mirror of
https://github.com/Gitlawb/openclaude.git
synced 2026-11-06 20:58:14 -04:00
v0.33.0
65
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  Kevin CodexandOpenClaude
|
50d4058861 |
feat: publish as @twigpine/openclaude (#2269)
The npm package moves from the @gitlawb scope to @twigpine. Everything that names the package now uses the new name, and the release workflow can create the new package and close out the old one. Rename - package.json, bun.lock, release-please config, docs, website, VS Code extension and tests use @twigpine/openclaude. - scripts/build.ts takes the baked-in package name from package.json instead of repeating it; scripts/verify-clean-install.ts does the same. One final release under the old name, then nothing - Shipped builds have no working auto-updater (the no-telemetry plugin stubs it out), so people update by re-running the install command. Anyone still typing the old name lands on whatever is latest there. - release.yml publishes this release once more as @gitlawb/openclaude. That build shows a startup notice, and `openclaude update` and `/update` print the same note and stop, saying the package moved and how to switch. - legacy-scope-gate limits this to a single release. It only runs while the old name's latest version is still 0.31.0. - There is no in-place migration. Both packages own the `openclaude` bin, so npm refuses to install one over the other, and a forced install is undone by uninstalling the old package. The docs give the safe order. Tokenless releases (OIDC only) - Both publish steps authenticate through npm trusted publishing and attach provenance; no npm token is used anywhere. npm only attaches a trusted publisher to a package that already exists, so @twigpine/openclaude is created once by hand as an empty 0.0.0 placeholder before its first release. - Publish steps skip a version that is already on the registry, publish the verified dist/ with --ignore-scripts, and report provenance and whether a trusted publisher was used in the run summary (scripts/npm-publish-report.ts). - The legacy-named build is built and install-verified before anything is published. Co-authored-by: OpenClaude <openclaude@gitlawb.com> |
||
  GravireiandGravirei
|
afa71563b6 |
chore(rebrand): update Gitlawb references to Twigpine (#2246) (#2248)
* chore(rebrand): update Gitlawb references to Twigpine (#2246) The GitHub org has been renamed to Twigpine, so point repo URLs, badges, CI repo-identity guards, and user-facing sponsor/partner labels at the new name. Scope is deliberately limited to references that are safe to change today: - GitHub URLs (github.com, api.github.com, raw.githubusercontent.com), including the skills registry and release-please release notes - The release-please release trigger, which gates on the repo slug and would otherwise stop publishing - User-visible display strings: gateway label/name, AI/ML API partner name, sponsored-tip sponsor, and docs/site prose Left on the old name because the rename has not landed for them: - `@gitlawb/openclaude` npm scope (the package does not exist on npm) - opengateway/ads/docs subdomains, which resolve only under gitlawb.com - The `gitlawb-opengateway` preset id, tip ids, and gateway file names, which are persisted in user config and sent on the wire * fix(aimlapi): stop matching topup intent on partnerName (#2246) partnerName is display metadata that travels alongside the partner id, not part of the intent identity. It is now excluded from INTENT_KEYS, so matchesIntent no longer requires it to be unchanged. Without this, renaming the partner on the Gitlawb -> Twigpine rebrand would have stranded any in-flight topup: a receipt persisted under the old name fails the strict equality check, so loadAimlapiTopupState returns null and the user restarts checkout. partnerId remains the identity field, so receipts are still scoped to the correct partner. * fix(web): use current Twigpine artwork for the partner card (#2246) The partner asset was a byte-identical rename, so the roster row rendered the former GitLawb key/branch symbol under the Twigpine name while the README pointed at the official tree mark. Vendors the current artwork from twigpine.com/logo.png, resized to the roster's 256x256 convention, keeping the self-hosting contract in web/src/data/partners.ts. --------- Co-authored-by: Gravirei <gravirei@users.noreply.github.com> |
||
  Sakiandliuyang
|
5bc160fb8b |
feat: add AnySearch as an explicit web search backend (#2261)
* feat: add AnySearch web search backend * fix(anysearch): preserve non-json error details --------- Co-authored-by: liuyang <liuy.web@lingyu.work> |
||
 rome-xi
|
3ed1c5a191 |
docs: clarify sharp opt-in for local image decode vs passthrough (#2226)
Maintainer confirmed sharp stays intentionally opt-in on published installs. Document that clipboard paste / local FileRead decode need `npm i -g sharp`, while pre-encoded URL/base64 passthrough does not. |
||
|
Kevin CodexandOpenClaude
|
790c009ae9 |
feat(search): make Exa the default web search backend and add /search (#2257)
* feat(search): make Exa the default web search backend and add /search Exa now leads the auto chain: keyed Exa (EXA_API_KEY) runs first, other keyed backends next, then a new keyless Exa free-tier adapter (Exa's hosted MCP endpoint), with DuckDuckGo as the last-resort fallback. Built-in search for Anthropic/Vertex/Foundry/Codex is unchanged. WEB_SEARCH_PROVIDER=exa uses the keyed API when a key is set, otherwise the free tier. New Exa options: EXA_SEARCH_TYPE, EXA_NUM_RESULTS, EXA_FREE_TIER (opt-out). The free-tier adapter handles all three rate-limit reply shapes, spaces calls to Exa's default QPS, backs off for five minutes after a limit, and parses Exa's plain-text result blocks defensively. New /search command: pick a backend, add or remove an API key via a masked input, show status, run a test search. Choices are saved to the env block of ~/.openclaude.json (0600) and applied immediately; settings.json env entries that override them are reported instead of silently losing. Security: isSensitive arg redaction now also covers local-jsx commands (/ads, /search), which previously recorded raw inline args in the transcript and model context. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> * fix(search): fall through when domain filters empty the Exa free-tier hits The keyless Exa endpoint has no server-side domain filters, so when the client-side filter removed every hit, runSearch returned a successful empty result and never tried DuckDuckGo, which can honor the filter. Providers can now set `fallbackInAuto` on their output; auto mode skips to the next backend on that signal, and returns the filtered-empty result only if no later backend does better. Genuine no-results replies and explicit `exa` mode are unchanged. Also adds doc comments to the touched functions that lacked them. Co-Authored-By: OpenClaude <openclaude@gitlawb.com> --------- Co-authored-by: OpenClaude <openclaude@gitlawb.com> |
||
 JATMN
|
70d97fd137 |
feat(web-search): add Ollama backend (#2234)
* feat(web-search): add Ollama backend * fix(web-search): harden Ollama routing * fix(web-search): preserve Ollama profile identity * fix(web-search): align Ollama diagnostics * fix(web-search): align Ollama endpoint diagnostics * fix(web-search): honor Ollama endpoint aliases * fix(web-search): reject Ollama key placeholders * fix(web-search): complete Ollama configuration guidance |
||
|
JATMN
|
876fb7924a |
feat(query): configure idle timeout (#2233)
* feat(query): configure idle timeout * docs(query): clarify idle timeout limits * feat(settings): configure query idle timeout * test(query): exercise idle timeout integration * fix(query): apply live idle timeout overrides |
||
 0xfandom
|
35d7edc2f6 |
fix(api): validate API_TIMEOUT_MS in the native Anthropic clients (#2169)
* fix(api): validate API_TIMEOUT_MS in the native Anthropic clients
The native Anthropic client path parsed API_TIMEOUT_MS with a raw
parseInt: `parseInt(process.env.API_TIMEOUT_MS || String(600 * 1000), 10)`
in client.ts and `parseInt(process.env.API_TIMEOUT_MS || '', 10)` in the
non-streaming fallback. Because `||` only substitutes the default for an
empty/unset value, any non-empty malformed value ("abc", "25ms") is truthy
and parses to NaN, and a negative value passes straight through. A NaN or
negative timeout on the SDK client is undefined behavior, and an oversized
value overflows the 32-bit setTimeout ceiling into a tiny/immediate delay.
The OpenAI-compatible shim already routes API_TIMEOUT_MS through
getApiTimeoutMs, which rejects non-digit/negative input, falls back to a
default, and clamps to the 32-bit ceiling. Reuse that single parser in the
native clients too. getApiTimeoutMs gains an optional fallbackMs argument so
the non-streaming path keeps its context-specific default (120s on remote,
300s otherwise) while still validating and clamping the override; existing
shim callers are unaffected (the default remains 600s).
Tests cover the fallback argument in the parser and assert the constructed
native client's timeout for malformed, negative, zero, unset, valid, and
oversized values.
* test(api): cover the non-streaming fallback timeout and pin route env
Add direct coverage for getNonstreamingFallbackTimeoutMs, which the previous
tests only exercised indirectly through the shared parser. It now asserts the
context-specific defaults survive the change (300s local, 120s remote) for
missing and invalid API_TIMEOUT_MS, that a valid override is honored in both
contexts, and that an oversized one is clamped. The function is exported for
this; test files are knip entry points, so it does not read as dead code.
Also clear every provider route-selection variable explicitly in the native
client timeout test. The suite's afterEach already restores them, but pinning
them up front keeps an inherited CLAUDE_CODE_USE_OPENAI (or another route
flag) from diverting getAnthropicClient into the shim and measuring the wrong
client's timeout.
* test(api): pin the native client path and document the timeout contract
The native timeout test cleared many provider variables but left
NEARAI_API_KEY untouched, and the suite never snapshotted it at all.
NEARAI_API_KEY alone selects the env-only Near AI route, and clearing the
competing vendor keys removed the very credentials whose presence suppresses
it, so an inherited value routed getAnthropicClient to the OpenAI shim. The
shim is returned as a cast object with no SDK timeout, so the assertions read
undefined and the regression silently stopped being covered. CLINE_API_KEY had
the same gap.
Snapshot, clear, and restore both alongside the other route-selection inputs,
and assert the constructed object is an Anthropic instance before reading its
timeout, so a stray variable or a future env-only route fails loudly instead
of weakening the test. Verified by injecting NEARAI_API_KEY: the guard now
fails on the shim object rather than passing on undefined.
Also refresh the API_TIMEOUT_MS reference, which still said the Anthropic SDK
kept its own timeout handling. It now describes both consumers: the
headers-deadline semantics for OpenAI-compatible paths, and the native
Anthropic SDK request timeout plus the non-streaming fallback's own defaults
(120s remote, 300s otherwise), under the same validation and clamping.
|
||
|
JATMN
|
055e5d551a |
feat(launcher): support --max-old-space-size-percentage (#2219)
* feat(launcher): support --max-old-space-size-percentage heap sizing Convert Node's percentage heap flag into --max-old-space-size from constrained or total RAM so small containers and large workstations can avoid the fixed 8192 MB cap on every supported Node version. Fixes #2213 * fix(launcher): reject unconstrained memory sentinels in heap percentage Ignore libuv UINT64_MAX constrainedMemory values, clamp sub-megabyte percentage results to 1 MB, and keep spaced heap-flag values on background Node launches. * fix(launcher): report unresolved heap percentage instead of silent MB fallback A valid percentage with unknown available memory no longer looks like an unrelated megabyte env or default success; the launcher warns once, docs state full precedence, and child NODE_OPTIONS tests call the real helper. * fix(launcher): strip launcher heap flags when Node already has a cap Commander rejected --max-old-space-size-percentage on native heap+gc and disable-relaunch paths. Strip those argv tokens before import, and do not treat a following non-percentage word as the flag value. * fix(launcher): propagate execArgv heap caps to subprocess NODE_OPTIONS Child tools inherit NODE_OPTIONS, not the parent process.execArgv. When the CLI already started with a numeric --max-old-space-size cap there, copy that value into NODE_OPTIONS instead of defaulting to 8192 MB. Also strip launcher-only heap flags on the OPENCLAUDE_HEAP_RELAUNCHED early-return path and harden launcher integration tests with Node 22-safe execArgv fixtures. |
||
  fancivezandfancivez
|
0b68e579b9 |
fix(profiles): apply context limit to all profile models (#2201)
* fix(profiles): apply context limit to all models * fix(profiles): include saved model in context limits * test(profiles): cover saved model context lifecycle * fix(profiles): align context limit keys with runtime models --------- Co-authored-by: fancivez <fancive@gmail.com> |
||
|
JATMN
|
3609d751c0 |
fix: identify OpenCode Go requests (#2203)
* fix: identify OpenCode Go requests * fix: harden OpenCode Go identity headers * fix: pin OpenCode session across retries |
||
 euxaristia
|
3451187aed |
fix(ctx): let explicit overrides beat discovered context windows (#2082)
* fix(ctx): prefer known model limits over generic 128k discovery Proxies such as OmniRoute often report context_length 128000 when per-model metadata is missing. That discovery value was beating known descriptors and settings.modelLimits, so 1M models auto-compacted against a 128k budget. Prefer larger known descriptors over the generic 128k discovery default, and let settings/env overrides beat discovery. Document the override path in /set-context-window help. Refs #2081 * test(ctx): cover OmniRoute + gpt-5.6-sol (user-reported gpt sol) The Discord report used GPT-5.6 Sol, not gpt-5.4. Regression now pins the catalog-less custom-route rescue to the 272k descriptor for gpt-5.6-sol. Refs #2081 * fix(ctx): let explicit overrides beat discovered context windows Addresses both review findings on #2082. P1 — drop the generic-128k rescue from the previous commit. The custom gateway discovery mapper copies an endpoint's own context_length / context_window into ModelCatalogEntry.contextWindow, and nothing synthesizes 128k on our side, so the numeric value carries no provenance: a flat 128000 is indistinguishable from a real per-deployment or tenant cap. Budgeting a known-larger descriptor over that cap traded an early auto-compact for a late context-window API failure. Discovery is authoritative over the model descriptor again. What remains is the safe half of the fix: an env prefix override and settings.json modelLimits now sit above discovery, so a user on a gateway that advertises the wrong window can pin the real one. Docs and /set-context-window help point at that path. Tests cover a gateway-advertised 128k and 200k window staying put for a model the catalog knows is larger, plus env and modelLimits overrides beating it. P3 — isolate the discovery-cache fixtures. getClaudeConfigHomeDir() ignores CLAUDE_CONFIG_DIR by design, so both the new modelLimits test and the pre-existing withTempConfigDir helper were writing fixtures into the caller's real config dir. Both now use setClaudeConfigHomeDirForTesting with save and restore, and clear the discovery cache on teardown so the in-memory sync snapshot cannot leak into a later suite. The modelLimits test now asserts the isolated cache resolves on its own before asserting the settings pin wins. Refs #2081 * test(ctx): cover env prefix overrides over discovery cache CodeRabbit on #2082 asked for a regression where CLAUDE_CODE_OPENAI_* prefix keys beat a seeded discovery cache for both contextWindow and maxOutputTokens, not just exact keys and settings.modelLimits. Refs #2081 * docs(ctx): Clarify permanent overrides for catalogued models Keep the documented workaround aligned with resolver precedence so users do not expect modelLimits to override built-in catalog entries. Refs #2081 |
||
 anushka ✩
|
294bd9a1df |
Add optional Sentry error reporting (env-driven, opt-in) (#2139)
* Add optional Sentry error reporting (env-driven, opt-in) * Fix Sentry init to use dynamic import instead of require (ESM compatibility) * Document SENTRY_DSN setup in advanced-setup docs * Disable Sentry default integrations; document runtime install requirement * Wire reportErrorToSentry into top-level error handlers; add sentry.test.ts |
||
 Bogdan
|
09eba26d30 |
feat(cost): support exact custom model pricing (#2131)
* feat(cost): support exact custom model pricing * fix(cost): address custom pricing review feedback |
||
|
Bogdan
|
c30578819e |
diagnostics(query): trace interruption causality (#2111)
* diagnostics(issue-1830): trace interruption causality * test(issue-1830): lock interruption ownership matrix * fix(codex): preserve stream deadline contract * fix(diagnostics): harden interruption trace lifecycle Refs #1830 * fix(diagnostics): harden interruption trace settlement Refs #1830 * fix(diagnostics): preserve interruption causality * fix(diagnostics): address interruption trace review * fix(diagnostics): preserve tracing observer contracts * fix(diagnostics): preserve interruption trace contracts * test(permissions): cover interactive hook interrupts |
||
 Lucas Molinariandjatmn
|
95409464f3 |
feat(codex): move codexplan default to GPT-5.6 Sol (#2051)
* feat(codex): default codexplan to GPT-5.6 Sol
Preserve existing reasoning and routing behavior while updating the default model, labels, documentation, and focused coverage.
* test(codex): lock fallback and routing behavior
* make credential-step test self-contained
* fix(codex): default unset teammate fallback to GPT-5.6 Sol
The changes to the inert codex config keys are known to have no functional effect, but we updated them to ensure the defaults are correct and consistent across the table.
* fix codexplan gateway defaults after model resolution
* Revert "fix codexplan gateway defaults after model resolution"
This reverts commit
|
||
|
JATMN
|
b0cbfe1100 |
fix(repl): make local interactive max-turns configurable (#2086)
* fix(repl): make interactive max-turns configurable Wire --max-turns into interactive sessionConfig and honor OPENCLAUDE_MAX_TURNS / CLAUDE_CODE_MAX_TURNS so long autonomous REPL sessions can raise the default 50-turn per-prompt cap (fixes #2079). * fix(repl): forward --max-turns on connect/ssh/remote launches sessionConfig covered the normal interactive paths; connect, SSH, assistant, and --remote built REPL props without spreading it, so the CLI override was dropped despite help advertising interactive support. * fix(repl): scope interactive max-turns to local query loops Remote-backed sessions bypass local query(), so forwarding --max-turns into those REPL props over-claimed enforcement. Clarify help/docs and match OPENCLAUDE_MAX_RETRIES precedence when OPENCLAUDE_MAX_TURNS is set but invalid. * feat(config): add interactive max turns under /config Expose replMaxTurns in the Config panel (50/100/200/500) and resolve it after CLI/env so local interactive sessions can raise the per-prompt cap without restarting. Resolve at query time so mid-session /config changes apply on the next prompt. * docs(repl): clarify invalid OPENCLAUDE_MAX_TURNS precedence Match the OPENCLAUDE_MAX_RETRIES contract: a set-but-invalid primary env var uses the default and does not fall through to legacy or /config. * fix(repl): address PR review on max-turns help and web version gate Share the --max-turns Commander description via an imported constant so help and tests stay in sync without breaking the CLI bundle, replace source-only help assertions with Commander behavior coverage, and add the published 0.27.0 entry so web verify-dist passes. * fix(repl): typecheck Commander maxTurns opts and warn on invalid env Avoid TS2339 on untyped Commander opts, log invalid OPENCLAUDE_MAX_TURNS like MAX_RETRIES, and clarify that /config shows the persisted preference. * fix(repl): warn when max turns is unlimited * fix(repl): scope unlimited-turn warning locally * fix(repl): preserve interactive turn caps across backgrounding * fix(repl): preserve turn caps when backgrounding * fix(repl): share turn budget across background handoff * fix(repl): reserve turns at provider dispatch * fix(repl): snapshot background handoff transcript * fix(tasks): avoid phantom background session task * fix(repl): preserve handoff lifecycle state * fix(repl): own pending background handoffs * test(tasks): isolate background session task storage * fix(repl): refresh background task title and test cleanup * test(repl): cover max-turn CLI dispatch paths * test(queue): cover prepend notification and priority * fix(repl): skip background handoff after foreground query throws Rebased onto main and gate Ctrl+B continuation on !didThrow so a faulted foreground turn cannot start a background session from partial state. * fix(repl): address PR review findings on notifications and handoff Dedupe background task notifications by embedded task id, gate background continuation on preflight veto, scope queue removal to main-thread notifications, and forward maxTurns through all launchRepl entry points. * fix(repl): resolve latest CodeRabbit inline review findings Dedupe claimed notification batches by task id, restore notifications on pre-registration abort, tighten test isolation, and replace remaining brittle source-text assertions with behavioral coverage. * fix(repl): keep notification restore active until provider dispatch Stop clearing notification ownership when preparation succeeds so pre-dispatch aborts can restore claimed queue items, and commit ownership once the provider starts. Add regression coverage for the abort path and headless max-turns zero. * test(repl): cover post-dispatch ownership and headless max-turns 0 Add regression tests for notification restore after provider dispatch commits ownership, and assert headless --max-turns 0 reaches query() without interactive resolution stripping the value. * fix(repl): restore only embeddable notifications on Ctrl+B handoff abort Track the deduped successor subset when restoring claimed main-thread task notifications so items already in the settled foreground transcript are not re-queued. Clarify that agent-scoped notifications intentionally stay on their owner drain path (issue #2079 scope is interactive turn caps only). * fix(repl): address review findings on background handoff Commit notification ownership when background sessions complete without provider dispatch, forward all task notifications on Ctrl+B again, and restore deferred max-turn cap attachments when continuation is cancelled. * fix(repl): guard deferred cap restore and skip remote turn limits Anchor deferred max-turn restoration to the handed-off transcript tail so a cancelled Ctrl+B handoff cannot attach the prior prompt's cap to a newer turn. Apply the interactive turn cap only in local sessions and align remote-session docs/help wording. * fix(repl): use messagesRef for deferred cap transcript anchor persistentMessages is block-scoped inside onQuery try; read the settled tail from messagesRef in finally so typecheck passes. * test: harden context fallback warning assertion after max-turns tests Scope the unknown-model context test to [context] warnings only so unrelated import-time debug logs do not fail CI, and clear turn env vars in both that test and replMaxTurnsProp setup to avoid cross-file pollution. * test: address PR review findings on headless max-turns boundary Add a runHeadless-to-ask regression that asserts maxTurns 0 is forwarded through the headless print path, and restore OPENCLAUDE_MAX_TURNS env vars in context.test.ts after the unknown-model fallback test mutates them. * test: tidy headless max-turns boundary test and env isolation Mock headless stdout so runHeadless completes cleanly without leaking output, restore spies in finally, and centralize turn-env cleanup in context.test beforeEach. * fix: address PR review findings for max-turns background handoff Separate model-request lifecycle from provider dispatch acceptance so interruption correction arms before async prep, notification ownership commits only after dispatch, deferred turn caps restore on every abort path, and foreground work stays blocked while handoff preparation runs. |
||
|
0xfandom
|
3925f2791c |
feat(auth): opt-in loopback proxy hosts that keep subscription (OAuth) auth (#2050)
* feat(auth): opt-in loopback proxy hosts that keep OAuth first-party Pointing ANTHROPIC_BASE_URL at any host other than api.anthropic.com switches the client to API-key mode, dropping a signed-in subscription session. That blocks running the CLI through a local transparent proxy (compression, inspection, caching) that forwards auth headers to Anthropic unchanged. Add ANTHROPIC_FIRST_PARTY_PROXY_HOSTS: a comma-separated host[:port] allowlist that extends first-party detection. It is honored only when the base URL points at a loopback host, and only loopback entries are considered -- both checks are redundant by design so a misconfigured non-loopback entry can never widen first-party status to an off-machine host. Default behavior is unchanged. Closes #2016 * docs(auth): document ANTHROPIC_FIRST_PARTY_PROXY_HOSTS * fix(auth): harden loopback proxy allowlist matching Normalize the base URL port to its scheme default (80/443) before comparing an explicit allowlist port, so a `127.0.0.1:80` entry matches `http://127.0.0.1`. Reject embedded credentials and non-http(s) schemes up front so an OAuth session is never attached to a URL carrying userinfo or a non-proxy scheme. |
||
|
Bogdanandjatmn
|
3808d19da4 |
fix(api): enforce API_TIMEOUT_MS for OpenAI-compatible headers (#1940)
* fix(api): enforce API_TIMEOUT_MS for OpenAI-compatible headers * test(api): cover Copilot responses fallback deadlines * fix(api): redact secrets in timeout URL paths * fix(api): harden Copilot response deadlines * fix(api): prevent header-timeout request replay * fix(api): harden timeout cleanup and redaction * fix(api): redact encoded transport credentials * fix(api): harden deadline retries and URL redaction * fix(api): preserve aborted fetch reasons * fix(api): preserve caller abort reasons * test(api): clear caller abort timer * docs(api): clarify API_TIMEOUT_MS transport scope * docs(api): explain timeout env loading * fix(api): reset deadline for proxy retries * fix(api): type deadline fetch adapter * fix(api): honor abort cleanup and request signals * fix(api): do not block proxy retries on body cancellation --------- Co-authored-by: jatmn <the@jat.mn> |
||
|
JATMN
|
46e80568be |
fix(provider): support custom Anthropic bearer auth (#1929)
* fix(provider): support custom Anthropic bearer auth * feat(provider): add custom Anthropic profile flow * fix(provider): restore custom Anthropic tokens on startup * fix(provider): preserve custom Anthropic env setup * fix(provider): clear stale custom Anthropic tokens * fix(provider): preserve custom Anthropic API-key env setup * fix(provider): cover custom Anthropic auth routing * test(api): isolate custom Anthropic client routing * test(api): cache-bust client provider imports * feat(provider): clarify custom provider presets * fix(provider): address custom Anthropic review feedback * fix(provider): preserve custom Anthropic headers * fix(provider): require custom Anthropic token * fix(provider): isolate custom Anthropic credentials * fix(provider): guard custom Anthropic setup * fix(provider): complete custom Anthropic integration * fix(provider): classify custom Anthropic proxies * fix(provider): gate proxy cache extensions * fix(provider): preserve custom Anthropic isolation * fix(provider): retain direct proxy model option * fix(provider): honor custom endpoint boundaries * fix(provider): keep proxy credentials local * fix(provider): disable proxy fast mode * fix(provider): preserve first-party route identity * fix(provider): isolate custom Anthropic endpoints * fix(provider): gate remaining first-party features * fix(provider): isolate custom Anthropic proxy features * test(web-search): make Brave timeout mock abort-aware * fix(provider): address custom Anthropic review feedback * test(provider): cover first-party beta gates * fix(provider): complete custom Anthropic isolation * fix(provider): complete custom Anthropic routing * fix(provider): address custom Anthropic review followups * fix(provider): close custom Anthropic review gaps * test(provider): keep custom Anthropic mock helpers isolated * test(provider): isolate model options gateway mocks * fix(provider): stabilize custom Anthropic model option display * fix(provider): address remaining review threads * fix(provider): synchronize active profile persistence * fix(provider): preserve custom Anthropic API key auth * fix(provider): avoid forwarding inherited Anthropic keys * fix(provider): guard custom auth selection * fix(provider): require first-party Anthropic port * test(web-search): avoid duplicate shared lock * fix(provider): resolve remaining review findings * fix(provider): harden custom Anthropic routing * fix(provider): simplify Anthropic thinking gate * fix(provider): preserve custom proxy routing and secret permissions * fix(mcp): isolate Claude.ai config cache by provider * fix(model): keep custom endpoints out of first-party UX * fix(provider): scope Opus off switch to Anthropic * fix(provider): disable tool search for custom proxies * fix(provider): close custom Anthropic review gaps * fix(provider): reject Anthropic staging custom profiles * fix(webfetch): classify custom Anthropic endpoints * fix(provider): block bearer auth at Anthropic origin * fix(provider): keep custom auth off staging OAuth * test(provider): strengthen auth regression coverage |
||
 JATMNandClaude
|
a32781537f |
fix(query): bound per-turn latency growth in long REPL sessions (#1949) (#1952)
* fix(query): bound per-turn latency growth in long REPL sessions (#1949) Addresses the progressive latency regression where consecutive prompts in a single session grow non-linearly (2nd prompt ~10s, 3rd 10+ min) due to unbounded message accumulation with no proactive compaction and no per-prompt turn cap on the main thread. - Cap the interactive REPL main thread at 50 turns per prompt (DEFAULT_REPL_MAX_TURNS). Headless/print mode and the SDK are unchanged (--max-turns flag / SDK callers still control it), preserving the SDK API contract. - Default maxMessagesCompactionThreshold to '200' so message-count compaction runs well before the context window fills, instead of 'off'. - Lower the auto-compact threshold buffer from 13k -> 30k so compaction fires earlier with less accumulated history. The effective-context floor buffer is kept at 13k and getAutoCompactThreshold() falls back to it for small-context models, so the threshold can never go negative (no #635 regression). Test updates: isolate the hard-cap override test from the new 200-message default, and correct an outdated constant reference in the autoCompact test. Co-Authored-By: Claude <noreply@anthropic.com> * fix(query): repair REPL latency guard * fix(query): cover resume and default guard paths * fix(query): enforce cap across interactive paths * docs(compaction): clarify disabled message limits * fix(query): retain explicit message thresholds * fix(query): enforce explicit threshold recovery * fix(query): honor legacy active-message limit * fix(doctor): report effective message compaction limit * fix(config): share message threshold validation * test(doctor): cover disabled message compaction * fix(compact): preserve latency guard coverage * test(repl): exercise turn cap defaults * fix(compact): honor disabled default message guard * fix(swarm): honor disabled auto compaction --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
0xfandom
|
eeed68f4fd |
feat(provider): add Cloudflare Workers AI integration (#1100) (#1178)
* feat(provider): add Cloudflare Workers AI integration
Adds Cloudflare Workers AI as a first-class OpenAI-compatible provider
preset, modeled on the Venice / Xiaomi MiMo descriptors.
- New `src/integrations/vendors/cloudflare.ts` descriptor:
- `classification: 'openai-compatible'`
- Default base URL with literal `<ACCOUNT_ID>` placeholder — users
substitute via `/provider` baseUrl edit, same shape as the Azure
OpenAI example already in `docs/advanced-setup.md`
- `CLOUDFLARE_API_TOKEN` env, with `OPENAI_API_KEY` as fallback
- `removeBodyFields: ['store']` since Workers AI rejects unknown
OpenAI body fields (mirrors Mistral / Gemini / Cerebras strip)
- Static catalog with current Workers AI chat models
(`@cf/meta/llama-3.3-70b-instruct-fp8-fast`,
`@cf/meta/llama-3.1-8b-instruct`,
`@cf/deepseek-ai/deepseek-r1-distill-qwen-32b`,
`@cf/qwen/qwen2.5-coder-32b-instruct`)
- Validation routing on `api.cloudflare.com` /
`gateway.ai.cloudflare.com` hosts so an env-pasted URL maps back
to the preset
- Env mirror sites in `src/utils/providerProfiles.ts`: mirror api key
into `CLOUDFLARE_API_TOKEN` when baseUrl contains a Cloudflare host
(3 sites: same-env check, openAIProfileEnv build, applyEnv).
- `CLOUDFLARE_API_TOKEN` added to `PROFILE_ENV_KEYS` / `SECRET_ENV_KEYS` /
`ProfileEnv` / `SecretValueSource` in `src/utils/providerProfile.ts`
so the profile-clean and secret-redact paths know about it.
- `src/utils/providerFlag.ts` `--provider <name>` startup flag now
detects a Cloudflare profile from `OPENAI_API_KEY ===
CLOUDFLARE_API_TOKEN` (mirrors how the other host-key mirrors are
reverse-mapped to their preset id).
- `bun run scripts/generate-integrations-artifacts.ts` regenerated
`integrationArtifacts.generated.ts` to include the cloudflare preset
+ route + vendor.
- Tests: `compatibility.test.ts` PRESETS list, new
`buildProfileSaveMessage` Cloudflare case in `provider.test.tsx`,
new `applyProviderProfileToProcessEnv` Cloudflare case in
`providerProfiles.test.ts`.
- Docs: README providers table row + `docs/advanced-setup.md` section
matching the MiMo / Mistral entries.
- Dedicated AI Gateway integration with `gateway_id` URL templating.
Today users can still paste a full Gateway URL into `OPENAI_BASE_URL`
and the preset's `matchBaseUrlHosts` picks `gateway.ai.cloudflare.com`
up.
- Dynamic `/models` discovery on the Groq #1143 / `mapModel` pattern —
Cloudflare's `/v1/models` returns the runnable model list and the
hybrid catalog path drops in cleanly. Left as a separate PR so this
one stays a focused preset add.
Closes #1100
* fix(cloudflare): narrow route matching to api.cloudflare.com host
`gateway.ai.cloudflare.com` is the shared host for *all* Cloudflare AI
Gateway routes (Workers AI, Anthropic, OpenAI, etc.), so matching it to
the Workers AI preset applied Workers-AI runtime metadata and
credential precedence (CLOUDFLARE_API_TOKEN before OPENAI_API_KEY, body
'store' strip, max_tokens field) to other providers' Gateway URLs.
Drop the shared host from the match list; a dedicated AI Gateway
integration with path-aware routing is the right follow-up.
Refs #1100.
* fix(provider-manager): keep Codex OAuth after DeepSeek when cloudflare added
The picker hardcoded `options.splice(7, 0, …)` to drop the Codex OAuth
entry right after DeepSeek. Adding cloudflare to ORDERED_PROVIDER_PRESETS
bumped DeepSeek to index 7, so the splice now lands Codex OAuth *before*
DeepSeek and breaks the test fixture that drives navigateToPreset by
keypress count.
Switch to a dynamic `findIndex('deepseek') + 1` lookup so any future
preset inserted between Bankr and DeepSeek keeps the established
ordering. Fixture updated to mirror the new picker order.
Caught by CI on 12b3ff… smoke-and-tests: 8 ProviderManager tests
timing out because navigateToPreset overshot/undershot the target.
* fix(cloudflare): exclude the shared AI Gateway host from Cloudflare routing
The profile env/alignment/startup paths mirrored CLOUDFLARE_API_TOKEN whenever
the profile URL merely contained 'gateway.ai.cloudflare.com'. That host is the
shared AI Gateway for all Cloudflare AI routes (Workers AI, OpenAI, Anthropic,
...), so a profile retargeted to /openai or /anthropic Gateway URLs was wrongly
tied to the Cloudflare route and credential precedence.
Add isCloudflareBaseUrl (hostname === api.cloudflare.com, matching the Workers
AI host and the descriptor's matchBaseUrlHosts) and route all three sites
through it, consistent with isXaiBaseUrl/isFireworksBaseUrl. Also restore
CLOUDFLARE_API_TOKEN in the provider profile test cleanup keys.
* fix(cloudflare): don't seed the placeholder base URL from the CLI shortcut
`openclaude --provider cloudflare` fell through the generic OpenAI-compatible
branch and applied the descriptor default base URL verbatim — including the
unresolved `<ACCOUNT_ID>` placeholder — leaving the shortcut 'configured' with
an endpoint that cannot serve a request. Skip seeding any base URL that still
contains a `<...>` placeholder, so the user must supply a real account-scoped
URL (OPENAI_BASE_URL / `/provider` edit) first, matching how the wizard treats
placeholder endpoints.
* test(cloudflare): assert exact null fallback for AI Gateway routes
The shared AI Gateway URL assertions used `.not.toBe('cloudflare')`, which
would also pass for any other non-cloudflare return value. The intended
fallback is null, so assert `.toBe(null)` to lock the regression boundary.
* fix(cloudflare): gate profile token mirroring on base URL host only
applyProviderProfileToProcessEnv mirrored CLOUDFLARE_API_TOKEN whenever
route.routeId === 'cloudflare'. route comes from the saved profile.provider,
so that disjunct is always true for a cloudflare profile, including one
retargeted to the shared gateway.ai.cloudflare.com AI Gateway host. The
sibling sites (isProcessEnvAlignedWithProfile, buildOpenAICompatibleStartupEnv)
already key on isCloudflareBaseUrl only; align this site with them so a
shared-gateway profile no longer leaks the token or stays pinned to the
cloudflare route. Add a regression test for the gateway.ai.cloudflare.com case.
* chore(integrations): regenerate artifacts for the Cloudflare vendor
The rebase took main's generated artifacts at the conflict; regenerate so the
Cloudflare vendor descriptor is registered in VENDOR_DESCRIPTORS and the
manifest alongside the providers main added.
* fix(cloudflare): mirror CLOUDFLARE_API_TOKEN into the OpenAI-compatible auth path
The --provider cloudflare shortcut fell through to the generic
OpenAI-compatible default branch and never copied CLOUDFLARE_API_TOKEN
into OPENAI_API_KEY, so a user who only set the token sent an
unauthenticated request. Add a dedicated cloudflare case that mirrors the
token (and clears a stale generic key when absent), keeping the
placeholder-URL skip.
buildOpenAICompatibleStartupEnv also returned from its strict-env branch
before the fallback CLOUDFLARE_API_TOKEN mirror, so a keyed Cloudflare
profile persisted a startup env that omitted the token and re-detected
inconsistently after relaunch. Mirror it in the strict branch alongside
nearai/fireworks. Add regression coverage for both paths.
* fix(cloudflare): gate token mirroring on a real Cloudflare endpoint
The cloudflare shortcut copied CLOUDFLARE_API_TOKEN into the generic
OPENAI_API_KEY unconditionally. The descriptor default carries an
unresolved `<ACCOUNT_ID>` placeholder and is never seeded, so with
OPENAI_BASE_URL unset (or still pointing at a previous OpenAI-compatible
provider) the token would be attached to the wrong host. Gate the mirror
on isCloudflareBaseUrl(getConfiguredOpenAIBaseUrl()) — only seed
OPENAI_API_KEY once the configured base URL resolves to
api.cloudflare.com, otherwise fail fast and leave it unset. Add
regression coverage for the unconfigured, stale-host, and AI-Gateway-host
cases.
* fix(cloudflare): reject placeholder URL and keep the OPENAI_API_KEY fallback
The token mirror keyed on the api.cloudflare.com host only, so the literal
<ACCOUNT_ID> placeholder URL (same host) passed the gate and copied the
token onto a non-working endpoint. It also deleted any generic
OPENAI_API_KEY when no token was set, breaking the documented
compatibility fallback for users authenticating a real Workers AI URL with
OPENAI_API_KEY. Mirror only on a real (non-placeholder) Cloudflare
endpoint, and preserve an existing generic key there when no dedicated
token is present.
Refs #1100
* refactor(cloudflare): model Workers AI as a gateway, not a vendor
Cloudflare Workers AI is a hosted OpenAI-compatible inference endpoint
reached over the shared openai transport, so it belongs with the gateway
providers (atlas-cloud, groq, together, ...) rather than the transport
vendors. Move it to gateways/cloudflare.ts via defineGateway (category
hosted, vendorId openai), regenerate the integration artifacts, and
allowlist its provider-specific @cf/* catalog ids in the gateway
descriptor check (no shared cross-provider descriptor exists, same as
azure-deployment).
Refs #1100
* fix(cloudflare): key Workers AI detection on the account path, not the host
api.cloudflare.com also serves the general Cloudflare REST API, so matching the
whole host treated unrelated URLs (e.g. /client/v4/user/tokens/verify) as the
Workers AI route and mirrored CLOUDFLARE_API_TOKEN into OPENAI_API_KEY for them.
isCloudflareBaseUrl now requires the Workers AI path
/client/v4/accounts/<account_id>/ai/v1 with a real (non-placeholder) account id,
and resolveRouteIdFromBaseUrl guards its cloudflare hostname match through the
same predicate. Both route detection and token/profile mirroring key on the
actual Workers AI endpoint.
Adds same-host negative regressions (general REST path is not routed and does
not mirror the token; unresolved <ACCOUNT_ID> placeholder is excluded) and
asserts the Cloudflare Workers AI preset appears in the first-run picker.
* fix(cloudflare): honor the Workers AI path boundary in the profile-provider fallback
resolveActiveRouteIdFromEnv returned the saved active-profile provider's route
id before consulting its base URL. For a `cloudflare` profile that had been
retargeted to a non-Workers URL — the shared AI Gateway host, or a general
api.cloudflare.com REST path — this still resolved as `cloudflare`, so the
Workers AI shim config (removeBodyFields: ['store'], Cloudflare model metadata)
and CLOUDFLARE_API_TOKEN mirroring were applied to a generic endpoint, even
though resolveRouteIdFromBaseUrl already excludes those URLs.
Gate the profile-provider shortcut through profileRouteHonorsBaseUrlBoundary,
which requires the path-aware isCloudflareBaseUrl for the cloudflare route (all
other routes are host-scoped by resolveProfileRoute and unaffected). A retargeted
profile now falls through to the generic openai/custom resolution; a genuine
Workers AI profile base URL still resolves as cloudflare.
Adds regressions for both retarget cases (gateway host + REST path) and the
positive Workers AI profile case.
* fix(cloudflare): require HTTPS and honor the Workers AI path in validation
isCloudflareBaseUrl accepted any scheme, so http://api.cloudflare.com/
client/v4/accounts/<id>/ai/v1 resolved as the cloudflare route and mirrored
CLOUDFLARE_API_TOKEN into OPENAI_API_KEY over cleartext. Require url.protocol
=== 'https:'.
Startup validation selected the Cloudflare target on host match alone, so a
non-Workers path like /client/v4/user/tokens/verify demanded Workers AI auth
instead of falling back to generic OpenAI validation. Gate the cloudflare
target on isCloudflareBaseUrl(request.baseUrl), mirroring the runtime route
resolver's path boundary.
* test(cloudflare): lock non-Workers path token boundary; fix stale host-only comments
The apply/persist paths already gate CLOUDFLARE_API_TOKEN mirroring on the
isCloudflareBaseUrl path predicate, but had no coverage for a same-host
non-Workers path (api.cloudflare.com/client/v4/user/tokens/verify) and the
comments beside the mirroring sites still described a host-only boundary.
Add negative apply and persist regressions asserting the token is not mirrored
or persisted for that non-Workers URL, and update the comments to describe the
real Workers AI path predicate instead of host-only matching.
* fix(cloudflare): fall back to a generic route for retargeted profiles
resolveProfileCapabilityRouteId returned the cloudflare capability route id for
any saved cloudflare profile whose base URL no longer resolves — including one
retargeted to gateway.ai.cloudflare.com or another OpenAI-compatible host. That
stripped generic capabilities (apiFormat, custom auth/request headers) from
profile sanitize/apply even though the runtime resolver runs such a profile as
a generic OpenAI-compatible route. Mirror the same isCloudflareBaseUrl boundary:
keep the cloudflare route only for the real Workers AI URL (or the unset
descriptor default) and fall back to 'custom' otherwise. Regression asserts a
retargeted cloudflare profile preserves OPENAI_API_FORMAT.
* test(cloudflare): assert retargeted profile resolves to the custom route
Pin both resolveActiveRouteIdFromEnv assertions for a retargeted cloudflare
profile to .toBe('custom') instead of .not.toBe('cloudflare'), so the test
locks the intended generic OpenAI-compatible fallback rather than merely
excluding the cloudflare route.
|
||
|
JATMN
|
e086e8c35a |
fix(safety): relax over-restrictive safety checks for benign coding tasks (#1897)
* fix(safety): relax over-restrictive safety checks for benign coding tasks (Fixes #1616) Issue #1616 reports refusals for routine, benign coding tasks. Two layers caused this: 1. Model-level over-refusal: CYBER_RISK_INSTRUCTION and the 'ask before acting' guidance biased the model toward refusing normal work. Reworded to explicitly permit ordinary engineering tasks and dual-use/security-adjacent work in authorized contexts, and to ask a clarifying question rather than refuse when intent is ambiguous. 2. Application-level heuristics that become hard blocks in auto/YOLO/headless mode: the bash command-injection check, the broad DANGEROUS_FILES/DANGEROUS_DIRECTORIES auto-edit guard, and the auto-mode stripping of ordinary interpreter allow-rules (Bash(python:*), npm run:*, etc.). Added an OPENCLAUDE_SAFETY_LEVEL knob (strict|balanced|permissive, default balanced). In 'permissive' the application-level heuristics above are relaxed while genuine Windows-path/symlink guards remain active. Default behavior is unchanged. Validation: - bun run typecheck: clean - bun run build: succeeds - bun test safetyLevel.test.ts, bashSecurity.safety.test.ts: pass - bashSecurity.test.ts, filesystem.test.ts, permissionSetup.test.ts, security-hardening.test.ts: pass (no regressions) * fix(safety): narrow permissive safety relaxations * fix(safety): address review follow-ups * fix(safety): address additional review findings * refactor(permissions): share rule normalization |
||
|
0xfandom
|
06e0ae6e0b |
feat(settings): per-model context_window and max_output_tokens overrides (#1234)
* feat(settings): per-model context_window and max_output_tokens overrides
Adds a `modelLimits` settings.json map so users can declare context window
and max output tokens for OpenAI-compatible models that are not in the
built-in catalog. Resolution order is env var → settings → catalog, so the
existing CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS / _MAX_OUTPUT_TOKENS env vars
keep priority. Keys are matched exactly, then by prefix, with optional
"<host>:<model>" host-qualified forms.
Example:
"modelLimits": {
"qwen3.6-plus": { "contextWindow": 1048576, "maxOutputTokens": 32768 }
}
Closes #478
* fix(model-limits): apply settings overrides in resolveModelRuntimeLimits
The settings.json `modelLimits` fallback was only wired into the scalar
getOpenAIContextWindow / getOpenAIMaxOutputTokens helpers. The runtime
resolution path (resolveModelRuntimeLimits) instead consumes the *Matches
variants, which only returned env-var matches — so a configured modelLimits
override never reached the model whose limits are actually resolved at
runtime, contrary to the documented env → settings → catalog order.
Fold the settings lookup into getOpenAIContextWindowMatches /
getOpenAIMaxOutputTokenMatches as a dedicated `settings` field, and insert it
between the exact env override and the built-in catalog in
resolveModelRuntimeLimits. Declare `modelLimits` on GlobalConfig so the lookup
is typed. Add an integration test that drives resolveModelRuntimeLimits and
asserts settings resolve for exact, host-qualified and prefix keys, and that an
env override still wins.
* fix(model-limits): resolve modelLimits from settings.json, not global config
readSettingsLimits read getGlobalConfig().modelLimits, which is ~/.openclaude.json
— a different file from the settings.json the feature is documented and schema'd
for (SettingsSchema in settings/types.ts). A user adding modelLimits to
settings.json saw no effect. Read it from getInitialSettings() (the merged
settings snapshot, session-cached) instead, and drop the now-unused modelLimits
field from GlobalConfig so the override lives in one place. Rewire both test
suites to a gated-passthrough getInitialSettings mock.
* test(model-limits): capture real settings module at load, not in beforeEach
The settings modelLimits suites re-imported the real settings module with
a cold dynamic import inside beforeEach. That import sat right at Bun's
default 5s hook timeout and intermittently failed the first test. Capture
the genuine module once via a top-level query-string-busted static import
so the cost moves to module load (no hook timeout) and the gated
passthrough still bypasses other suites' settings.js mocks. Also correct
the integration-test comment to name the helpers the runtime path
actually calls (getOpenAIContextWindowMatches / getOpenAIMaxOutputTokenMatches).
* fix(model-limits): keep env-prefix override above settings in runtime resolver
resolveModelRuntimeLimits ordered the settings `modelLimits` value above
the env-prefix match, so a broad env-prefix override (e.g.
`{"my-custom":N}`) was silently overtaken by a more specific settings
entry (`my-custom-deployment`). The scalar getOpenAIContextWindow treats
env (exact ?? prefix) as strictly higher priority than settings; mirror
that in the runtime resolver: env.exact, then env.prefix, then settings,
then catalog/cache/descriptor. Regression covers both contextWindow and
maxOutputTokens.
* docs(model-limits): document the settings.json modelLimits override
Add a user-facing section near the env-var overrides covering the
modelLimits map, JSON shape, exact/prefix/host-qualified key matching, and
the env > settings > catalog > descriptor precedence.
* fix(model-limits): keep catalog above env-prefix in runtime precedence
The previous reorder put the env-prefix match above the catalog value,
which broke the existing invariant that a `:cloud` catalog variant takes
its known catalog limit rather than inheriting a broad base-model env
prefix (deepseek-v4-pro:cloud regressed to 262144). Correct order:
exact env -> catalog/cache -> env prefix -> settings -> descriptor. This
still keeps settings strictly below env-prefix (the original drift fix)
while preserving catalog precedence over prefix. Docs precedence updated
to match.
* docs(advanced-setup): document CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS env var
The modelLimits section referenced the max-output env var but the
Environment Variables table only listed the context-window one, leaving
output-only configuration undocumented. Add the matching table row.
Refs #478
* docs(model): align openaiContextWindows precedence comments with the resolver
The module header and the OpenALimitOverrideMatches.settings comment claimed a
resolution order of "env → settings → catalog", which contradicts
resolveModelRuntimeLimits (exact env → catalog/discovery cache → prefix env →
settings modelLimits → descriptor default). Since this module only produces the
override candidates and does not own the precedence, narrow the comments to say
so and point at runtimeMetadata.ts as the authoritative chain, so this
precedence-sensitive code isn't misread when touched again.
* fix(model): rank host-qualified modelLimits keys above bare model keys
lookupByModel grouped all exact matches (host-qualified and bare) ahead of all
prefix matches, so a bare exact key like `qwen3.6-plus` beat a host-qualified
prefix like `openrouter.ai:qwen3`. That defeated the advertised per-endpoint
disambiguation for versioned model families. A host-qualified key is strictly
more specific than a bare one, so rank both host-qualified forms (exact and
prefix) in the high-priority tier ahead of the bare exact match, leaving only
the bare prefix in the low-priority tier.
* fix(model): keep an exact modelLimits key ahead of any host-qualified prefix
The previous commit ranked host-qualified PREFIX matches above bare exact
matches, which broke the deliberate precedence in context.test.ts: an exact
`gpt-4o` limit was overridden by an unrelated `api.foo.com:gpt-4` prefix that
only matches a shorter, different model name.
Restore the tiering so an exact match (host-qualified or bare) always beats a
prefix, and a host-qualified key beats a bare key WITHIN the same match kind.
The supported way to set a different limit for the same model per endpoint is a
host-qualified EXACT key. Narrow the regression + comment to that behavior.
* docs(model): align modelLimits matching wording with exact-over-prefix rule
Narrow the advanced-setup wording so a host-qualified key only wins over a bare
key within the same match kind (a bare exact key still beats a host-qualified
prefix), matching lookupByModel's exact ?? prefix behavior; per-endpoint limits
for the same model need host-qualified exact keys. Also note modelLimits as part
of the documented user-override layer in the integration add-model and
common-pitfalls guides.
* docs(model): clarify modelLimits host-port key and catalog/cache precedence
Spell out that the host-qualified key uses new URL(baseUrl).host — including the
port when present (localhost:4000:my-model, not localhost:my-model) — and split
the precedence line so the built-in catalog is shown as checked before the
discovery-cache value, matching resolveModelRuntimeLimits.
|
||
|
0xfandom
|
db01038d5c |
feat(model-picker): surface inactive provider profiles in /model (#1119 piece 2) (#1164)
* feat(model-picker): surface inactive provider profiles in /model When a user configures multiple providerProfiles (Kimi + Z.AI + OpenRouter + SambaNova in the #1119 repro, but the pattern fits any multi-provider setup), switching the main session between them currently requires round-tripping through /provider — /model only shows the active profile's models. Make /model the single switcher: - ModelOption gains an optional `switchToProfileId`. Existing options leave it unset and behave exactly as today. - `getInactiveProviderProfileOptions` enumerates every configured profile that isn't the active one and emits a picker entry per model, labelled `<model> · <profile.name>` so the user can see the choice changes providers, not just models. - Each option's `value` is encoded with `__switch_profile__:<id>:<model>` so the picker's plain-string `value` channel stays the source of truth and same-named models under different base URLs (`gpt-4o` on multiple OpenAI-compatible endpoints) stay disambiguated. - /model's handleSelect detects the prefix, calls `setActiveProviderProfile` (same path /provider uses — applies env, persists active profile, refreshes startup file), then sets `mainLoopModel` to the bare model string. Only surfaces inactive options when `CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED` is set, so users who haven't opted into the multi-profile workflow at all don't see the affordance. Tests cover round-trip encoding (including OpenRouter-style colon-bearing model strings), the active-filter, the multi-model explosion, and that `getModelOptions()` 3P path includes the inactive options only when the profile env is applied. Combined invocation with the rest of `src/utils/model/` + `src/commands/model/` + `src/utils/providerProfiles.test.ts` runs clean to guard against mock-leak (per the 2026-04-30 lesson — spreads `import * as actual` for every `mock.module` factory). Refs #1119 * fix(model-picker): run fast-mode cleanup on cross-profile switch The new switch-profile branch returned before reaching the fast-mode reconciliation, so a user with fastMode latched on Anthropic Opus could switch to an OpenAI profile and silently keep fastMode on even though the new model can't support it. Extract the cleanup into a pure helper `reconcileFastModeForSwitch` and call it from both branches. Refs #1119. * fix(model-picker): decode cross-profile values before effort/display lookup Inactive-profile entries encode the picker value as `__switch_profile__:<profileId>:<model>`, but `resolveOptionModel` forwarded the raw string straight to `parseUserSpecifiedModel`. For a reasoning-capable cross-profile entry such as `gpt-5.4`, `modelSupportsEffort()` then saw the prefixed string and reported "Effort not supported", and `handleSelect` dropped the toggled effort even when the underlying model accepts it. Run `parseSwitchProfileValue` first; when it matches, hand the bare target model to `parseUserSpecifiedModel` so effort capability, default-effort lookup, and display-name resolution all key off the real model id. * fix(model-picker): include inactive profiles on local OpenAI-compatible scope The inactive-profile compute lived after the `getAdditionalModelOptionsCacheScope()?.startsWith('openai:')` early return, so users with a local OpenAI-compatible profile active (Ollama, lm-studio, any localhost endpoint) never saw the cross-profile switcher in `/model`. They still had to round-trip through `/provider` to change profile. Hoist `profileEnvApplied`, the active-profile lookup, and `getInactiveProviderProfileOptions(activeProfileId)` above the early return, and append `inactiveProfileOptions` to the local-OpenAI branch return value. Other branches (Claude.AI, MiMo, MiniMax, ant) were already either irrelevant or have their own gating. Test: new regression in modelOptions.crossProfile.test.ts pins `getAdditionalModelOptionsCacheScope` to an `openai:` value and confirms the inactive profile still surfaces with a parseable `__switch_profile__` value. * fix(model-picker): apply the allowlist to the decoded cross-profile model filterModelOptionsByAllowlist evaluated cross-profile options by their encoded __switch_profile__:<id>:<model> value, so an availableModels allowlist that permits the bare target (e.g. glm-5.1) dropped every inactive-profile entry. Check the allowlist against parseSwitchProfileValue(value)?.model ?? value, and cover both the allowed and denied cases. * fix(model-picker): only surface cross-profile switch options on the /model path The inactive-profile entries come from the shared getModelOptions() list, but only the /model command's onSelect decodes __switch_profile__ values and activates the target profile. The prompt hotkey and Settings pickers wrote the encoded value straight to mainLoopModel, sending an invalid model string. Gate these options behind a new allowProfileSwitch prop that only the /model command sets; inline pickers no longer surface an option they cannot honor. Also apply the org allowlist to the decoded target model in the /model select handler. * test(model-picker): drop flaky cross-profile allowlist case The decoded-allowlist assertion drove the org allowlist through the shared session settings cache, which is racy across bun's single-process run and could leak availableModels into sibling suites (the providerConfig cache-scope tests went red in CI). The decode itself is a one-line guard already exercised by the parseSwitchProfileValue round-trip coverage, so remove the unreliable case rather than ship CI flake. Also snapshot the real provider/auth modules before mocking so each harness call rebuilds its mock from a clean base instead of a previous test's overrides (bun live-repoints the imported namespace to the active mock). * test(model-picker): stop cross-profile mocks leaking into provider suites The cross-profile tests mock.module'd ../providerProfiles, ./providers, ../auth and ../../services/api/providerConfig per test. bun's mock.module is process-wide and mock.restore() does not undo it, so these persisted into later files — most damagingly the providerConfig mock, which replaced the module with a single-function stub and stripped resolveProviderRequest / getAdditionalModelOptionsCacheScope from providerConfig.local's suite (now adjacent after the rebase onto #1706). Install each mock once at module load, keep the full export surface, and gate the overrides on module-level flags cleared in beforeEach/afterEach so the persisted mocks are transparent passthroughs for every other suite. Same pattern as the cross-spawn / install-surfaces leak fixes. * fix(model): reconcile fast mode before activating the switched profile In the cross-profile /model switch path, reconcileFastModeForSwitch ran after setActiveProviderProfile. The reconciler gates on isFastModeEnabled(), which reads the *active* provider — so once the target profile is activated it reflects the new (fast-mode-less) provider and short-circuits to 'unchanged', leaving fastMode latched on for a model that can't use it. Compute the reconciliation before activating the profile, so it evaluates against the source provider and correctly returns 'off' for an unsupported target. Add a command-level regression test that drives handleSelect with a __switch_profile__ value while setActiveProviderProfile flips the fast-mode state, and asserts fastMode is set to false (it fails if the call order regresses). * fix(model): re-check fast mode after activating a switched profile The pre-activation reconcile gates on the source provider, so its 'on' result is stale when the target provider cannot run fast mode even though the target model name passes the source-side support check (e.g. a third-party shim exposing a claude-opus-* model). Re-evaluate isFastModeEnabled / supported / available after setActiveProviderProfile and force fastMode off when it is no longer genuinely supported. Add a command-level regression test for that path and wrap the cross-profile test cleanup in try/finally so a failing assertion still unmounts the Ink instance (jatmn review, #1119). * test(model-picker): cover cross-profile allowlist with isolated settings Re-add the regression dropped in 06a0c80: filterModelOptionsByAllowlist must evaluate the allowlist against the decoded target model, not the encoded __switch_profile__ wrapper. Uses this suite's per-test settings cache (reset in afterEach) instead of the shared cache that made the earlier version flaky (jatmn review, #1119). * test(model-picker): make the cross-profile allowlist test leak-proof The new allowlist test drove availableModels through setSessionSettingsCache, but sibling suites (ModelPicker, ProviderManager, ...) mock.module both settings.js (getSettings_DEPRECATED) and modelAllowlist.js (isModelAllowed) process-wide, so in the full sequential run the leaked stubs defeated the cache and the denied option was not filtered (smoke-and-tests red on the full suite, green in isolation). Drive the allowlist deterministically from this suite instead: install-once, gated, passthrough mocks of getSettings_DEPRECATED (the filter gate) and isModelAllowed (the per-option check), both keyed off a single activeSettingsOverride and cleared in afterEach. Same gated-passthrough pattern as the suite's existing providerConfig/providers/auth/profiles mocks and the agent.test.ts allowlist approach. * fix(model): keep cross-profile switch options out of the SDK models list getModelOptions() now returns inactive-profile entries encoded as __switch_profile__:<id>:<model>. print.ts mapped those straight into the ModelInfo list returned to SDK/web callers, exposing UI-only values that are not selectable model ids. Filter them with parseSwitchProfileValue before building modelInfos. Add ModelPicker coverage for the allowProfileSwitch filter (hidden inline, shown when allowed) and document cross-profile /model switching in the provider-profile docs. * test(model-picker): prove cross-profile switch options never reach SDK models Extract selectSdkModelOptions as the single gate the SDK modelInfos builder runs every getModelOptions() entry through, and cover it directly: an encoded __switch_profile__:<id>:<model> option is dropped while real model ids pass through. Fails if an inactive-profile affordance ever leaks into the initialize.models response again (#1119). * docs(model-picker): clarify the env gate for inactive-profile entries The inactive-profile models only appear when the provider-profile env workflow is active (CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED=1), not for every multi-profile setup. Spell that out and restore the local-only `--provider ollama` guidance that was folded into the paragraph. * fix(model-picker): gate SDK option filter on switchToProfileId marker selectSdkModelOptions filtered on the encoded __switch_profile__ value prefix, which also reserved that prefix for every custom model id. A real configured model whose id starts with __switch_profile__: would vanish from the SDK models response and non-switching pickers. Key the gate on the explicit switchToProfileId marker, which only synthesized switch options carry, and add the collision regression. Refs #1119 * fix(model-picker): reuse switch confirmation for cross-profile selections The cross-profile branch built its own "Switched to" message and returned before the regular path appended the selected effort and the "Billed as extra usage" notice, hiding cost-impacting feedback when a reasoning/extra-usage target was chosen through an inactive profile. Append effort and the extra-usage check to the switch confirmation. Refs #1119 * fix(model-picker): surface inactive profiles on the active Ollama path The isOllamaProvider() early return ran before the inactive-profile options were computed, so an active local Ollama profile saw only its own models and lost the cross-profile switcher, forcing the /provider round-trip this feature removes. Hoist the inactive-profile compute above the Ollama branch and append it to the Ollama returns. Refs #1119 * fix(model): surface inactive profiles on all provider branches; decode only real switch options Two follow-ups to the #1119 unified /model switcher: - inactiveProfileOptions was computed before the early-return branches but only appended on Ollama / local-scope / PAYG paths. The GitHub Copilot, NVIDIA NIM, MiniMax, Xiaomi MiMo, ant, and Claude-subscriber branches returned first, so a user with a saved profile active on any of those routes lost the cross-profile entries and had to round-trip through /provider. Append the (env-gated, so empty unless a profile is applied) inactive options on those branches too. - filterModelOptionsByAllowlist decoded any value starting with `__switch_profile__:` via parseSwitchProfileValue, even a normal custom model id that merely shares that prefix, evaluating the allowlist against the wrong inner model. Gate the decode on the `switchToProfileId` marker (the type's documented contract) so non-switch ids are checked verbatim. Extends the cross-profile harness with gated getAPIProvider / NVIDIA / subscriber overrides and adds branch-append + verbatim-allowlist regressions (red-green). * fix(model): key profile-switch handling on the marker across picker and command The allowlist/SDK paths already used the switchToProfileId marker, but two surfaces still keyed on the raw `__switch_profile__:` value prefix: - ModelPicker's inline-picker filter hid any option whose value started with the prefix, so a real custom model id like `__switch_profile__:vendor:gpt-5.4` disappeared from prompt/settings pickers. It now filters on `switchToProfileId === undefined`. - the /model command decoded parseSwitchProfileValue(model) for any prefixed string and tried to activate the encoded profile id, so selecting such a custom model activated a nonexistent profile instead of setting the literal model. It now only treats the value as a switch when the decoded profile id maps to a real configured provider profile — which every synthesized switch option does, and a prefix-colliding custom id does not. Drops the now-unused SWITCH_PROFILE_VALUE_PREFIX import from ModelPicker. Adds a picker regression (marked switch hidden, prefixed custom model stays visible) and completes the cross-profile branch coverage (MiniMax, Xiaomi MiMo, ant) so every branch that appends inactive-profile options is locked. * test(model): register target profiles in cross-profile switch tests The /model command now only treats a `__switch_profile__:` value as a switch when its decoded profile id maps to a real configured provider profile. The cross-profile switch tests set up setActiveProviderProfile but left the shared getProviderProfiles mock empty, so the new guard classified their switch values as literal models and the fast-mode / effort / extra-usage assertions no longer ran. Register each test's target profile via getProviderProfiles so the switch path executes as intended. * fix(model): gate cross-profile switches on the selected option marker Selecting a value that merely parses as `__switch_profile__:<profileId>:<model>` activated the provider whenever <profileId> existed, so a literal custom model id such as `__switch_profile__:profile_openai:gpt-5-mini` wrongly switched the active provider instead of being applied verbatim. Thread the picked option's `switchToProfileId` marker from ModelPicker.onSelect (selectOptions already carries it) and only activate a profile when the marker matches the decoded id. The effort/display resolver had the same gap — it decoded every prefixed value; gate it on a genuine marker-backed switch option too. Add a regression asserting a marker-less prefixed id is applied literally. * test(model): cover Max/Team Premium and empty-catalog switch-append paths The cross-profile branch-coverage suite exercised the populated-catalog returns but not the Max/Team Premium subscriber early return nor the empty-catalog fallbacks (NVIDIA/MiniMax/Xiaomi), which are the same paths that previously dropped the inactive-profile switch options. Lock them so every changed return that appends `...inactiveProfileOptions` is covered. * fix(model): keep inactive-profile switch options in /model discovery overrides The interactive /model command passes an optionsOverride into ModelPicker for descriptor-backed and legacy OpenAI-compatible discovery contexts, built from mergeActiveProfileModelOptions which only merges the ACTIVE profile's route models. Because the picker renders optionsOverride ?? getModelOptions(), the inactive-profile switch entries getModelOptions() appends never reached those paths, so the unified switcher vanished for provider-profile routes (OpenRouter/Kimi/MiniMax, refreshed local profiles). Re-append the same inactive-profile switch options (allowlist-filtered on the decoded target) to any override list before handing it to the picker. * fix(model): base the switch marker on the presented option, treat ties as ambiguous The picker derived switchToProfileId with selectOptions.find(value===...), and the effort/display resolver decoded when any getModelOptions() entry with the same value carried the marker. If a literal custom model id collided with an encoded switch value, the literal could borrow a different same-value option's marker and wrongly activate a provider. Add resolveSelectedSwitchProfileId, which keys on the actual presented option and treats duplicate-value matches as ambiguous (no switch), and route both the onSelect marker and the decode decision through it. |
||
|
Kevin Codexandjatmn
|
2edec9a140 |
fix(deps): ship a zero-warning, minimal install (#1784)
* fix(deps): ship a zero-warning, minimal install
The published package declared 62 runtime `dependencies`, but `dist/cli.mjs`
is a fully-bundled esbuild output that inlines almost all of them. End users
therefore installed ~476 transitive packages — including three subtrees the
bundle never needs at install time, each emitting an install warning:
- node-domexception (deprecated) via google-auth-library
- protobufjs (allow-scripts) via @grpc/* (already bundled into dist)
- sharp (allow-scripts) native image module
The repo's `overrides`/`allowScripts` silence these locally, but those are
root-only npm settings and are ignored when the package is installed as a
dependency — so end users saw the warnings.
Core changes:
- package.json: runtime dependencies trimmed 62 -> 3 (@orama/orama,
@orama/plugin-data-persistence, @vscode/ripgrep). Bundled packages, plus
the optional sharp/google-auth-library, move to devDependencies so they
are built/tested but not shipped.
- package.json: @anthropic-ai/sdk, @modelcontextprotocol/sdk, react and
react-reconciler declared as OPTIONAL peerDependencies — externalized by
the ./sdk bundle but bundled into the CLI. Optional peers keep the CLI
install minimal and warning-free while still resolving for ./sdk consumers.
- externals.ts: sharp, google-auth-library and @anthropic-ai/bedrock-sdk
marked OPTIONAL_RUNTIME_EXTERNALS (loaded on demand, not shipped).
- validate-externals.ts: runtime deps validate against externals; bundled
deps validate against dependencies + devDependencies.
- client.ts: load @anthropic-ai/bedrock-sdk via the runtime importer so
esbuild no longer inlines it and hoists its static @aws-sdk import into
the CLI bundle (that was a startup crash for default installs).
Optional-dependency UX (consistent, actionable errors):
- New src/utils/optionalRuntimeModule.ts exports importRuntimeModule and
importOptionalRuntimeModule. The optional variant translates a missing
package (code === 'ERR_MODULE_NOT_FOUND', specifier present in message)
into "<feature> requires "<pkg>" ... Run `npm i -g <pkg>`". Generic so
typed call sites keep their module types.
- Routed ALL optional-package load sites through it (previously only one
did): google-auth-library (client.ts, auth.ts, geminiAuth.ts),
@anthropic-ai/foundry-sdk + @azure/identity (client.ts), and the
@aws-sdk/* Bedrock paths (model/bedrock.ts, tokenEstimation.ts, aws.ts).
- imageProcessor.ts: sharp-missing error now says `npm i -g sharp`.
- docs/advanced-setup.md: new "Optional provider packages" table and a
Vertex note documenting the on-demand installs.
- Unit test for the helper (friendly error, success path, specifier match,
raw passthrough).
- knip.json: ignore google-auth-library (now loaded via runtime string).
Verified on the current tree:
- tsc, build/validate-externals, knip, and tests all pass.
- npm pack + install --omit=dev adds 8 packages, zero deprecation/
allow-scripts/funding warnings; --version/--help/mcp list run.
- With packages absent, CLAUDE_CODE_USE_BEDROCK and CLAUDE_CODE_USE_VERTEX
print the friendly `npm i -g <pkg>` error (verified end-to-end).
- ./sdk imports once its optional peers are present (24 exports, no warns).
- Bundled ajv + ajv-formats validate with no ajv installed; no unguarded
native runtime requires (fsevents absent in chokidar 4; bun:sqlite Bun-only).
Trade-off: image reads, AWS Bedrock, Azure Foundry and GCP/Vertex now prompt
a one-time `npm i -g <pkg>` instead of being shipped to every user.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
Review fixes (CodeRabbit + jatmn):
- validate-externals: the INTENTIONALLY_BUNDLED exemption is now scoped per
bundle. The CLI exempts every bundled package; the SDK does NOT exempt
packages declared as peerDependencies (keyed on package.json, an independent
source of truth) so dropping react/@anthropic-ai/sdk from SDK_EXTERNALS now
fails validation instead of silently passing. Added an explicit minimal-
install contract check: bundled packages must be devDependencies-only — never
in `dependencies`, and only the SDK-external subset may be optional peers.
Validation logic extracted to scripts/externalsValidation.ts + tests.
- FileReadTool oversized-image fallback now loads via the shared
getImageProcessor() (not a raw import('sharp')) and re-throws
ImageProcessorUnavailableError, so a missing processor surfaces the
`npm i -g sharp` install hint instead of returning an over-budget image.
- optionalRuntimeModule: match the missing specifier as a QUOTED token, not a
raw substring, so a missing transitive package whose name contains the
requested one (sharp vs sharp-libvips, @aws-sdk/client-bedrock vs
@aws-sdk/client-bedrock-runtime) no longer triggers the wrong install hint.
Predicate extracted to isMissingSpecifierError() with regression tests.
- docs/advanced-setup.md: the Vertex auth section now shows both documented
paths (gcloud ADC and a GOOGLE_APPLICATION_CREDENTIALS service-account file).
Review fixes (round 2, CodeRabbit):
- validate-externals: assert the optional-peer install contract — every
peerDependency must be { optional: true } in peerDependenciesMeta
(validateOptionalPeers), so losing that flag fails the build instead of
silently reintroducing install warnings.
- validate-externals: hard-check OPTIONAL_RUNTIME_EXTERNALS placement
(validateOptionalRuntimeexternals). Anything esbuild can see statically must
stay external in BOTH bundles (dropping sharp/google-auth-library now fails);
the runtime-indirection-only subset (new RUNTIME_INDIRECTION_ONLY_EXTERNALS)
must stay OUT of externals so esbuild never re-exposes their static imports.
- Deeper-dig fix: @anthropic-ai/foundry-sdk was misclassified as
INTENTIONALLY_BUNDLED, but it is loaded only through the Function indirection
(esbuild never sees it, so it was never actually bundled) — its sole presence
in dist is the specifier string. Per the PR's own "Azure Foundry now prompts"
trade-off it is on-demand, so it now lives in OPTIONAL_RUNTIME_EXTERNALS +
RUNTIME_INDIRECTION_ONLY_EXTERNALS (mirroring bedrock-sdk). sandbox-runtime is
genuinely statically imported, so it stays bundled.
- Provider-routing coverage (scripts/optionalRuntimeSpecifiers.test.ts): a
static scan asserts every importOptionalRuntimeModule specifier is a declared
OPTIONAL_RUNTIME_EXTERNAL and never also INTENTIONALLY_BUNDLED — the
invariant that keeps a provider's optional package loadable on demand.
- All new validators extracted to scripts/externalsValidation.ts with tests.
Review fixes (round 3, CodeRabbit):
- client.ts: gate the Vertex google-auth-library import behind the non-skip
branch. CLAUDE_CODE_SKIP_VERTEX_AUTH (proxy/test) uses a mock GoogleAuth and
must not require the optional package; it was loaded unconditionally before.
- optionalRuntimeModule: drop the hard-coded `npm i -g`. The helper backs both
the global CLI and project-local ./sdk consumers, so the hint is now
context-neutral ("npm install <pkg>" / add -g for the global CLI).
- validate-externals: every SDK_ONLY_EXTERNALS entry must STAY a
peerDependency (a dropped peer leaves runtimeDeps while the SDK still
externalizes it); and OPTIONAL_RUNTIME_EXTERNALS must never be shipped (fail
on overlap with dependencies/peerDependencies). Both with tests + live-verified.
- optionalRuntimeSpecifiers.test: pin the EXACT set of optionally-loaded
specifiers instead of a >=5 count (a count passes even if a provider path
regresses).
- attachments: extract tryReadEditedImageAttachment() — background watched-file
image attachments DEGRADE to null on any failure (incl.
ImageProcessorUnavailableError) so a missing optional package never aborts a
turn, while the explicit FileReadTool path still surfaces the install hint.
Deterministic regression test (bad path -> null).
- docs: Bedrock row notes profile-based auth also needs
@aws-sdk/credential-providers; install-hint wording matches the new message.
Review fixes (round 4, CodeRabbit):
- attachments: stop sending the raw file path through the analytics
bypass-cast (tengu_watched_file_compression_failed). Send only the safe
file extension via getFileExtensionForAnalytics, matching the existing
tengu_file_read_dedup pattern, so no usernames/project paths can leak.
- externals.ts: corrected the OPTIONAL_RUNTIME_EXTERNALS header comment,
which still claimed all entries "remain in COMMON_EXTERNALS" — no longer
true since the indirection-only subset (bedrock/foundry) must stay OUT of
the externals lists.
(Other CodeRabbit comments on this push re-surface items already addressed in
prior commits: the peerDependenciesMeta-optional check (validateOptionalPeers),
the SDK-peers-present and optional-not-shipped validator rules, the
exact-specifier-set test, the attachments degrade contract + test, and the
context-neutral install hint are all present. The "assert every optional
external is a devDependency" suggestion is intentionally NOT applied: @aws-sdk/*
and @azure/identity are transitive devDeps via bedrock-sdk/foundry-sdk, so a
blanket assertion would be incorrect; source resolution is covered by the
build + tests that import these packages.)
Review fixes (round 5, CodeRabbit):
- attachments: stop leaking file paths via logError in the background-image
degrade path. readImageWithTokenBudget can throw path-bearing messages
(e.g. "Image file is empty: <path>") and logError persists message/stack, so
log only the error TYPE name now. (Analytics payload was already sanitized.)
- attachments: tryReadEditedImageAttachment takes an injectable reader so the
degrade contract is tested for the EXACT error types — ImageProcessorUnavailableError
and a path-bearing read error both degrade to null (not just ENOENT) — plus a
success case. No mocking.
- validate-externals: enforce the source-install half of the optional contract.
Non-transitive OPTIONAL_RUNTIME_EXTERNALS must be devDependencies so `bun
install` source builds resolve them. The new TRANSITIVE_OPTIONAL_EXTERNALS
documents the exemption (@aws-sdk/* via @anthropic-ai/bedrock-sdk, @azure/identity
via @anthropic-ai/foundry-sdk — provided transitively, not direct devDeps). A
blanket "all optionals are devDeps" check would have wrongly failed on those.
Tests + live-verified (dropping sharp from devDependencies now fails).
Review fixes (round 6, CodeRabbit + jatmn):
- optionalRuntimeSpecifiers.test: the call-site scan regex missed
generic-annotated calls (importOptionalRuntimeModule<...>(...)) in
model/bedrock.ts and tokenEstimation.ts, so the exact-set assertion was
incomplete. Regex now allows an optional generic; EXPECTED_SPECIFIERS adds
@aws-sdk/client-bedrock and @aws-sdk/client-bedrock-runtime (7 total).
- importOptionalRuntimeModule default generic is now <T = unknown> (was any),
so destructured imports are no longer silently any. Every call site now
supplies its module type — typeof import('<pkg>') where the package is
type-resolvable (bedrock-sdk, foundry-sdk, @aws-sdk/credential-providers,
google-auth-library), and a named minimal-shape alias for @azure/identity
(not a direct devDep, so typeof import can't resolve it). This gives
compile-time verification of each provider's module contract (export names,
shapes) — the structural answer to the "cover the provider branches" ask.
- attachments: tryReadEditedImageAttachment takes injectable {read,log,track};
a new test asserts the sanitized-telemetry contract directly — the logError
payload is path-free and the analytics payload carries only `ext`, never the
edited-image path.
* fix(deps): address optional runtime review findings
* test(deps): isolate optional runtime importer mocks
* fix(deps): clarify AWS optional auth labels
* fix(deps): close optional runtime review gaps
---------
Co-authored-by: jatmn <the@jat.mn>
|
||
|
JATMN
|
cd13a61537 |
fix(memory): recover from autocompact overflow failures (#1858)
* fix(memory): recover from autocompact overflow failures * fix(memory): address autocompact review findings * fix(memory): close autocompact recovery gaps * fix(memory): reduce OpenAI conversion pressure * test(memory): add long-session guard smoke * fix(memory): add runtime memory guard diagnostics * fix(memory): surface autocompact failure diagnostics * fix(memory): reuse hard-cap resolver in diagnostics * fix(memory): avoid hard-cap diagnostic drift * fix(memory): clarify hard-cap diagnostics |
||
|
Bogdan
|
5226fb9ee7 |
fix(query): configure hard max and abort reasons (#1850)
* fix(query): configure hard max and abort reasons * fix(query): normalize legacy abort reasons * test(query): dedupe abort classification setup |
||
|
Bogdan
|
8182a46441 | feat(report): render task reports as markdown (#1826) | ||
 JATMNandjatmn
|
259c7ec27a |
fix(ollama): preserve chat history with native context (#1805)
* fix(ollama): preserve chat history with native context Route Ollama chat requests through the native /api/chat endpoint so OpenClaude can send request-level options.num_ctx instead of relying on Ollama's OpenAI-compatible shim. Default the Ollama request context to 32768 tokens, support OPENCLAUDE_OLLAMA_NUM_CTX and OLLAMA_CONTEXT_LENGTH overrides, and map max tokens/temperature/top_p into native Ollama options. Adapt native Ollama streaming and non-streaming responses back into the existing OpenAI-shaped conversion pipeline, including usage, text, structured tool calls, and tool_use stop reasons. Normalize native Ollama request messages for images and historical tool calls, avoiding OpenAI-only image_url/id/type payload fields in /api/chat requests. Add Ollama context diagnostics, loopback-only ollama ps status checks, regression coverage, and documentation for verifying active context length. * fix(ollama): address native routing review feedback * fix(ollama): restrict loopback host matching * fix(ollama): exclude wildcard bind address * fix(ollama): keep https localhost proxies on chat completions --------- Co-authored-by: jatmn <12479882+jatmn@users.noreply.github.com> |
||
|
Bogdan
|
a47493342f |
feat(report): generate deterministic session task reports (#1802)
* feat(report): generate deterministic session task reports * fix(report): address task report review findings * fix(report): stabilize task report paths on Windows * test(report): expect redacted git metadata cwd * test(report): assert literal redacted git cwd * fix(report): capture PowerShell and backgrounded validations * fix(report): detect quoted validation commands * fix(report): reconcile background validation notifications * fix(report): keep foreground command statuses authoritative * test(report): assert command status precedence |
||
|
JATMN
|
dd4c4abc81 |
feat(api): add OpenAI-compatible credential pool failover (#1706)
* feat(api): rotate OpenAI credential pools * fix(api): align pooled credential discovery * fix(cache-probe): preserve GitHub credential precedence * fix(provider): honor pooled OpenAI fallbacks * fix(provider): validate pooled profile credential labels * fix(api): harden OpenAI credential pool handling Reject placeholder values in pooled OpenAI credentials before requests, discovery, diagnostics, and profile generation can use them. Normalize pooled credentials to a single usable key for model discovery, runtime cache partitions, cache probing, and NVIDIA NIM cache lookups. Preserve documented profile precedence by letting live shell credentials override saved pools, carrying OpenCode fallback pools through launch, and redacting individual pool members in profile display. Add regression coverage for pooled credential validation, profile launch/rebuild behavior, discovery/cache callers, diagnostics, provider autodetect, and shim failover semantics. * fix(provider): cover pooled key recommendation path Import the pooled OpenAI credential validator in provider-recommend and split invalid credentials from unset credentials in user guidance. Add a script-level regression that runs the OpenAI recommendation path with OPENAI_API_KEYS so the ts-nocheck script cannot regress with runtime ReferenceErrors. Scrub pooled OpenAI keys before xAI OAuth profile env construction and loosen the invalid-pool discovery test to assert auth header absence instead of exact header shape. * fix(tests): stabilize rebased provider checks * fix(provider): address pooled credential review findings * test(api): cover opencode go credential failover * fix(provider): share OpenAI credential usability checks * fix(provider): respect pooled credential precedence * fix(model): preserve pooled discovery credential precedence * fix(model): fall back from unusable pooled discovery keys |
||
|
euxaristia
|
38b0e27333 |
fix(opencode-go): sync model catalog with opencode.ai/go (#1745)
* fix(opencode-go): sync model catalog with opencode.ai/go The OpenCode Go subscription page (https://opencode.ai/go) lists 13 models, but the catalog had 20. Remove the 7 models no longer offered: glm-5, kimi-k2.5, minimax-m2.5, qwen3.5-plus, mimo-v2-pro, mimo-v2-omni, hy3-preview. Catalog now matches the page exactly: - OpenAI-compatible: GLM 5.2, GLM 5.1, Kimi K2.7 Code, Kimi K2.6, DeepSeek V4 Pro, DeepSeek V4 Flash, MiMo V2.5 Pro, MiMo V2.5 - Anthropic messages: MiniMax M3, MiniMax M2.7, Qwen3.7 Max, Qwen3.7 Plus, Qwen3.6 Plus Updates gateway catalog, model descriptors, generated artifacts, and tests. * fix(opencode-go): reorder model catalog to match opencode.ai/go listing Reorder both the gateway catalog and model descriptor lists to match the order models appear on https://opencode.ai/go, so the in-app model picker mirrors the subscription page. No model added or removed — purely a reorder. GLM-5.2 → Qwen3.7 Max → Kimi K2.7 Code → MiMo V2.5 Pro → DeepSeek V4 Pro → Qwen3.7 Plus → MiniMax M3 → MiMo V2.5 → DeepSeek V4 Flash → GLM 5.1 → Kimi K2.6 → Qwen3.6 Plus → MiniMax M2.7 * test(opencode-go): assert exact model set matches opencode.ai/go catalog Address CodeRabbit review on #1745 — the count-only test wouldn't catch catalog drift. Add a strict set assertion verifying the 13 expected IDs are present and no removed/unexpected IDs remain. * test(opencode-go): update Anthropic Messages route test for refreshed catalog The direct-env-routing test listed minimax-m2.5 and qwen3.5-plus, which were removed from the opencode-go catalog. Replace with the five /messages-endpoint models that remain: minimax-m3, minimax-m2.7, qwen3.7-max, qwen3.7-plus, qwen3.6-plus. Unblocks the smoke-and-tests CI check on #1745. * fix: update OpenCode Go model references to 13 models and add assertions |
||
|
JATMN
|
5625f4217d |
fix: preserve provider route context metadata (#1741)
* fix: preserve provider route context metadata Resolve issue #1732 by keeping active provider-profile routes attached during context limit resolution and making gateway-prefixed model IDs resolve against provider-scoped metadata instead of falling through to global aliases. Preserve composite provider-path suffixes such as accounts/fireworks/models/... and fireworks/models/... before generic last-segment matching, so wrapped gateway IDs resolve Fireworks-specific limits instead of generic descriptors. Refresh OpenCode Zen and OpenCode Go catalog metadata, including route-specific context/output limits, regenerate integration artifacts, add DeepSeek V4 Pro on NVIDIA NIM, add the Gemini 3.1 Pro router alias, and update user-facing OpenCode model counts. Scope OpenCode descriptor default model names to OpenCode routes via providerModelMap so unprefixed vendor lookups are not hijacked by gateway descriptors. Add wrapper-path assertions for the user-facing max output token helper. Add regression coverage for provider-prefixed gateway models, active-profile route preservation, account-qualified composite paths, and OpenRouter-wrapped fireworks/models/... paths. Harden Windows/full-suite validation by normalizing plugin hook display paths and resetting status-redaction HOME/USERPROFILE state. Validation: bun install; bun run build; bun run smoke; bun run typecheck; bun run typecheck:type-tests; bun run check (4634 pass, 0 fail); bun run test:provider (857 pass, 0 fail); bun run test:provider-recommendation (91 pass, 0 fail); bun run integrations:check; bun run security:pr-scan -- --base upstream/main; git diff --check. Follow-up validation: bun test src/integrations/runtimeMetadata.test.ts --max-concurrency=1; bun test src/utils/context.test.ts src/integrations/runtimeMetadata.test.ts src/integrations/gateways/opencode.test.ts --max-concurrency=1; bun run test:provider; bun run integrations:check; bun run typecheck; git diff --check. # Conflicts: # src/integrations/gateways/opencode-go.ts # src/integrations/models/opencode.ts * fix: align OpenCode context metadata Refresh OpenCode Zen and Go descriptor context/output limits against the live OpenCode model lists and Models.dev provider metadata. Add a regression assertion for provider-specific OpenCode limits so route-scoped metadata does not fall back to generic model budgets. * fix: remove duplicate Gemini model descriptor Keep the canonical Gemini 3.1 Pro descriptor and rely on provider-prefixed suffix matching for google/gemini-3.1-pro runtime lookups. Also separate the OpenCode limit regression test from the following assertion for readability. * fix: preserve OpenCode Go messages auth metadata * test: cover OpenCode Go review cases |
||
|
Bogdan
|
7c034c5a62 |
feat: add redacted diagnostic issue reports (#1647)
* feat: add redacted diagnostic issue reports * fix: address diagnostic report review feedback * fix: report Codex runtime diagnostics accurately |
||
|
Bogdan
|
d8dbf274b4 |
chore(runtime): align Node.js minimum version (#1644)
* chore(runtime): align Node.js runtime requirements * test(runtime): cover prefixed Node versions * fix(runtime): check node executable in doctor |
||
|
JATMN
|
de726c43e1 |
Fix custom provider context discovery (#1620)
* Fix custom provider context discovery Teach the custom OpenAI-compatible gateway to discover context windows from /v1/models metadata, including LiteLLM model_info context_length and max_input_tokens fields. Use cached discovery metadata when resolving runtime context and output limits, with sync cache reads kept memoized and partitioned by endpoint, credential, and custom headers. Add provider-profile maxContextLength env overrides and document LiteLLM context metadata plus the CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS fallback. Cover startup discovery, runtime cache lookup, custom gateway parsing, profile overrides, and env custom-header cache partitioning with focused tests. * Fix discovery smoke test isolation Clear CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC during discovery service test setup so full-suite environment state cannot force startup discovery down the nonessential-traffic skip path. Verified with: - bun test ./src/integrations/discoveryService.test.ts - CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 targeted startup discovery test - bun run smoke - bun run typecheck * Partition custom discovery startup test cache Use a test-only custom header in the startup custom route discovery test so it exercises network discovery even when the full suite has pre-seeded the no-header custom discovery cache key. Verified with: - bun test ./src/integrations/discoveryService.test.ts - CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 targeted startup discovery test - bun run smoke - bun run typecheck * Fix profile context override lifecycle Add CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS to managed profile cleanup so switching profiles clears stale context-window overrides, including same-model OpenAI-compatible switches. Preserve persisted context-window overrides when rebuilding OpenAI-compatible startup env after restart. Verified with: - bun test src/utils/providerProfile.test.ts src/utils/providerProfiles.test.ts - bun run typecheck - bun run smoke * Detect profile context override drift Include CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS in OpenAI-compatible active-profile env alignment so managed profiles with maxContextLength are re-applied when the override is missing or stale. Verified with: - bun test src/utils/providerProfiles.test.ts - bun run typecheck - bun run smoke |
||
|
GravireiandGravirei
|
0b24b60ce9 |
feat(provider): add Fireworks AI as official OpenAI-compatible provider (#1590)
* feat(provider): add Fireworks AI as official OpenAI-compatible provider
Includes vendor descriptor, brand descriptor (276 models), model
descriptors (full + merged), routing metadata, env auto-detection,
profile support, client defaults, and docs.
* test: add focused regression tests for Fireworks AI auth and routing
- Add 7 env-only routing tests in client.test.ts (shim routing,
stale model replacement, base URL override, shim option cleanup,
non-Fireworks override ignored, priority with MiniMax, Bedrock yield)
- Add FIREWORKS_API_KEY auto-detection test in providerAutoDetect.test.ts
- Add profile apply/persistence/env-drift tests in providerProfiles.test.ts
- Fix FIREWORKS_API_KEY propagation in strictEnv early return path
* fix: address reviewer comments on Fireworks integration
- Remove OPENAI_API_KEY exclusion so Fireworks cred wins over stale OpenAI key
- Fix TS type error in test by using String() wrapper
- Add Fireworks to detection priority comment in providerAutoDetect.ts
- Add useFireworksEnvOnlyProvider to shim condition for pattern consistency
- Replace loose .includes('fireworks.ai') with isFireworksBaseUrl() exact hostname check
* fix: add explicit case 'fireworks' in applyProviderFlag for credential precedence
- Add 'fireworks' to PREFERRED_PROVIDER_ORDER
- Add case 'fireworks' with dedicated key winning pattern (mirrors atlas-cloud)
- Add FIREWORKS_API_KEY to copiedOpenAIKeyProvider detection so stale
keys are cleaned up when switching away from Fireworks
* fix: guard fireworks defaultModel assignment against 'undefined' string coercion
* fix: remove leftover conflict marker in providerProfiles.ts
* docs(fireworks): add JSDoc to Fireworks functions for coderabbit docstring coverage
Adds JSDoc annotations to isFireworksBaseUrl, getFireworksBaseUrlOverride,
hasFireworksEnvOnlyProviderIntent, isFireworksModelName, and
applyFireworksEnvOnlyDefaults.
* fix(fireworks): cross-check NEARAI_API_KEY in env-only intent functions
hasNearaiEnvOnlyProviderIntent and hasFireworksEnvOnlyProviderIntent were
missing mutual cross-checks. When both NEARAI_API_KEY and FIREWORKS_API_KEY
are set, neither excludes the other, and nearai silently wins by ordering.
Adding !hasNonEmptyEnvValue(processEnv.FIREWORKS_API_KEY) to the nearai intent
and !hasNonEmptyEnvValue(processEnv.NEARAI_API_KEY) to the fireworks intent
ensures both return false, forcing explicit provider selection.
* fix(fireworks): fix typo in JSDoc — OPENAI_API_API_BASE -> OPENAI_API_BASE
* fix(fireworks): remove merge artifact and preserve no-key auth headers
- src/utils/providerAutoDetect.ts: remove leftover ======= conflict
marker and stale duplicate priority lines
- src/utils/providerProfiles.ts: preserve apiFormat, authHeader,
authScheme, authHeaderValue in the no-key OpenAI-compatible
fallback path so saved Responses mode / custom auth config
survives restart
* fix: Fireworks env-only startup preservation and MIMO priority comment
- Add FIREWORKS_API_KEY check to hasConcreteProviderSelection() so env-only
Fireworks setup is not overwritten by Gitlawb Opengateway default
- Add regression test verifying FIREWORKS_API_KEY survives no-profile startup
- Fix providerAutoDetect.ts priority comment to include MIMO_API_KEY (position 8)
and renumber subsequent entries to match actual detection order
* fix: also preserve env-only NEAR AI startup in hasConcreteProviderSelection()
* fix: remove duplicate Fireworks model descriptor, add FIREWORKS_API_KEY to test env cleanup
* fix: move duplicate model check to generation-time, add OPENAI_AUTH_* env cleanup to test harness
---------
Co-authored-by: Gravirei <gravirei@users.noreply.github.com>
|
||
|
GravireiandGravirei
|
eacc7d8fac |
feat: add NEAR AI provider integration (#1594)
* feat: add NEAR AI provider integration
- Create vendor, brand, and model descriptors for NEAR AI (22 models)
- Add NEAR AI to route metadata, client, provider auto-detect, and profiles
- Update compatibility tests and ProviderManager test PRESET_ORDER
- Add README and docs entries for NEAR AI provider
- Update .env.example with NEAR AI configuration
* fix: address CodeRabbit review comments
- Fix .env.example: change 'Option N' to 'Option 11' in quick reference
- Narrow isNearaiModelName to use explicit NearAI model prefixes instead of broad includes('/')
- Add NEARAI_API_KEY propagation in strictEnv startup path
* fix: align NEAR AI validation host matching with wildcard subdomain routing
- Add *.completions.near.ai to matchBaseUrlHosts in vendor descriptor
- Add matchHostnameAgainstRouteHosts helper with wildcard (*.) prefix support
- Use helper in both resolveRouteIdFromBaseUrl and getRuntimeValidationTarget
- Add regression test for qwen35-122b.completions.near.ai TEE endpoint
- Add NEARAI_API_KEY to test env cleanup list
* fix: align Near AI integration with env-only provider best practices
- Replace loose .includes('near.ai') with isNearaiBaseUrl() in providerProfiles.ts
for exact hostname validation (all 4 instances)
- Add NEARAI_API_KEY to copiedOpenAIKeyProvider detection in providerFlag.ts
- Add case 'nearai' to applyProviderFlag switch with dedicated key precedence
- Add 'nearai' to PREFERRED_PROVIDER_ORDER
- Add useNearaiEnvOnlyProvider to OpenAI shim condition in client.ts
- Remove OPENAI_API_KEY exclusion from hasNearaiEnvOnlyProviderIntent (dedicated
key wins over stale generic key, consistent with xAI pattern)
- Update detection priority comment in providerAutoDetect.ts to include
MIMO_API_KEY, XAI_API_KEY, and NEARAI_API_KEY
* fix: add exact completions.near.ai host to isNearaiBaseUrl
* fix: add higher-precedence provider key exclusions to hasNearaiEnvOnlyProviderIntent
* fix: add OPENAI_API_KEY and MINIMAX_API_KEY exclusions to hasNearaiEnvOnlyProviderIntent
* fix(near-ai): don't let stale OPENAI_API_KEY suppress Near AI routing
---------
Co-authored-by: Gravirei <gravirei@users.noreply.github.com>
|
||
|
JATMN
|
14036209cd |
Add configurable message-count compaction (#1587)
* Add configurable message-count compaction Add a /config setting for opting into message-count-based compaction thresholds and persist it in global config. Disable the legacy OPENCLAUDE_MAX_ACTIVE_MESSAGES default unless the new setting is off and the environment variable is explicitly set. Add a timeout around forked compact summaries using a child abort controller so timeouts and user aborts clean up without affecting the main thread. Document the diagnostic setting and normalize trailing line endings in Windows alias docs/script. * Address compaction PR review feedback Add a shared literal enum and normalizer for message-count compaction thresholds, use it in config, /config UI, and query threshold handling. Move the compact timeout constant to module scope and mark the /config docs snippet with a text fence. |
||
|
|
286d403093 |
Update(zen-go): add claude-opus-4-8, minimax-m3, mimo-v2.5-free models and proper effort level integration for Zen/Go models (#1505)
* feat(provider): add OpenCode Zen/Go subscription support
Add OpenCode as a first-class provider, enabling users to connect their
Zen (pay-as-you-go) and Go ($10/mo) subscriptions via the /provider command.
New integration descriptors:
- vendors/opencode.ts — OpenCode Zen vendor (41 models)
- gateways/opencode-go.ts — OpenCode Go gateway (12 models)
- brands/opencode.ts — brand descriptor
- models/opencode.ts — full model catalog (GPT, Claude, Gemini, Qwen,
GLM, Kimi, MiniMax, Grok, DeepSeek, MiMo, Nemotron)
Modified files:
- integrationArtifacts.generated.ts — register descriptors and presets
- providerProfile.ts — add OPENCODE_API_KEY env/secret key, 'opencode'
profile type, and buildLaunchEnv handler
- providerConfig.ts — add DEFAULT_OPENCODE_BASE_URL constants
Auth: OPENCODE_API_KEY env var or interactive key entry in /provider
Transport: openai-compatible (chat_completions)
Base URLs: https://opencode.ai/zen/v1 (Zen), /zen/go/v1 (Go)
* feat(provider): add [Zen]/[Go] tags to OpenCode preset labels
Add visual tags in the /provider preset selection to distinguish
OpenCode Zen (pay-as-you-go) from OpenCode Go (subscription).
* feat(provider): enable dynamic model discovery for OpenCode
Switch OpenCode vendor and Go gateway from static to hybrid model
catalog with openai-compatible discovery. Models are fetched from
/v1/models on startup and cached for 1 hour. Manual refresh is
supported via the /provider UI.
Static model list is preserved as fallback when discovery fails.
* test(provider): add comprehensive OpenCode Zen/Go test suite
97 tests across 2 files covering:
Integration tests (72 tests):
- Vendor descriptor: id, label, classification, base URL, model, auth,
transport, preset, validation, catalog, discovery, usage metadata
- Gateway descriptor: id, label, vendorId, category, base URL, model,
auth, transport, preset, catalog, discovery
- Brand descriptor: id, label, canonicalVendorId, capabilities, modelIds
- Model catalog: registration, vendor/gateway associations, required
fields, valid classifications, reasoning/coding tags, no duplicates,
model counts (41 Zen, 12 Go), modelDescriptorId consistency
- Cross-reference: brand↔model, vendor↔model, gateway↔model,
shared OPENCODE_API_KEY
- Registry validation: no errors, no preset conflicts
- Edge cases: unique ids, unique apiNames, non-empty labels, valid
contextWindow/maxOutputTokens, valid defaultModel format, validation
message content, discovery config
Profile tests (25 tests):
- Type guard: isProviderProfile('opencode'), rejects invalid values
- buildLaunchEnv: persisted env, defaults, process env precedence,
OPENCODE_API_KEY mapping, whitespace/null/undefined/empty handling,
very long keys, special characters, concurrent access, boundary
values, no credential leakage
* fix(provider): add per-model endpoint routing (P1)
Add endpointPath field to OpenAIShimTransportConfig so catalog entries
can specify which API path to use per model. This addresses the
maintainer's [P1] finding that all models were routed to
/chat/completions regardless of their upstream endpoint.
Changes:
- descriptors.ts: add endpointPath?: string to OpenAIShimTransportConfig
- openaiShim.ts: buildRequestUrl checks shimConfig.endpointPath first
- vendors/opencode.ts: add transportOverrides to 31 catalog entries
(GPT→/responses, Claude/Qwen→/messages, Gemini→/models/<id>)
+ switch to source: 'static' to prevent free models from live API
- gateways/opencode-go.ts: add transportOverrides to 4 entries
(MiniMax/Qwen→/messages) + switch to source: 'static'
- opencode.test.ts: update tests for static source, remove discovery tests
* refactor(opencode): model OpenCode Zen/Go as gateways (P2)
* docs(provider): document OpenCode setup and move badge metadata to descriptors
- Add OpenCode Zen/Go rows to README supported providers table
- Add OpenCode Zen/Go examples and OPENCODE_API_KEY to advanced-setup.md
- Add PresetBadge type to descriptor/manifest with badge propagation in
artifact generator
- Move 4 hard-coded preset badges ([FREE], [Sponsor], [Zen], [Go]) from
ProviderManager.tsx into descriptor preset metadata
- Add badge field to providerUiMetadata so UI components read from manifest
- Update integration overview docs to recommend preset.badge for future
gateways
* fix(provider): match request body to endpoint format for OpenCode /messages and /responses (P1)
Extend the openaiShim transport so that endpointPath overrides select
both the URL and the correct body/response format:
- /responses → OpenAI Responses API body (input, max_output_tokens)
- /messages → Anthropic Messages API body (content blocks, system, max_tokens)
Also fixes: abort listener leak in SSE passthrough, system prompt
content-block flattening, and removes [Zen]/[Go] badge entries (P3).
Co-Authored-By: OpenClaude (mimo-v2.5-pro) <openclaude@gitlawb.com>
* fix(provider): add Google AI SDK body/response format for OpenCode Zen Gemini models (P1)
The three Gemini models in the OpenCode Zen catalog (gemini-3.5-flash,
gemini-3.1-pro, gemini-3-flash) were sending chat-completions body to
the /models/gemini-* endpoint, which expects Google AI SDK format.
- effectiveTransport now detects /models/gemini- endpointPath → 'gemini'
- buildGeminiBody() converts Anthropic messages → Google contents[]
with role mapping, systemInstruction, generationConfig, functionDeclarations
- geminiSseToAnthropic() parses Google SSE frames → Anthropic stream events
with text deltas, functionCall tool_use, finishReason mapping
- _convertGeminiToAnthropicResponse() for non-streaming responses
- Streaming/non-streaming routing via URL detection (/models/gemini-)
- serializeBody(), hasToolsPayload, omitGeminiTools all updated
* fix: prevent OpenCode model descriptors from shadowing canonical limits
P1: Prefix all defaultModel values in opencode.ts with 'opencode-'
so the fallback findModelDescriptorForApiName() doesn't match
canonical model names. The OpenCode descriptors are still found
via catalog entry lookup when the OpenCode route is active.
P2: Add 'OpenCode Go' and 'OpenCode Zen' to PRESET_ORDER in
ProviderManager.test.tsx between 'OpenAI' and 'OpenRouter'
so navigateToPreset() sends the correct number of j keypresses.
* fix: align OpenCode Go descriptor metadata with Zen
- category: 'hosted' → 'aggregating' (both are aggregating gateways)
- add validation block with OPENCODE_API_KEY guidance
- update test assertion from 'hosted' to 'aggregating'
* fix: accept OPENAI_API_KEY as fallback in OpenCode validation
When users set up OpenCode Zen/Go via /provider, the key is saved as
OPENAI_API_KEY (via buildCompatibilityProcessEnv). The validation block
only checked OPENCODE_API_KEY, causing a startup warning even though
the runtime auth header had the key it needed.
Add OPENAI_API_KEY to validation.credentialEnvVars for both gateways,
matching the pattern used by Hicap and Gitlawb Opengateway.
* chore: trigger mergeability recheck
* feat(shim): forward effort/thinking to OpenCode Zen/Go endpoints
- buildResponsesBody: add reasoning_effort + reasoning_summary + include
- buildAnthropicMessagesBody: add thinking config (adaptive/enabled/budget)
- buildGeminiBody: add thinkingConfig with thinkingLevel mapping
- modelSupportsEffort: allow OpenCode Claude and Gemini models
- modelSupportsMaxEffort: add opus-4-7
- getAvailableEffortLevels: show standard levels for OpenCode native models
- opencode-go: add missing validation block
* feat: update OpenCode Zen and Go model counts, add new models, and enhance effort level handling
* feat: implement xhigh effort support for specific models and adjust effort level handling
* fix(effort): address reviewer feedback on xhigh + new models
- docs/advanced-setup.md: bump OpenCode Go count 12 → 13
- openaiShim.ts: include opus-4-8 / opus-4.8 in the adaptive thinking
detection so the new model uses the adaptive + effort path instead
of falling back to budgetTokens
- effort.ts: modelUsesOpenAIEffort now also rejects models that include
'claude-' or 'gemini-' — without this, OpenCode Claude/Gemini
routes (provider=openai) were misclassified as OpenAI-style and
could leak xhigh past the new gate
- effort.codex.test.ts: lock in the new exclusion with a regression
test against the openai provider
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(effort): address reviewer feedback on xhigh effort + new models
Closes the three P2 findings from PR #1505 review:
1. Settings schema now accepts 'xhigh' so a persisted xhigh survives
restart instead of being silently dropped by .catch(undefined).
2. ModelPicker /effort cycle is driven by getAvailableEffortLevels(model)
instead of a boolean includeMax, so models supporting xhigh
(opus-4-7/4-8, OpenAI/Codex) can actually select it from the picker.
displayEffort clamp now uses the available levels list, so stale
xhigh also clamps to high when the focused model doesn't support it.
3. SDK/control metadata uses getAvailableEffortLevels(model) instead of
the EFFORT_LEVELS fallback that advertised xhigh to every max-capable
model. SDK schema + generated types extended to include 'xhigh'.
Also fixes a latent generator bug: the array case in generate-sdk-types
now parenthesizes union/intersection elements so the trailing [] binds
the whole type, e.g. ("a"|"b")[] rather than "a"|"b[]. Without this,
the regenerated xhigh levels ended up typed as the single-literal
"xhigh"[] and broke the modelInfo assignability check.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore(effort): order xhigh before max in EFFORT_LEVELS
EFFORT_LEVELS now matches getAvailableEffortLevels() output order
(['low', 'medium', 'high', 'xhigh', 'max']), and the order asserted by
the existing effort.codex.test.ts tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore(effort): order xhigh before max in settings + SDK schemas
Matches the EFFORT_LEVELS / getAvailableEffortLevels order from the
previous commit. The Zod enum order doesn't affect runtime validation,
but keeps the source consistent and avoids confusion if anyone reads
the enum literal to infer display order.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(effort): clamp ModelPicker selection and mark xhigh as current
- ModelPicker.handleSelect: clamp the emitted/persisted effort to the
focused model's available levels so a toggled-but-unsupported level
(e.g. 'xhigh' on a model that doesn't support it) is never written
to settings.json or handed to the consumer. Add focusedAvailableLevels
+ focusedDefaultEffort to the memo guard so the function regenerates
when the focused model changes.
- EffortPicker: compare the xhigh option against the persisted 'xhigh'
level directly. The 'max' alias path is kept only for legacy
settings.json values that still hold 'max' from before xhigh was
introduced.
* docs(effort): fix stale EffortPicker comment about xhigh normalization
openAIEffortToStandard is a type cast that passes 'xhigh' through as a
first-class EffortLevel — the shim only converts to 'max' at the
Anthropic request boundary, not here. Update the comment to match.
* docs(effort): update /effort help to match xhigh support matrix
The /effort --help output still described max as "Opus 4.6 only" and
xhigh as an "alias for max", but this PR promotes xhigh to a first-class
EffortLevel and allows it for OpenCode Claude Opus 4.7/4.8 (with max
also allowed for those Opus variants). Update the help so it matches
the picker/runtime behavior:
- max: "(Opus 4.6+)"
- xhigh: "(OpenAI/Codex and Opus 4.7+)"
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(sdk): address reviewer P2 — sync xhigh across override union, schemas, CLI
- Add 'xhigh_effort' to ModelCapabilityOverride union so the new
call at effort.ts:93 typechecks (P2 finding 1).
- Add 'xhigh' to AgentDefinition.effort enum (coreSchemas.ts) and
control.applied.effort enum (controlSchemas.ts), then regenerate
coreTypes.generated.ts so the SDK public contract matches the
first-class effort level (P2 finding 2).
- Add 'xhigh' to the --effort CLI flag allowed list and help text
(main.tsx:945-951) so users can actually pass --effort xhigh
instead of hitting "It must be one of: low, medium, high, max".
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(effort): narrow allowlist to shim-serialized models; sync max description
Address reviewer findings on PR #1505:
P2: The broad `m.includes('opus-4') || m.includes('sonnet-4')` branch
made older variants (claude-opus-4-1, claude-sonnet-4-5) advertise
effort support, but the Anthropic /messages shim only serializes
low/medium as anthropicBody.effort for the isAdaptive || isOpus45
set (opus-4-5/4-6/4-7/4-8, sonnet-4-6). For other models the shim
only emits thinking for high/max, so low/medium on those models
was silently dropped on the wire. Collapse the two 4-model branches
into one that matches the shim's serialization set; the substring
match still covers prefix variations (claude-, opencode-claude-).
P3: getEffortLevelDescription('max') said "Opus 4.6 only" but
modelSupportsMaxEffort now allows opus-4-6, opus-4-7, opus-4-8.
Update the shared description to "Opus 4.6+" so the picker and
/effort confirmation agree with the new support matrix (matching
the /effort --help text from
|
||
 JoneSSL
|
07c1c56b4f |
Add Azure / Foundry launch support to VS Code extension (#1365)
* Enhance OpenClaude VS Code extension with Microsoft Foundry / Azure OpenAI support. Added configuration options for Azure API key, endpoint, and deployment settings. Updated README and documentation for new features, including a setup wizard for Azure integration. Improved terminal launch environment handling for Azure compatibility. * Fix packaged Windows helper runtime references * Use installed CLI from Windows helper aliases * Scope Windows helper env overrides to invocation * Align Windows alias docs with shipped helper |
||
 chioarub
|
169d0f737d |
Add provider-profile model picker modes (#1472)
* fix(model): preserve discovered models for active profiles * test: isolate attribution settings state * fix(model): add provider profile picker modes * docs: document provider profile model picker mode * Preserve cached legacy model options on empty refresh |
||
|
JATMN
|
3be54de16b |
Make OpenGateway the default startup provider (#1493)
Default fresh installs to the Gitlawb OpenGateway profile, keep validation behavior for saved profiles, and mark OpenGateway as the recommended provider in the picker. Update setup docs and generated integration metadata to reflect the API-key-backed OpenGateway route, and add coverage for the fresh-install startup environment. |
||
|
chioarub
|
f3d41c6161 |
fix(release): verify npm latest tag and document @latest install (#1378)
* fix(release): verify npm latest tag and document @latest install * fix(auto-updater): use @latest for global installs |
||
|
|
5a22d604f8 |
feat(provider): add OpenCode Zen/Go subscription support (#1350)
* feat(provider): add OpenCode Zen/Go subscription support Add OpenCode as a first-class provider, enabling users to connect their Zen (pay-as-you-go) and Go ($10/mo) subscriptions via the /provider command. New integration descriptors: - vendors/opencode.ts — OpenCode Zen vendor (41 models) - gateways/opencode-go.ts — OpenCode Go gateway (12 models) - brands/opencode.ts — brand descriptor - models/opencode.ts — full model catalog (GPT, Claude, Gemini, Qwen, GLM, Kimi, MiniMax, Grok, DeepSeek, MiMo, Nemotron) Modified files: - integrationArtifacts.generated.ts — register descriptors and presets - providerProfile.ts — add OPENCODE_API_KEY env/secret key, 'opencode' profile type, and buildLaunchEnv handler - providerConfig.ts — add DEFAULT_OPENCODE_BASE_URL constants Auth: OPENCODE_API_KEY env var or interactive key entry in /provider Transport: openai-compatible (chat_completions) Base URLs: https://opencode.ai/zen/v1 (Zen), /zen/go/v1 (Go) * feat(provider): add [Zen]/[Go] tags to OpenCode preset labels Add visual tags in the /provider preset selection to distinguish OpenCode Zen (pay-as-you-go) from OpenCode Go (subscription). * feat(provider): enable dynamic model discovery for OpenCode Switch OpenCode vendor and Go gateway from static to hybrid model catalog with openai-compatible discovery. Models are fetched from /v1/models on startup and cached for 1 hour. Manual refresh is supported via the /provider UI. Static model list is preserved as fallback when discovery fails. * test(provider): add comprehensive OpenCode Zen/Go test suite 97 tests across 2 files covering: Integration tests (72 tests): - Vendor descriptor: id, label, classification, base URL, model, auth, transport, preset, validation, catalog, discovery, usage metadata - Gateway descriptor: id, label, vendorId, category, base URL, model, auth, transport, preset, catalog, discovery - Brand descriptor: id, label, canonicalVendorId, capabilities, modelIds - Model catalog: registration, vendor/gateway associations, required fields, valid classifications, reasoning/coding tags, no duplicates, model counts (41 Zen, 12 Go), modelDescriptorId consistency - Cross-reference: brand↔model, vendor↔model, gateway↔model, shared OPENCODE_API_KEY - Registry validation: no errors, no preset conflicts - Edge cases: unique ids, unique apiNames, non-empty labels, valid contextWindow/maxOutputTokens, valid defaultModel format, validation message content, discovery config Profile tests (25 tests): - Type guard: isProviderProfile('opencode'), rejects invalid values - buildLaunchEnv: persisted env, defaults, process env precedence, OPENCODE_API_KEY mapping, whitespace/null/undefined/empty handling, very long keys, special characters, concurrent access, boundary values, no credential leakage * fix(provider): add per-model endpoint routing (P1) Add endpointPath field to OpenAIShimTransportConfig so catalog entries can specify which API path to use per model. This addresses the maintainer's [P1] finding that all models were routed to /chat/completions regardless of their upstream endpoint. Changes: - descriptors.ts: add endpointPath?: string to OpenAIShimTransportConfig - openaiShim.ts: buildRequestUrl checks shimConfig.endpointPath first - vendors/opencode.ts: add transportOverrides to 31 catalog entries (GPT→/responses, Claude/Qwen→/messages, Gemini→/models/<id>) + switch to source: 'static' to prevent free models from live API - gateways/opencode-go.ts: add transportOverrides to 4 entries (MiniMax/Qwen→/messages) + switch to source: 'static' - opencode.test.ts: update tests for static source, remove discovery tests * refactor(opencode): model OpenCode Zen/Go as gateways (P2) * docs(provider): document OpenCode setup and move badge metadata to descriptors - Add OpenCode Zen/Go rows to README supported providers table - Add OpenCode Zen/Go examples and OPENCODE_API_KEY to advanced-setup.md - Add PresetBadge type to descriptor/manifest with badge propagation in artifact generator - Move 4 hard-coded preset badges ([FREE], [Sponsor], [Zen], [Go]) from ProviderManager.tsx into descriptor preset metadata - Add badge field to providerUiMetadata so UI components read from manifest - Update integration overview docs to recommend preset.badge for future gateways * fix(provider): match request body to endpoint format for OpenCode /messages and /responses (P1) Extend the openaiShim transport so that endpointPath overrides select both the URL and the correct body/response format: - /responses → OpenAI Responses API body (input, max_output_tokens) - /messages → Anthropic Messages API body (content blocks, system, max_tokens) Also fixes: abort listener leak in SSE passthrough, system prompt content-block flattening, and removes [Zen]/[Go] badge entries (P3). Co-Authored-By: OpenClaude (mimo-v2.5-pro) <openclaude@gitlawb.com> * fix(provider): add Google AI SDK body/response format for OpenCode Zen Gemini models (P1) The three Gemini models in the OpenCode Zen catalog (gemini-3.5-flash, gemini-3.1-pro, gemini-3-flash) were sending chat-completions body to the /models/gemini-* endpoint, which expects Google AI SDK format. - effectiveTransport now detects /models/gemini- endpointPath → 'gemini' - buildGeminiBody() converts Anthropic messages → Google contents[] with role mapping, systemInstruction, generationConfig, functionDeclarations - geminiSseToAnthropic() parses Google SSE frames → Anthropic stream events with text deltas, functionCall tool_use, finishReason mapping - _convertGeminiToAnthropicResponse() for non-streaming responses - Streaming/non-streaming routing via URL detection (/models/gemini-) - serializeBody(), hasToolsPayload, omitGeminiTools all updated * fix: prevent OpenCode model descriptors from shadowing canonical limits P1: Prefix all defaultModel values in opencode.ts with 'opencode-' so the fallback findModelDescriptorForApiName() doesn't match canonical model names. The OpenCode descriptors are still found via catalog entry lookup when the OpenCode route is active. P2: Add 'OpenCode Go' and 'OpenCode Zen' to PRESET_ORDER in ProviderManager.test.tsx between 'OpenAI' and 'OpenRouter' so navigateToPreset() sends the correct number of j keypresses. * fix: align OpenCode Go descriptor metadata with Zen - category: 'hosted' → 'aggregating' (both are aggregating gateways) - add validation block with OPENCODE_API_KEY guidance - update test assertion from 'hosted' to 'aggregating' * fix: accept OPENAI_API_KEY as fallback in OpenCode validation When users set up OpenCode Zen/Go via /provider, the key is saved as OPENAI_API_KEY (via buildCompatibilityProcessEnv). The validation block only checked OPENCODE_API_KEY, causing a startup warning even though the runtime auth header had the key it needed. Add OPENAI_API_KEY to validation.credentialEnvVars for both gateways, matching the pattern used by Hicap and Gitlawb Opengateway. * chore: trigger mergeability recheck --------- Co-authored-by: Gravirei <gravirei@users.noreply.github.com> Co-authored-by: OpenClaude (mimo-v2.5-pro) <openclaude@gitlawb.com> |
||
 stamsam
|
2e3f7467f9 |
docs(vertex): clarify Claude on Vertex setup (#1273)
* docs(vertex): clarify Claude on Vertex setup * docs(vertex): point region overrides at env utils * docs(vertex): use cli model selector |
||
|
JATMNandJATMN
|
d02c10b399 |
feat: configure API retry backoff (#370) (#1095)
* feat: configure API retry backoff Add OpenClaude-branded retry controls for retryable API failures. - Replace the old CLAUDE_CODE_MAX_RETRIES config with OPENCLAUDE_MAX_RETRIES - Allow OPENCLAUDE_MAX_RETRIES=0 to disable retries after the initial request - Cap retry attempts at 100 and invalid values fall back to the default of 10 - Add OPENCLAUDE_RETRY_DELAY_MS to configure the exponential backoff base for APIs that omit Retry-After - Keep Retry-After precedence over configured retry delay - Document both settings in .env.example and advanced setup docs - Add focused retry configuration tests for defaults, invalid values, caps, zero retries, configured delay, and Retry-After precedence Validation: - bun test src/services/api/withRetry.test.ts - bun run build * Honor legacy max retries env var Add compatibility fallback from CLAUDE_CODE_MAX_RETRIES when OPENCLAUDE_MAX_RETRIES is unset. Document the deprecated fallback and cover precedence behavior in retry configuration tests. --------- Co-authored-by: JATMN <12479882+jatmn@users.noreply.github.com> |
||
|
Kevin Codex
|
13a090162f | fix(gemini): preserve tool calls through opengateway (#1204) | ||
|
|
4d04f5bf4f |
feat(opengateway): add Gemini 3.1 Flash Lite + GLM 5.1 FP8 to catalog (#1194)
* feat(opengateway): add Gemini 3.1 Flash Lite + GLM 5.1 FP8 to catalog Opengateway now routes non-Xiaomi models through GMI Cloud (configured in opengateway/src/providers.ts via modelIds: - google/gemini-3.1-flash-lite-preview - zai-org/GLM-5.1-FP8 Adding both as catalog entries on the gitlawb-opengateway gateway descriptor so openclaude users see them in the model picker when the Opengateway preset is active. Each catalog entry reuses the existing upstream model descriptor (`gemini-3.1-flash-lite-preview`, `GLM-5.1`) for capability metadata; the apiName uses the full vendor-prefixed form the gateway routes on. No new model/brand/vendor descriptors needed — only the gateway catalog gets the new IDs. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * update opengateway --------- Co-authored-by: OpenClaude <openclaude@gitlawb.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |