detection table owned by pi-ai.
2026-07-19 15:04:51 +08:00
Tianyi Cui
4791b40b26 fix(llm-pi-ai): classify usage-based context overflow
Pass each resolved catalog model capacity into pi-ai stream conversion so the upstream full-message classifier can recognize provider-specific, silent, and length-stop overflow signals. Retain the harness text fallback for legacy provider wording and cover the catalog-resolution path with a mock-provider regression.
2026-07-19 14:18:13 +08:00
Tianyi Cui
954c2ad2b5 docs(llm-pi-ai): track overflow classification gap 2026-07-19 13:03:15 +08:00
Tianyi Cui
7be78c7d4c Merge latest origin/master into compact-post-step-overflow-recovery
# Conflicts:
#	docs/agent-lifecycle.md
#	docs/architecture.md
#	docs/cookbook/extension-cookbook.i18n.yaml
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/event-producer-consumer.md
#	docs/rfc/INDEX.md
#	docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md
#	docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml
#	docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md
#	docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md
#	docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md
#	docs/rfc/implemented/feature/2026-07-07-session-prefix.md
#	packages/compact/compact-basic/README.md
#	packages/compact/compact-basic/src/config.ts
#	packages/compact/compact-basic/src/index.ts
#	packages/compact/compact-basic/src/summarizer.ts
#	packages/compact/compact-basic/tests/compact-basic.spec.ts
#	packages/compact/compact-basic/tests/compact-loop-repro.spec.ts
#	packages/compact/compact/README.md
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/core/agent-loop/src/loop.ts
#	packages/core/agent-loop/tests/cancel.spec.ts
#	packages/llm/llm-deepseek/src/adapter.ts
#	packages/llm/llm-pi-ai/README.md
#	packages/llm/llm-pi-ai/src/stream.ts
#	packages/llm/llm-pi-ai/tests/convert.spec.ts
#	packages/llm/llm/README.md
#	packages/llm/llm/src/index.ts
#	packages/llm/llm/tests/service.spec.ts
#	scripts/gen-doc-graphs.ts
2026-07-19 12:06:23 +08:00
Tianyi Cui
42863d7c24 Merge branch 'codex/simp-prune-llm-contract' into codex/simp-hide-llm-adapter-helpers
# Conflicts:
#	docs/config-catalog.md
#	packages/llm/llm-deepseek/src/index.ts
#	packages/llm/llm-deepseek/tests/adapter.spec.ts
#	packages/llm/llm-pi-ai/README.md
#	packages/llm/llm-pi-ai/src/index.ts
#	packages/llm/llm-pi-ai/tests/adapter.spec.ts
#	packages/llm/llm-pi-ai/tests/convert.spec.ts
2026-07-18 12:47:53 +08:00
Hypatia May
e8d066f750 feat(core): add post-step request recovery (PR3 phase 1) 2026-07-15 16:03:52 +08:00
Yichen Jiang
634840d406 fix(llm-pi-ai): validate replay provenance 2026-07-15 15:26:03 +08:00
Yichen Jiang
d3f8cb0f23 fix: harden replay and pi-ai request boundaries 2026-07-15 13:45:19 +08:00
Yichen Jiang
f1d39921c9 feat(acp): advertise and switch llm models 2026-07-15 13:33:42 +08:00
Yichen Jiang
815365dbbe Merge remote-tracking branch 'origin/master' into worktree/provider-routed-llm-adapters
# Conflicts:
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.md
#	docs/event-producer-consumer.md
#	docs/persistence-catalog.md
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl
#	examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl
#	examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl
#	examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl
#	examples/acp-agent/tests/snapshots/skill-load/session.jsonl
#	examples/acp-agent/tests/snapshots/text-turn/session.jsonl
#	examples/sandbox-acp-agent/cordis.yml
#	examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl
#	examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl
#	examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl
#	packages/compact/compact-basic/README.md
#	packages/compact/compact-basic/src/index.ts
#	packages/compact/compact-basic/tests/compact-basic.spec.ts
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/src/loop.ts
#	packages/core/agent-loop/tests/properties.spec.ts
#	packages/core/session/README.md
#	packages/core/session/src/types.ts
#	packages/core/session/tests/derived-cache.spec.ts
#	packages/llm/llm-deepseek/src/index.ts
#	packages/llm/llm-pi-ai/README.md
#	packages/llm/llm-pi-ai/src/adapter.ts
#	packages/llm/llm-pi-ai/src/convert.ts
#	packages/llm/llm-pi-ai/tests/adapter.spec.ts
#	packages/llm/llm/README.md
#	packages/llm/llm/src/call-config.ts
#	packages/llm/llm/src/index.ts
#	packages/ui/acp-agent/src/index.ts
#	packages/ui/acp/tests/harness.ts
#	packages/ui/jsonrpc/README.md
#	packages/ui/jsonrpc/src/server.ts
#	packages/ui/stdio-agent/README.md
#	packages/ui/stdio-agent/src/index.ts
#	python/sdk/README.i18n.yaml
2026-07-14 22:17:50 +08:00
Yichen Jiang
e547980d77 feat(llm): route adapters by provider 2026-07-14 21:57:52 +08:00
Tianyi Cui
9361402c68 Merge branch 'codex/simp-prune-llm-contract' into codex/simp-hide-llm-adapter-helpers
# Conflicts:
#	docs/config-catalog.md
2026-07-14 19:10:48 +08:00
Tianyi Cui
91075e010a refactor: hide llm adapter helpers 2026-07-14 04:03:44 +08:00
Tianyi Cui
148046b9c8 docs: rebalance prose cleanup and add trimming skill 2026-07-13 23:27:00 +08:00
Tianyi Cui
75838e10b5 docs: trim generated prose 2026-07-12 03:36:43 +08:00
Tianyi Cui
cd9737d569 Gate JSDoc completeness on every package export
New doc-sync gate verify-export-jsdoc walks every module-level exported
name under packages/*/*/src and requires description prose everywhere,
plus @param per parameter and @returns on non-void annotated returns for
function-like exports, public class methods, properties, and accessors.
The parsing + check helpers move out of gen-cordis-catalog.ts into a
shared scripts/jsdoc.ts so 'documented' means one thing on both gated
surfaces.

Deliberate exemptions (documented in the RFC): heritage-declared class
members (the seam declaration is the doc's one home — the one checker
query in an otherwise pure-AST walk), cordis plugin-protocol slots
(name/inject/reusable/Config/apply, top-level and static), constructors,
overload implementations, declare-module augmentation bodies, and
re-export statements (checked at the defining module).

The 203 under-documented exports the gate found at adoption are filled
in this change, so the gate lands green; generated catalogs/graphs are
regenerated for the shifted line pointers.

RFC: docs/rfc/implemented/process/2026-07-06-export-surface-jsdoc-gate.md
2026-07-06 22:09:30 +08:00
Tianyi Cui
b9e2d7ed85 Merge master into app attribution RFC 2026-07-05 00:45:39 +08:00
Tianyi Cui
544cc0439e Merge remote app attribution branch
Resolve the RFC and implementation to defer OpenRouter-specific attribution headers and keep mandatory attribution to User-Agent only.
2026-07-04 22:47:53 +08:00
Tianyi Cui
5a8234643a refactor(llm): drop the inert request knobs — prefill and strict
GenerateOptions.prefill had no production setter and both adapters
rejected it with LlmError('UNSUPPORTED') — its entire observable
behavior was two throws, each pinned by one adapter test. DeepSeek's
chat-prefix completion is a Beta feature on a base URL neither adapter
targets. ToolSchema.strict was threaded through defineTool, the
registry's schemas() allowlist, the deepseek wire mapping, a per-tool
payload-patching pass in the pi-ai adapter, and a tool-catalog render
row, yet no shipped tool set it and the internal endpoint story for
strict mode was never built.

Remove both fields end-to-end: the vocabulary in dsh-llm, the adapter
guards and wire branches, the dsh-tools threading, the tool-catalog
Strict row, the pinning tests, the core.md pastes, the adapter README
rows, and the cookbook line that used prefill as the UNSUPPORTED
example (now stated generically). The pi-ai payload fixup keeps the
half with a job: pi-ai stamps strict:false on every serialized tool,
so the fixup scrubs it unconditionally for wire parity with the
hand-rolled twin (per-tool set/delete machinery gone). temperature/
stop/maxTokens are untouched — honored end-to-end by both adapters.

Each knob returns with its first real producer: prefill with an
adapter that implements chat-prefix completion, strict with a tool
that wants it and a beta-endpoint story.

RFC: docs/rfc/implemented/simplification/2026-07-04-drop-inert-request-knobs.md
(moved from proposed/, amended to shipped reality); the content-block
vocabulary RFC's consequence line now records prefill as producer-gated.
2026-07-04 18:38:39 +08:00
Tianyi Cui
0ebb86e70f Implement mandatory app-attribution headers per the RFC
dsh-llm owns the vocabulary (attribution.ts): AppIdentity with the version
read from the package manifest, userAgent(), and attributionHeaders(target,
identity) over a closed AttributionTarget union ('generic' | 'openrouter').
Both adapters send the headers on every provider request — llm-deepseek in
its fetch headers, llm-pi-ai through pi-ai's StreamOptions.headers — behind
an explicit attributionTarget config (never inferred from baseURL), with
mock-server tests asserting exact wire arrival and the absence of the
OpenRouter set by default.

The RFC moves to implemented/ amended with the settled identity (the
deepseek-harness token, the DeepSeek Harness title, the planned
deepseek-ai/deepseek-harness-sdk URL behind a FIXME until that repo exists)
and the explicit-config OpenRouter decision.
2026-07-04 18:14:42 +08:00