`shift_enter_unavailable` kept its own list of brands and missed every
other reason the Kitty keyboard protocol gets skipped: JetBrains, screen,
tmux below 3.3 and tmux with `extended-keys off` all swallow it, yet the
prompt still advertised Shift+Enter there. It now reads
`kitty_skip_reason` directly. Two skips deliver the modifier another way
and stay available: Apple Terminal, where `route_enter` polls
CoreGraphics, and Windows Terminal, where the console key record carries
SHIFT — a bare ConHost, only optimistically refined to Windows Terminal,
keeps advertising Alt+Enter.
The old list also carried a `VTE_VERSION >= 8200` cutoff, citing VTE
0.82.0 as the first release with the protocol. It is not: at tag 0.82.0
the string "kitty" appears nowhere in `src/parser-seq.py`, `src/vte.cc`
or `src/widget.cc`, and `_vte_keymap_GDK_Return` encodes only Alt
(`ESC CR`), so Shift+Enter leaves a VTE terminal as the same bare CR as
Enter. Every VTE now advertises Alt+Enter, and `/terminal-setup` stops
telling GNOME Terminal users to upgrade to a version that would not
help. It also stops advertising Alt+Enter to WezTerm, which binds that
chord to ToggleFullScreen.
The pager rendered "Compaction failed." with the error dropped, and the
shell's unsuppressed auto-compaction failure sent an empty error. Both
now carry the decoded first line of the failure (retry guidance plus the
detail), decoded from the ACP data rather than its JSON-escaped Display,
propagated unchanged through the compact extension, capped for a banner.
Endpoint credentials never reach the banner: the sampler redacts the
parsed endpoint (userinfo, sensitive query values, fragment via the
repository sanitizer) in every 401 message and the appended request URL,
and the shell redacts every URL in the error text before line selection,
including URLs whose password holds whitespace or that follow a
multi-byte delimiter.
Ported from upstream 1.0.13 (grok-build dispatch/prompt.rs,
session/compaction.rs), extended with the redaction.
Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
With fd 2 dead (a closed pane, an exited pipe reader) every write fails,
eprintln! panics on that failure, and under panic = "abort" the process
dies by SIGABRT with a crash report on the next launch instead of its
exit code. Exit reports, headless plain-format diagnostics, update-exit,
setup-result and leader-management messages now write through
best_effort_stderr::eprint_line: one attempt, failure reported, never a
panic.
Ported from upstream 1.0.19 (grok-build best_effort_stderr.rs).
Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
str::lines() splits on neither separator, so a paste carrying them counted
as one line and the invisible characters broke the textarea's width model.
Bare \r, U+2028 and U+2029 now normalize to \n on every paste route (the
prompt, the inline paste key and the previous-message editor); dropped
file paths keep their bytes verbatim because a separator in a filename is
payload.
Ported from upstream 1.0.18 (grok-build prompt_widget normalize_line_breaks).
Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
AutoCompactStarted carries the count the trigger fired on, but only
AutoCompactCompleted refreshed the context bar, so the "N% full" banner
sat next to a stale pre-turn number until the next stream update. Both
lifecycle updates now refresh the bar, on the root view and on subagent
views.
Ported from upstream 1.0.12 (grok-build acp_handler/session_notification.rs).
Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
The queued /compact command drained into Effect::Compact with only the
session id, so the instructions typed after the command never reached the
shell's compaction prompt (which already accepts userContext). The effect
carries the parsed instructions, trimmed so an edited queue row with
leading whitespace still counts.
Ported from upstream 1.0.22 (grok-build dispatch/queue.rs).
Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
A terminal that stopped draining the pty parked the writer thread inside
its tty write while it held the stderr lock; the next inline stderr write
from the event loop (mouse toggle, notification, kitty clear) deadlocked
the loop, and /quit hung on the unbounded writer join and the teardown
writes.
EscapeWriter queues out-of-band escapes on the frame writer: the mouse
capture toggle, notifications (title, progress, protocol), the auth
cursor, gboom keyboard flags, the wrap clipboard request, and the kitty
clears (queued per agent view and merged into the frame's post-flush,
nested subagent views included). The $EDITOR/$PAGER handoff aborts when
the writer does not drain. WriterThread::join_within and the teardown
run under a 2 s grace; after a stall fd 2 is silenced, the exit hints,
relaunch and update prints are skipped, and the panic hook keeps only its
log report.
Ported from upstream 1.0.19 (grok-build EscapeWriter, WriterJoin,
run_bounded_teardown), extended to the remaining inline writes.
Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
Edit/Read/Grep rules matched only the raw argument string, so a workspace
symlink (or a quoted, `~`, `./`, `..`, or absolute spelling) reached a
denied file. The policy now resolves the path exactly as the tools do
(sanitize, expand `~`, display-cwd remap, join to the requesting session's
cwd), follows symlinks parent-first, and re-checks deny/ask rules on the
opened path and its target as absolute, `./`-relative and relative
spellings. Escalation only: no allow is granted through a link. A link
that cannot be followed forces a prompt that survives YOLO, auto mode and
the session edit grant, with event reason `unresolved_link`.
Permission requests now carry the requesting tool's cwd and display cwd
so a child worktree session sharing its parent's handle is checked where
it runs.
Ported from upstream 1.0.14 (grok-build permission/policy.rs symlink
re-check), reshaped for Kigi's lexical rule matcher.
Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
Port of upstream grok-build 1.0.14 ("--sandbox strict now restricts
writes to ~/.grok/sessions only"), shaped for Kigi.
The strict profile granted the whole ~/.kigi read-write, so a sandboxed
command could plant a global SessionStart hook or flip
`[sandbox].profile` in config.toml for the next launch. Landlock cannot
carve a child out of a write grant, so the home is now read-only
except an explicit allowlist of state subtrees (run, sessions,
worktrees, worktree_pool, tasks, memory, logs, debug, crash, memtrace,
trace-exports); config.toml, auth.json, sandbox.toml, hooks/, bin/ and
vendor/ stay read-only. A symlinked state dir under the home is
followed only to the default ~/.kigi/sessions.
What the process itself writes there after enforcement moves or is
minted first:
- kigi-shell `apply_sandbox` mints the device id, extracts the bundled
rg and the bundled skills BEFORE enforcement for every profile that
restricts home writes (`restricts_home_writes`, custom profiles
extending strict included).
- The sandbox audit log lives at ~/.kigi/sessions/sandbox-events.jsonl.
- Leader lock/socket default to ~/.kigi/run/, the leader stderr log to
~/.kigi/logs/leader.log; discovery scans run/ and the legacy root,
and the default target prefers the current socket.
Root-level caches (version.json, agent_id, slash-mru.json, pager.toml,
claude_import_state.json) degrade best-effort under strict; documented.
Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
After `/model`, the header kept the previous model's window ("15K /
1.0M" on a 262K model) until the next turn or a restart. The pager
caches the window inside its context snapshot (streaming `totalTokens`
updates refresh it from the catalog) and nothing refreshed the cache
when the session's model changed. Comparing cached numbers against
catalog windows cannot tell a catalog-derived total from a shell
effective limit (KIGI_DEBUG_CONTEXT_WINDOW, header upgrades), so the
shell, which installs the effective window, now reports it:
- kigi-shell: `handle_set_session_model` returns the installed window;
`model_switch::apply` stamps it as `totalContextTokens` in the
`session/set_model` response meta and carries it on the
`ModelChanged` broadcast (`context_window`, serde-default: old pagers
ignore it, old leaders omit it). The response meta previously
serialized the actor's inner `Result` and reported success on an
actor failure; that error now propagates.
- kigi-tui: `Effect::SwitchModel` reads the meta; `SwitchModelComplete`
carries `Ok(Option<u64>)`; the completion handler and the follower
`ModelChanged` arm call `AgentView::apply_context_window`, which
re-derives the snapshot (pct, free tokens) and reports whether it
changed so a follower redraws on a window-only change.
- Tests: the bare `/model <name>` dispatch path asserts the snapshot and
the drawn header; follower with/without the field; same-model new
window redraw; actor returns the window; serde round trip.
Claude-Session: https://claude.ai/code/session_01RUqV8HVGXcAETyYbZ2tPQ4
The GitHub account is restored, so github.com/ZacharyZhang-NY/Kigi-CLI is
the canonical repo again. Reverse the 2026-08 Gitea migration:
- .github/workflows/{release,warm-cache}.yml: restore the GitHub-hosted
pipeline dropped in 3e1652c, unchanged — hosted runners, rust-cache,
softprops release with every asset attached atomically.
- .gitea/workflows/release.yml: retire the Gitea edition (the runners are
being deregistered; git.zacharyzhang.com keeps the v0.1.12/v0.1.13
releases for old clients).
- kigi-env: update_base_url now defaults to the GitHub Releases API. The
updater already speaks GitHub wire format and sends a User-Agent; v0.1.14
is published to BOTH forges with identical assets so pre-0.1.14 installs
polling Gitea self-update onto the GitHub channel.
- install.sh / install.ps1: resolve releases from api.github.com.
- feedback, /docs, SECURITY.md, frontend worker + site: repo, issues and
raw-file links point at github.com / raw.githubusercontent.com.
- docs/RELEASE.md: GitHub edition of the checklist; Gitea runner sections
retired.
- version: 0.1.13 -> 0.1.14 (the cross-forge transition release).
Claude-Session: https://claude.ai/code/session_01A6RcwHhhsFYYrNdQB4ASuP
Second layer of platform gaps the mac/linux-only gate history left:
unix-only test imports/helpers now cfg-gated (mermaid, fast-worktree,
hunk-tracker, pager-render link test, three pty_e2e module decls),
clippy-suggested cleanups in Windows-cfg code (file-utils classifier,
tui console-mode restore, shared clipboard arboard-error flow, tools
terminal closure, workspace capability tail), and `cargo update` of h2
(RUSTSEC-2026-0258) and webbrowser (RUSTSEC-2026-0257) so `cargo deny
check advisories` passes again.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KSy9S31pZNWXtRZNVJ1sDf
Port of upstream grok-build 1.0.9. A bare positional http(s):// URL
with no transport flag was silently added as a stdio command whose
"command" was the URL. It now infers the HTTP transport with a notice;
extra args, --env, legacy --command/--url, and every explicit flag keep
their prior meaning, and scheme-less URL-looking commands still stay
stdio with the existing warning.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KSy9S31pZNWXtRZNVJ1sDf
The canonical repo is git.zacharyzhang.com now, so every URL a user can
actually reach had to move with it.
Self-updater: `PRODUCTION_ENDPOINTS.update_base_url` targets Gitea's
`/api/v1/repos/.../releases`, which serves the same wire format GitHub's
releases API did — `Release`/asset deserialisation is unchanged. The alpha
channel requests `?per_page=30&limit=30` because GitHub reads the page size
from `per_page` and Gitea from `limit`, and each ignores the other's, so one
URL stays correct on either.
Installers: same API base, and the documented one-liners become
`https://kigicli.dev/install.{sh,ps1}`. That domain's Worker proxies both
files from Gitea raw `main`, so the published install command survives any
future forge move without being reprinted everywhere. install.ps1 also drops
the GitHub-specific `Accept: application/vnd.github+json`.
Everything else user-facing: `/feedback` and the shell's feedback fallback
point at the Gitea issue tracker, `/docs` at the Gitea-rendered README, and
web_fetch's User-Agent at kigicli.dev. SECURITY.md now routes reports to the
issue tracker with a warning to withhold exploitable detail, because Gitea
has no equivalent of GitHub's private vulnerability reporting. Comments
naming `.github/workflows/release.yml` name `.gitea/` now.
Tests assert against these constants rather than literal URLs, so they
follow automatically; the one URL-shape assertion (production endpoints are
https) still holds.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Launching kigi in a non-project directory (~/Downloads, ~, /tmp — anywhere
`is_project_dir` rejects) leaves the agent view session-less behind the
project-picker question, which only a PLAIN prompt can open. Slash
commands still execute there, so `/model <name> <effort>` stashed its
switch in `deferred_model_switch` — a stash that assumes a create is in
flight — and with none pending it dangled forever with zero feedback:
the picker rendered, the user chose model and effort, and nothing
changed. Not a 0.1.10 regression: 0.1.9 pty-reproduces identically; the
report correlated with the upgrade only because every earlier launch
happened to be from a project directory.
Apply the QueueCommand precedent ("queued slash work bypasses the
picker, so create the deferred session or it never drains") to both
deferral sites — Action::SwitchModel in the router and
set_default_model's no-session branch — via
skip_picker_and_create_session, whose in-flight guard already makes it a
no-op while a create is pending, so the racing-create case is unchanged.
SessionCreated then applies the stash through the existing
apply_deferred_model_switch path; pty-verified end-to-end from
~/Downloads (session created, model changed, effort applied).
The hardcoded Codex catalog advertised `ultra` for gpt-5.6-sol and
gpt-5.6-terra, so selecting it sent `reasoning.effort = "ultra"` and the
Responses endpoint answered 400 with its real menu, which ends at `max`.
The tier was kigi's invention: the enum documented it as codex-only, the
catalog was its only producer, and the upstream model snapshot never
listed it. Removing the variant as well as the catalog entries means
`/effort ultra` is rejected at the TUI instead of parsing and failing on
the wire; a persisted `ultra` degrades to the model default through
`lenient_reasoning_effort_opt`, as designed for vocabulary changes.
kigi allowed loopback unconditionally and missed several non-public
ranges, and the SSRF check ran only on the initial URL.
Policy (ssrf.rs):
- loopback is blocked unless `[toolset.web_fetch] allow_local` (or
KIGI_WEB_FETCH_ALLOW_LOCAL) is on, AND the URL names it explicitly,
so a public name resolving to loopback stays blocked (DNS rebinding)
- add 0.0.0.0/8, 100.64/10, 192.0.0.0/24, TEST-NET-1/2/3, 198.18/15,
240/4, IPv6 site-local and documentation prefixes
- inherit the IPv4 verdict through mapped, compatible, NAT64 and 6to4
wrappers; network-specific NAT64 prefixes remain uncovered (see doc)
Plumbing (client.rs), where the exploitable half lived:
- re-check every redirect hop, not just the first
- compare hosts exactly; a `www` sibling has its own A records, so it
is a cross-host redirect rather than an auto-followed hop
- run the check before the fetch service, so a blocked URL is never
posted to an endpoint that egresses elsewhere
- exempt explicit local hosts from the https upgrade and from the
single-label filter, and re-upgrade each followed hop
Wiring: allow_local reaches WebFetchParams from both construction
paths; documented in the config guide and the README env table.
Ports kimi-code's AgentSwarm: a `prompt_template` containing `{{item}}`
expanded over an `items` list into up to 128 subagents, run to completion
and returned as one aggregate. Kigi already exceeds upstream on planning,
verification, isolation and merge via /graph; what it lacked was cheap
immediate fan-out. Entirely client-side — no new backend surface.
The engine is three pure pieces plus a runner: `plan` validates and
expands (every fault reported before a single member starts — a
half-launched swarm is expensive to unwind), `schedule` is the launch
ramp as testable arithmetic, `run` drives it against the existing
`SubagentBackend`. Reuses the single-spawn coordinator rather than
inventing a batch API.
Load-bearing decisions, each the result of a defect found in review:
- `backgrounded` is its own outcome. A member that outlives the 600s
foreground budget is detached by the coordinator and KEEPS RUNNING;
reporting it as failed invites the model to relaunch its item, putting
a second agent on the same files. It is never offered for resume.
- `InFlightGuard` cancels live members on Drop. Send-now cancels the turn
WITHOUT cancelling subagents and aborts the task; the dropped receivers
read as "parent gone" and each child re-attaches itself. There is no
cooperative path to use instead — `Cancellation` is constructed nowhere
in the tree — so Drop is the only seam that fires.
- Retries and wall clock are both bounded. The swarm blocks the caller's
turn, so every wait needs a ceiling it cannot argue past; stragglers at
the deadline are reported as still-running, with their ids.
- `ToolKind::AgentSwarm` is its own variant: `TemplateRenderer`'s
`by_kind` map holds one tool name per kind, so sharing `Task` would
silently redirect `${{ tools.by_kind.task }}` in other tools' prompts.
- An explicitly requested model that cannot be validated is refused, as
the task tool already does — one loud error beats `items.len()` quiet
ones. Depth stays capped at 1: upstream's unlimited nesting is a
hazard, not a feature.
- `SubagentResult.rate_limited` is classified where the typed ACP error
code is still in hand; a scheduler re-deriving it from a formatted
string would stop adapting the day the wording changed.
- Aggregate output is clamped per member (head+tail, loss stated):
native tool output is truncated nowhere downstream.
42 agent_swarm tests. The fake backend awaits, so the concurrency and
ordering assertions can actually fail; the cap test also proves the
fixture can exceed the cap.
On Windows, crossterm's console backend never emits Event::Paste: a
terminal paste arrives as a per-character key burst that the event loop
reassembles with timing heuristics. Three of its bounds split real
pastes into fragments:
- the 10 ms continue window is below one Windows scheduler quantum
(~15.6 ms), so a routine mid-burst gap ended collection early;
- the 5000-event safety cap truncated any paste past ~5 KB;
- the 2 ms detection window missed bursts whose second chunk lagged,
so collection never started.
Each fragment became its own synthetic paste. The paste chip then held
only the first fragment, and pasting again could never byte-equal the
chip content, so repaste-to-expand inserted a duplicate instead of
expanding — while macOS worked, because the unix parser buffers a
bracketed paste to the end marker and always delivers one whole event.
Widen the continue window past one quantum (25 ms), raise the cap above
any real paste (200k events), and skip the detection window entirely
when the batch already holds a >=8-key burst, which typing and
auto-repeat never produce. Unix paths are untouched: batches containing
a real Event::Paste never enter this reassembly.
Covered by a paused-clock test that trickles a burst tail with
one-quantum gaps and asserts it reassembles into a single paste.
Sweep every first-party crate source (1956 .rs files) to the project comment
guidelines: delete redundant restatements, decorative banners, change
narration, and end-of-line comments; keep and tighten the crucial ones
(invariants, bug rationale, SAFETY blocks, ported-source attribution).
No functional code changed. Every edit is proven comment-only against the
prior tree by a comment-stripping lexer (string/char/raw-string aware) plus a
separate doctest-fence check. Where removing a comment made rustfmt or clippy
want to re-lay-out adjacent code, the minimal triggering comment is restored so
code tokens stay byte-identical.
Gates green: cargo fmt --all --check (0 diffs), cargo check and cargo clippy
--workspace --all-targets (0 warnings).
Adds scripts/check_codegen_comment_guidelines.py — the enforcement gate for
these guidelines (flags banners, end-of-line comments, change narration, and
commented-out code).
Persist-failure ≠ switch-failure. The default_model rollback arm re-ran
set_default_model_inner(prev) AND issued a reverse SwitchModel whenever
the config.toml write failed — the only mechanism in the codebase that
deliberately re-shows the ORIGINAL model after a successful pick. On
Windows, where AV/indexer file locks routinely failed that write (until
27d009c), every /model selection appeared to not take.
The session switch succeeds independently and reports its own failures
via handle_switch_model_complete; a disk-persist failure now keeps the
live model, logs, and surfaces only the 'Could not save' toast — the
same policy PersistPreferredModel already ships ('still active for this
session').
Verified: kigi-tui 6874 tests green, clippy clean.
The shell stamps meta.provider (platform display name via
parse_managed_model_key) on every managed {platform}/{model} catalog
entry in to_acp_model_info; user-defined [model.*] entries stay
provider-less. The /model dropdown surfaces it in the description column
(a model's own description still wins), so the picker reads as 'choose a
model from your connected providers'.
Verified: kigi-shell 5261 + kigi-tui 6873 tests green, clippy clean.
A required-args slash command submitted bare (/model, or /m) ran straight
into its usage error. The completeness contract already existed —
is_command_complete's documented 'Blocks' row — but had zero non-test
callers; both dispatch paths ran the command unconditionally.
Both the session prompt path and the dashboard dispatch box now consult
is_command_complete before running: an incomplete required-args command
re-opens the input as '/{command} ' with the cursor in the args phase, so
the existing suggestion dropdown lists the choices (for /model: the
catalog — by construction the connected providers' models, after
1bb10ef). Generalizes to every future required-args command; no new UI.
Verified: kigi-tui 6872 tests green, clippy clean.
/login previously fired the resolved method's flow immediately — there was
no way to see providers or their status. It now lands on the provider
picker; already-connected providers show a green 'connected' badge in the
key column.
Shell: initialize() probes stored credentials once (primary session flag,
auth.json oauth/<provider> scopes, resolved platform keys env>auth.json>
config) and stamps _meta.connected on each advertised method
(connected_method_ids + stamp_connected_meta, pure and unit-tested).
Display state only — never an authorization input.
TUI:
- PendingMenuItem::connected() reads the badge from method meta; the
picker renders it green (accent_success), replacing the shortcut hint.
- New Action::OpenLoginPicker: /login shows the picker; mid-session it
stashes the view like dispatch_login, and starts no flow by itself.
- Mid-session picker: last row reads 'Cancel' and dispatches CancelLogin
(clicking it must not exit the app); Esc also returns to the session.
- After a successful login, the just-authenticated method is stamped
connected in the TUI's advertised-methods copy (auth_in_flight_method →
AuthComplete), so a later /login shows the badge without re-initialize.
Verified: kigi-shell 5256 + kigi-tui 6870 tests green, clippy clean.
Root cause: PendingMenuItem::Login carried only a label, so every provider
row collapsed to the id-less Action::Login, and dispatch_login resolved
the FIRST advertised interactive method — the Kimi device flow. Selecting
Grok/Claude/Copilot/Codex all opened kimi.com. (The shell side was already
correct: authenticate() dispatches each method id to its own OAuth flow.)
- PendingMenuItem::Login now carries the advertised method id (None only
on the no-interactive-method fallback row).
- New Action::LoginWith(AuthMethodId); the picker dispatches it with the
row's own id. Action::Login keeps its meaning (resolved/default method)
for /login, auto-login, and re-auth.
- dispatch_login_with resolves the id against the advertised methods and
FAILS CLOSED on an unknown id — no silent first-method fallback — then
adopts the method's label and start mode.
Tests: picker rows pinned to their method ids; LoginWith(claude-pro-max)
must authenticate with claude-pro-max even when kimi-code was previously
resolved; unknown ids surface an error and start nothing.
Verified: kigi-tui 6867 tests green, clippy clean.
Root cause (issues: unscrollable list + half-blocked moon): the stacked
welcome layout gave the menu one Length row per item. With ~30 advertised
providers the vertical layout overflowed and the constraint solver
squeezed every Length — clipping the logo — while rows past the fold were
silently unreachable.
- WelcomeLayout::compute_inner caps the menu to the rows genuinely left
over after logo/prompt/version, so the chrome never gets squeezed.
- render_menu is now a minimal-scroll viewport: it scrolls only when the
selection exits it (stable under hover — no re-centering feedback
loop), draws the picker-style scrollbar, and returns index-aligned hit
rects (zero Rect for off-screen rows) plus the offset, which AppView
feeds back next frame.
- Mouse wheel moves the login-picker selection (clamped, not wrapping).
Test: pending_menu_scrolls_and_never_clips_the_moon renders the full
method list at 40 rows and asserts the whole moon (10 braille rows), the
version badge, and that selecting Quit scrolls it into view.
Verified: kigi-tui 6864 tests green, clippy clean.
29th platform `openai-codex` (uses_oauth, Responses wire). PKCE-localhost login at
auth.openai.com (client app_EMoamEEZ73f0CkXaXp7hrann, redirect localhost:1455/auth/
callback, form token exchange, fresh-random state) reusing the claude-pro-max flow;
OAuthFlow::PkceLocalhost gained a redirect_path and OAuthConfig an authorize_extra
(empty elsewhere, so claude/xai/copilot authorize URLs stay byte-identical).
Codex-specific: the access token is a JWT carrying chatgpt_account_id, which becomes
the `chatgpt-account-id` inference header. It is derived STATELESSLY from whichever
bearer rides each request (so a rotated token needs no persisted field), and BOTH
login and refresh fail fast when the claim is absent — gated on the explicit
OAuthConfig.requires_chatgpt_account_id fact, never inferred from the token-body
encoding (a plain form endpoint is the OAuth norm and must not inherit this).
Inference rides the existing Responses wire at chatgpt.com/backend-api/codex →
/responses, with codex headers (chatgpt-account-id, originator, OpenAI-Beta
responses=experimental, codex UA) gated on SamplerConfig.openai_codex so API-key
`openai` stays byte-identical; store:false was already the global Responses default.
Catalog is HARDCODED (no live endpoint exists for this backend; read from the
official Codex CLI's model cache): gpt-5.6-sol/terra/luna + gpt-5.5, ctx 272000,
each with its real reasoning levels (low..ultra — ReasoningEffort gained Ultra).
Excluded: gpt-5.3-codex-spark (supported_in_api=false), gpt-5.4/-mini and
codex-auto-review (hidden) — they would list but fail at inference. The fetch
short-circuits before any HTTP; Kigi never shells out to the codex CLI or reads
~/.codex.
Security review fixes: redact any `account-id` header from request logs (it was
reaching debug logs), strict 3-segment JWT check (fail closed), refresh no longer
fails open on a missing claim. Inherits leak-safe pooled routing (scope
oauth/openai-codex) — never the Kimi token. Full gate green (234 suites, 0 warnings).
28th platform `github-copilot` (uses_oauth, ChatCompletions wire). Two-stage auth:
RFC-8628 GitHub device flow (client Iv1.b507a08c87ecfe98, scope read:user, errors
in a 200 body) mints the DURABLE github token; a GET api.github.com/copilot_internal/
v2/token exchange re-mints the SHORT-LIVED copilot token. Persisted as key=copilot
token, refresh_token=github token, expires_at=copilot expiry; the "refresh" is a
copilot-token re-mint (not a refresh_token grant), dispatched via
OAuthTokenBody::GithubCopilotExchange in the generic refresher.
VS Code editor-identity headers on /models + /chat/completions, gated on
SamplerConfig.github_copilot / PlatformId::sends_copilot_editor_headers() so every
other ChatCompletions provider stays byte-identical. Live /models filtered
(parse_github_copilot_listing) to the openai-completions-served models: keep iff
model_picker_enabled && policy.state!="disabled" && tool_calls!=false AND not a
claude-4.x/5.x (messages) or gpt-5/oswe/mai- (responses-only) id — those need
per-model wire routing (documented debt), excluded rather than mis-routed.
Inherits the leak-safe pooled routing (scope oauth/github-copilot); its bearer/
refresh/api_key never touch the Kimi token (regression test added). Fail-fast on
an out-of-range copilot expires_at (would otherwise silently 401 mid-session).
Adversarial security review: GO, no CRITICAL/HIGH. Known limitation: Pi's
per-model policy-enablement POST is not ported (documented in AGENTS.md).
27th registry variant, 2nd subscription-OAuth provider. Log in with a Claude
Pro/Max subscription via PKCE authorization-code + S256 (loopback callback on
127.0.0.1:53692, with a manual code-paste fallback), then use it against
api.anthropic.com — reusing the existing Anthropic Messages wire + Anthropic
listing + the multi-provider OAuth foundation (dbce6bf). Sourced from Pi
(earendil-works/pi auth/oauth/anthropic.ts): client 9d1c250a..., authorize
claude.ai/oauth/authorize, token platform.claude.com/v1/oauth/token, scope
'…user:inference user:sessions:claude_code…'.
New machinery (foundation handles token routing — claude-pro-max is a
uses_oauth platform so its bearer/refresh/api_key already route to its own
pooled manager, never Kimi):
- OAuthConfig gains flow{DeviceCode|PkceLocalhost} + token_host + token_body
{Form|JSON}; xai/kimi rows unchanged (DeviceCode/Form).
- auth/oauth_pkce.rs: PKCE S256 wire — loopback listener with STRICT state
validation (CSRF, fail-closed), manual-paste fallback, JSON code→token
exchange + rotating-refresh. Never logs code/verifier/tokens.
- Messages OAuth adaptation gated on SamplerConfig.anthropic_oauth (true only
for a claude-pro-max managed key): Authorization: Bearer + anthropic-beta
oauth + user-agent claude-cli + x-app cli, and the required 'You are Claude
Code' system prefix. API-key anthropic/minimax Messages requests are
BYTE-IDENTICAL (regression-guarded).
- Live /models under the OAuth Bearer + oauth-beta headers (Anthropic listing,
enriched from models.dev anthropic); persistent 401 → 0 models + WARN, NO
hardcoded fallback list (honest failure).
Adversarial review: no blocking findings (secret handling, CSRF/state, the
anthropic_oauth gate, token routing, non-regression all CONFIRMED). Full gate
green. Registry at 27; picker updated. Residual (unverifiable without a real
Claude Pro/Max account): whether GET /v1/models accepts the OAuth bearer, and
the real endpoint's acceptance of the OAuth Messages request.
First subscription-OAuth provider beyond Kimi Code (26th registry variant).
Log in with a Grok/SuperGrok/X subscription via RFC-8628 device-code OAuth
(auth.x.ai), then use it against api.x.ai/v1 — reusing the existing xai wire
(ChatCompletions + OpenAI listing + Passthrough + restrict + models_dev_id
xai). Sourced from Pi (earendil-works/pi auth/oauth/xai.ts): client
b1a00492..., scope 'openid profile email offline_access grok-cli:access
api:access', standard Bearer (no x-xai-token-auth).
Foundation (generalizes Kigi's Kimi-singleton OAuth to per-provider, root
cause, not a patch):
- Registry: OAuthConfig on PlatformSpec (client_id/host/device+token
paths/scope/scope_key); XAI_OAUTH_CONFIG + XAI_GROK_SPEC (uses_oauth, method
id 'xai-grok', an interactive login after kimi-code).
- Generic device-code wire (auth/oauth_device.rs) + GenericDeviceRefresher,
sharing the RFC-8628 core with Kimi; Kimi's bespoke flow is byte-identical
(X-Msh headers, KIMI_CODE_OAUTH_SCOPE, keyring gating unchanged).
- Per-provider AuthManager via a process-global pool (auth/oauth_registry.rs):
build-on-demand with start_proactive_refresh, keyed by scope. The session
resolves the AuthManager for the ACTIVE model's platform for bearer/refresh/
401-recovery/api_key — an oauth-platform model always uses its OWN token,
never the primary.
- Live /models under OAuth; base routes oauth().is_some() -> platform.base_url()
(kimi-code stays on proxy_url).
Security: adversarial review + a systematic token-leak audit found and closed
FIVE channels where the primary Kimi token could reach api.x.ai (bearer
resolver, api_key stamping, aux summary/classifier/image-describe models, and
subagent model-override). Each fix routes through the platform-aware resolver
(the oauth model's pooled token or None, NEVER the primary) and is revert-to-red
verified. No access/refresh token is ever logged.
Registry at 26; picker updated (xai-grok interactive login row); TUI
context-window already auto-updates per model. Full gate green (234 suites,
fmt, clippy -D warnings, deny). GPT/Claude/Grok officially permit third-party
subscription use.
Providers 21-22 (24th & 25th registry variants), sourced from Pi
(earendil-works/pi). Pi drives MiniMax through its Anthropic-COMPATIBLE
surface (baseUrl .../anthropic), so Kigi reuses the existing Anthropic
Messages machinery (wire_api=Messages, listing=Anthropic, key_header=XApiKey
x-api-key+anthropic-version) rather than the OpenAI path. Global:
api.minimax.io/anthropic, MINIMAX_API_KEY, models.dev minimax. China:
api.minimaxi.com/anthropic, MINIMAX_CN_API_KEY, models.dev minimax-cn.
The base carries the /v1 suffix (.../anthropic/v1) since Kigi appends bare
paths → listing .../anthropic/v1/models?limit=1000, inference
.../anthropic/v1/messages (matches the live-probed x-api-key-gated endpoint).
restrict_to_enriched=FALSE: the 7 MiniMax-M* models are clean (no pollution)
and restrict would drop launch-day models not yet in models.dev.
Also HARDENS parse_anthropic_listing to tolerate a bare array in addition to
the {data:[...]} envelope (mirrors parse_openai_listing's sniff that Together
taught us) — so MiniMax's Anthropic-compatible /models can't silently empty
the catalog if it serves a bare array. A bare object without data still errors.
Review found no defects (5 areas CONFIRMED incl. the /v1 non-doubling, the
additive parser change, restrict=false rationale). Residual (logged): the live
200 body / anthropic-version acceptance is unverifiable without a key; the
bare-array tolerance + restrict=false hedge most shapes.
Tests: e2e mocks the x-api-key-gated Anthropic listing (proves the auth header
+ enrichment + keying under minimax/); both validation tests reject 401 with
the per-variant console host; new parser test covers envelope + bare array +
bare-object-errors. Registry at 25; picker 26 rows.
Providers 19-20 (22nd & 23rd registry variants), sourced from Pi
(earendil-works/pi). Pi's xiaomi.ts / xiaomi-token-plan-cn.ts use plain
openAICompletionsApi (no thinking dialect) → Kigi Passthrough. Global: MiMo
at api.xiaomimimo.com/v1, XIAOMI_API_KEY, models.dev xiaomi. China token plan:
token-plan-cn.xiaomimimo.com/v1, XIAOMI_TOKEN_PLAN_CN_API_KEY, models.dev
xiaomi-token-plan-cn. Both Bearer + OpenAI listing + ChatCompletions +
restrict_to_enriched; /models auth-gated → validator.
id-match proven vs Pi's static ids (mimo-v2.5-pro, mimo-v2-flash, ...). The
CN token plan lists 4 mimo TTS models (tool_call=false); restrict's tool_call
cut drops them, keeping only the 3 chat models — the e2e proves this
non-vacuously with the real mimo-v2-tts. Review found no defects.
Registry at 23; picker 24 rows (welcome picker verified rendering all rows at
a taller viewport).
Providers 17-18 (20th & 21st registry variants), sourced authoritatively
from Pi (earendil-works/pi), the open-source agent whose provider list is
being mirrored. Pi's zai.ts / zai-coding-cn.ts use plain openAICompletionsApi
(NO special thinking dialect — overturns the matrix's 'thinking:{type} → new
dialect' concern), so Kigi maps them to Passthrough. Global: api.z.ai/api/
coding/paas/v4, ZAI_API_KEY, models.dev zai-coding-plan. China (Zhipu
BigModel): open.bigmodel.cn/api/coding/paas/v4, ZAI_CODING_CN_API_KEY,
models.dev zhipuai-coding-plan. Both Bearer + OpenAI listing + ChatCompletions
+ restrict_to_enriched; /models is auth-gated → validator.
id-match is PROVEN (not just assumed like Qwen): Pi's static model ids
[glm-4.5-air, glm-4.7, glm-5-turbo, glm-5.1, glm-5.2, glm-5v-turbo] are
byte-identical to the models.dev zai-coding-plan keys, all tool_call=true, so
restrict keeps every model with no silent-empty risk. Review found no defects.
GLM thinking is not lost (reasoning_content is parsed regardless of dialect).
Tests: e2e proves enrichment-supplied context + non-vacuous restrict (a
non-enriched wire model is dropped) + Passthrough; both variants' validation
tests hit /models and assert the per-variant console host (z.ai vs
open.bigmodel.cn). Registry at 21; picker 22 rows.
Also fixes the welcome login-picker test for the now-taller menu (renders at
a taller viewport to verify content coverage) and logs the real menu-overflow
UX debt: the picker clips rows past the fold with no scroll (q/l shortcuts
still work; only shown when unauthenticated) — deferred to its own cycle.
Provider 16 (19th registry variant). Same endpoint + models + Kimi dialect
as the existing OAuth kimi-code platform (api.kimi.com/coding/v1 via the
KIGI_CODE_BASE_URL override), but authenticated with a static KIMI_API_KEY
instead of the device flow — for users who have a Kimi For Coding key rather
than an OAuth subscription. Bearer, OpenAI listing, ChatCompletions,
ChatCompat::Kimi, wire_serves_metadata=true (Kimi /models self-serves
context/thinking), restrict_to_enriched=false (clean 3-model catalog).
/coding/v1/models is auth-gated (401) so it doubles as the validator.
No collision: KIMI_API_KEY was previously unused (grep-verified), and the
house BYOK reads only KIGI_API_KEY/XAI_API_KEY/legacy. kimi-code (OAuth) and
kimi-coding (static key) are independently gated (OAuth-token vs key) and
their models get distinct managed keys (kimi-code/k3 vs kimi-coding/k3) — a
user with both simply sees each Kimi model twice; no dedup collision, no crash.
Review (6 areas): no blocking defects; confirmed the spec correctly mirrors
KIMI_CODE_SPEC (differing only in uses_oauth/api_key_envs/console_host/labels)
and the coexistence is benign. Strengthened the e2e's dialect assertion (Kimi
is the default ChatCompat, so it did not discriminate a parse failure) by
also asserting parse_managed_model_key attributes the key to KimiCoding.
Tests: e2e proves wire-served context (1_048_576 from the wire) with the
models.dev fetch SKIPPED (all-wire-metadata provider, .expect(0)), bare-id
round-trip under kimi-coding/, Kimi dialect; validation test rejects a 401
from /models. Registry at 19; picker 20 rows; snapshot already bundles
kimi-for-coding.
Providers 14-15 (17th & 18th registry variants), Alibaba DashScope
compatible-mode. Global: token-plan.ap-southeast-1.maas.aliyuncs.com,
QWEN_TOKEN_PLAN_API_KEY, models.dev alibaba-token-plan. China:
token-plan.cn-beijing.maas.aliyuncs.com, QWEN_TOKEN_PLAN_CN_API_KEY,
alibaba-token-plan-cn. Both Bearer + OpenAI listing + ChatCompletions +
Passthrough (stream_options.include_usage is documented-supported).
/models is auth-gated (401 without a key) so it doubles as the validator;
metadata from models.dev enrichment. The token plan is a multi-vendor
catalog (deepseek/kimi/minimax/glm/qwen); restrict_to_enriched keeps the 15
tool-calling chat models and drops the 4 qwen-image/wan image generators.
Review downgraded two flagged concerns: the enable_thinking non-streaming
400 cannot occur (Kigi never issues non-streaming ChatCompletions in
production — all inference streams), and Qwen thinking is NOT invisible
(reasoning_content is parsed regardless of the Passthrough dialect). No
defects. Residual (logged): restrict does an exact id-match of live /models
ids vs the models.dev keys; a mismatch fails safe (0 models) — verify with a
real key. Snapshot already bundles both providers (regenerated in ebf1105).
Tests: global e2e proves enrichment-supplied context (wire carries none),
non-vacuous tool_call restriction (qwen-image dropped), bare-id round-trip,
Passthrough; both variants' validation tests hit /models (401 reject) and
assert the correct per-variant console host. Registry at 18; picker 19 rows.
13th provider (16th registry variant). Also reconciles a naming collision
the matrix flagged: this fork is house-branded "xai" (cf. xai.dev metadata,
KIGI_CODE_XAI_API_KEY legacy env), so XAI_API_KEY + method xai.api_key were
the GENERIC house BYOK, not x.ai/Grok. The provider table wants xai/XAI_API_KEY
for Grok.
Resolution (user-approved): XAI_API_KEY now keys the x.ai/Grok provider; the
house BYOK primary env moves to KIGI_API_KEY, keeping XAI_API_KEY and
KIGI_CODE_XAI_API_KEY as back-compat fallbacks (read_xai_api_key_env checks
KIGI_API_KEY first). The xai.api_key method id is unchanged (persisted-session
compat); the platform method id is the bare "xai", distinct from it.
xAI spec: api.x.ai/v1, Bearer, OpenAI listing + ChatCompletions, Passthrough
(docs confirm stream_options.include_usage accepted). /v1/models is minimal
(ids only) and requires auth, so it doubles as the key validator (401 on bad
key, no override) and metadata comes from models.dev enrichment. Live ids
match the models.dev "xai" keys byte-for-byte, so restrict_to_enriched keeps
the 5 tool-calling chat models (grok-4.5/4.3/4.20-0309-*/build-0.1) and drops
the grok-imagine-* generators + the non-tool multi-agent model. Snapshot
regenerated to include the xai provider (was stale; gen script already listed
it in TARGETS).
Env migration is comprehensive to avoid keying the xai platform (which would
trigger a live api.x.ai fetch) or leaving house-key reads stranded: routed
the trace CLI resolver + acp_agent/auth.json bridge + paste-key ext handler
through the new primary; moved all leader/pager/e2e harness setters to
KIGI_API_KEY; made every house-key isolation test unset KIGI_API_KEY too;
updated user-facing hints to name KIGI_API_KEY.
Tests: e2e proves enrichment-supplied context (wire carries none), non-vacuous
tool_call restriction, bare-id round-trip under xai/, Passthrough; validation
tests hit /models (401 reject, 200 accept); house_env_var_takes_precedence_over_xai
pins the new precedence. Registry at 16; picker 17 rows; 4 auth arrays + xai.
Review (16 findings, all fixed): caught a missed else-branch env clear in the
paste-key handler (would leak the house key past a clear) and a non-hermetic
credential-priority test; both fixed.
12th provider. API-key via AI_GATEWAY_API_KEY, Bearer, OpenAI listing +
ChatCompletions, Passthrough dialect. Second wire-metadata provider but
takes the enrichment path instead: Vercel serves context under
context_window, which WireModel ignores (reads context_length), so
wire_serves_metadata=false + restrict_to_enriched pulls context/limits
from the models.dev "vercel" snapshot (302/306 live ids match snapshot
keys byte-for-byte, so restrict keeps essentially the whole catalog).
/models is public (200 for any key), so login validation targets
/credits (key_validation_path) which 401s on a bad bearer — avoids
false-accepting invalid keys against the public listing.
Tests: e2e proves enrichment-wins (wire context_window=999 distinct from
enrichment context=400000, asserts 400000) and non-vacuous tool_call
restriction; validation test proves /credits (not /models) is hit.
Registry at 15 (ordinal/VARIANT_COUNT/ALL), 4 auth arrays + 16-row picker.
The 14th registry row: id "nvidia", NVIDIA_API_KEY > auth.json "nvidia"
scope, https://integrate.api.nvidia.com/v1 with KIGI_NVIDIA_BASE_URL
override, Bearer, ChatCompletions, enrichment-backed metadata
(models_dev_id nvidia — the quirk matrix's earlier 'absent' claim was
wrong; models.dev has 84 nvidia models), restrict_to_enriched=true (the
NIM listing mixes chat/embedding/rerank/vision/image; keep the 45
tool-calling chat models). Slashed org/model ids
(nvidia/meta/llama-3.3-70b-instruct) round-trip via the first-slash split;
the native id rides the wire.
NIM exposes raw vLLM behavior and stream_options support varies per model
(some strict vLLM backends 4xx on it), so chat_compat=StrictOpenAi strips
stream_options — streaming works across the whole fleet, usage falls back
to estimation. Snapshot reasoning models carry no effort menus, so kigi
sends no reasoning_effort (which an unsupported strict validator would
400 on). Review: no defects. Logged note: a key lacking the org 'Public
API Endpoints' permission passes /models validation but 403s on chat
(user-fixable edge case).
The 13th registry row: id "cerebras", CEREBRAS_API_KEY > auth.json
"cerebras" scope, https://api.cerebras.ai/v1 with KIGI_CEREBRAS_BASE_URL
override, Bearer, ChatCompletions, enrichment-backed metadata
(models_dev_id cerebras).
Cerebras' catalog is all chat LLMs (no embedding/tts pollution) and its
/models is minimal (ids only), so restrict_to_enriched=FALSE: keep every
live model, enrich the known ones (context + effort menus low/medium/high),
unknown ones keep the default context. The e2e pins this enrich-without-
restrict path (new — prior enrichment providers all used restrict=true).
Review caught a likely-DOA defect: Cerebras uses strict
additionalProperties:false validation (confirmed 400-rejecting store,
maxTokens, thinking, nested reasoning_content), and stream_options is not
in its schema — so Passthrough (which keeps the stream_options.include_usage
kigi injects on every streaming request) would very likely 400 all
streaming. Generalized ChatCompat::Mistral -> ChatCompat::StrictOpenAi
(serde alias "mistral" keeps pre-rename persisted sessions loading), which
strips stream_options + private fields for any strict OpenAI-compat
validator; both Mistral and Cerebras now map to it. Future strict-validator
candidates (NVIDIA/Azure/Xiaomi/OpenCode) noted for the same check.
reasoning_effort (incl. "none") passes through; /v1/models requires auth
so key validation works; console cloud.cerebras.ai.
The 12th registry row: id "together", TOGETHER_API_KEY > auth.json
"together" scope, https://api.together.xyz/v1 with KIGI_TOGETHER_BASE_URL
override, Bearer, ChatCompletions + Passthrough, enrichment-backed
metadata (models_dev_id togetherai) with the tool-calling listing
restriction (Together's listing mixes chat/embedding/rerank/image types).
Together's GET /v1/models returns a BARE JSON ARRAY, not the OpenAI
{object:list,data:[]} envelope. New shared parser parse_openai_listing
tolerates both shapes (sniffs the top-level [ vs { for accurate
diagnostics); every OpenAI-listing provider now routes through it, with
byte-equivalent envelope behavior (verified: Groq/Google/OpenRouter
unchanged) and non-silent errors. Together's org/Model ids match the
togetherai snapshot keys exactly (verified), so restrict_to_enriched keeps
the ~27 tool-calling models without the id-shape trap.
Review: ship-ready, shared-parser change proven strictly-additive and safe,
registry/e2e/dialect all correct. Backlog logged: kigi ignores the wire
per-model field, so a live Together chat model absent from
models.dev is dropped until indexed — a future wire- filter would
unlock the fresh full catalog.
The 11th registry row and the first THIRD-PARTY wire_serves_metadata=true
provider: id "openrouter", OPENROUTER_API_KEY > auth.json "openrouter"
scope, https://openrouter.ai/api/v1 (note /api/v1) with
KIGI_OPENROUTER_BASE_URL override, Bearer, OpenAI listing +
ChatCompletions + Passthrough.
OpenRouter's public /models serves context_length for every model
(verified live: 340/340), so it needs NO enrichment: models_dev_id=None,
wire_serves_metadata=true, restrict_to_enriched=false. An OpenRouter-only
user makes zero models.dev calls; context comes straight from the listing.
Slashed ids (anthropic/claude-opus-4.8) round-trip through the managed key
via the first-slash split; the native id rides the wire. The e2e pins all
of this with the models.dev refresh disabled.
Review-confirmed defect fixed (and independently re-verified with live
curls): OpenRouter's /models is PUBLIC — GET /models returns 200 for ANY
key — so login key-validation would false-accept a bad key, deferring the
failure to the first chat 401. New spec field key_validation_path lets a
public-listing platform validate against an auth-requiring endpoint;
OpenRouter uses /key (401s for bad keys). Reusable for Vercel (also
public). Tests pin the /key validation and no regression to the default
/models path.
Gate caught a fixture regression: the kimi_import test used openrouter.ai
to represent a CUSTOM provider, which now correctly dedupes to the builtin
OpenRouter — moved the fixture to a reserved llm.example.test host that no
future platform can shadow.
The 10th registry row: id "google", GEMINI_API_KEY > auth.json "google"
scope, https://generativelanguage.googleapis.com/v1beta/openai (Gemini's
OpenAI-compatibility shim) with KIGI_GOOGLE_BASE_URL override, Bearer,
OpenAI listing + ChatCompletions + Passthrough, enrichment-backed
metadata (models_dev_id google), tool-calling listing restriction.
Review caught a ship-blocking defect: Gemini's compat /models returns
-PREFIXED ids (confirmed via Google's own cookbook), but the
models.dev snapshot keys and the chat endpoint use the BARE id. Without
normalization the enrichment lookup misses and restrict_to_enriched
silently empties the Gemini catalog (login works, zero models
selectable). A doc WebFetch had hidden this — the compat docs show bare
INPUT ids to retrieve/chat but never print the list OUTPUT.
Fix: new spec field strip_listing_id_prefix, applied in the fetch before
filter/enrich/keying. Google sets Some("models/") (defensive: a no-op if
an id is already bare, so correct regardless of the live shape); all other
rows None. The e2e now feeds the REAL prefixed listing ids and asserts
they survive as the bare managed key google/gemini-2.5-pro with the bare
id on the wire (chat rejects the prefix); a registry test pins the config.
Note: models.dev models Gemini reasoning as budget_tokens (not
effort-type), so no auto effort-menu — models still fully work; reasoning
is dynamic. Gemini compat applies default safety filters (no BLOCK_NONE).
The 9th registry row, pure Groq pattern: id "fireworks",
FIREWORKS_API_KEY > auth.json "fireworks" scope,
https://api.fireworks.ai/inference/v1 (note /inference/v1) with
KIGI_FIREWORKS_BASE_URL override, OpenAI listing + ChatCompletions +
Passthrough dialect, enrichment-backed metadata (models_dev_id
fireworks-ai) with the tool-calling listing restriction.
Fireworks native ids are deeply slashed (accounts/fireworks/models/glm-5p2);
the e2e pins the full round-trip: the managed key
(fireworks/accounts/fireworks/models/glm-5p2) parses back on the first
slash, and — the 404-risk property — the NATIVE id rides the inference
wire (entry.model and the resolved SamplerConfig.model) while the
fireworks/ prefix stays internal routing only.
Review (models.dev provider.toml + Fireworks docs): row facts confirmed,
registry integrity at 9, counts complete, e2e strong on all axes, zero
defects. One tradeoff logged as debt: restrict_to_enriched drops
fine-tuned/account-scoped deployed models (a headline Fireworks feature)
that can never be in models.dev.
The 8th registry row: id "mistral", MISTRAL_API_KEY > auth.json
"mistral" scope, https://api.mistral.ai/v1 with KIGI_MISTRAL_BASE_URL
override, enrichment-backed metadata with the tool-calling listing
restriction (embed/moderation/OCR noise).
Mistral is NOT a pure-pattern provider — an adversarial review found two
doc-confirmed blockers that no test exercises (no e2e covers a chat POST),
so the gate-green registry row alone would have shipped it DOA. A research
workflow pinned the exact wire shapes against the mistralai/client-python
SDK source (adversarially verified), then both were fixed:
1. stream_options 422: Mistral's strict Pydantic validator rejects the
stream_options.include_usage field kigi injects on every streaming
request (the SDK's request model has no such field). New
ChatCompat::Mistral dialect strips it (plus the kigi-private message
fields, like Passthrough). Streaming usage falls back to token
estimation.
2. Reasoning content arrays: Mistral reasoning models return content as
Union[str, List[ContentChunk]] on both streaming and non-streaming,
which the flat Option<String> path could not decode -> aborted turn.
A UNIVERSAL lenient deserializer (#[serde(from = "Raw..")] on
ChatResponseMessage + ChatChunkDelta) accepts string-or-array, routing
{type:text} chunks to the answer and the nested text of {type:thinking}
chunks to reasoning_content, tolerant of the OPEN chunk union (unknown
types ignored, never fatal). String content stays byte-identical for
every other provider (kimi/deepseek/groq/BYOK).
Review refuted all seven attack lines (no regression, no crash, exhaustive)
and flagged one coverage gap, now closed: a stream-consumer integration
test drives a full thinking -> transition -> answer chunk sequence and
proves it yields the same reasoning-sibling + assistant-answer result as
the reasoning_content string path.
Also folds a verified quirk matrix for all 23 remaining API providers into
providers-plan.md, tiered by real difficulty (self-enriching OpenRouter/
Vercel; bare-array Together listing; Messages-dialect MiniMax reusing the
Anthropic machinery; non-Bearer Azure/Bedrock; router wildcards; the OAuth
block).
The 7th registry row and the first pure-pattern cycle: id "groq",
GROQ_API_KEY > auth.json "groq" scope, https://api.groq.com/openai/v1
with KIGI_GROQ_BASE_URL override, OpenAI listing + ChatCompletions +
Passthrough dialect (Groq accepts the OpenAI-style reasoning_effort
scalar verbatim), enrichment-backed metadata with the tool-calling
restriction (the listing carries whisper/tts/guard noise — 8 of 15
enrichment entries are non-chat).
Review verdict: faithful pattern repeat, zero blocking findings — row
facts verified against live Groq docs, registry integrity at 7, e2e
proven strong on both axes (restriction + dialect mapping). Added the
recommended pin: managed keys split on the FIRST slash, so Groq's
provider-native slashed ids (openai/gpt-oss-120b and 10 more) round-trip
as groq/openai/gpt-oss-120b → (Groq, openai/gpt-oss-120b).
Also fixes a pre-existing test race this cycle surfaced: the enterprise-
endpoints test asserted moonshot's fixed base while non-serial, racing
serial tests that legitimately point KIGI_MOONSHOT_CN_BASE_URL at
wiremock; now serial + env-unset like its documented siblings. Two
display-only advisories logged as tracked debt (Groq's delta.reasoning
field invisible in the TUI; platform-generic rate-limit copy).
The 6th registry row: id "deepseek", DEEPSEEK_API_KEY > auth.json
"deepseek" scope, base https://api.deepseek.com (chat rides
{base}/chat/completions per official docs) with KIGI_DEEPSEEK_BASE_URL
override, enrichment-backed metadata (1M context, 384k output cap,
high/max effort menu).
Structural fix the cycle exposed: kigi's Kimi-specific body adaptation
ran UNCONDITIONALLY on every ChatCompletions request. New ChatCompat
dialect, declared per platform row and threaded through SamplerConfig,
ClientDefaults, and the session-persisted SamplingConfig (serde-default
Kimi keeps restored pre-field sessions and BYOK endpoints byte-identical;
production persist seams copy it; subagents inherit it):
- Kimi: full legacy pipeline (dispatch ≡ legacy pinned)
- DeepSeek: thinking:{type, reasoning_effort} per api-docs.deepseek.com
(server maps low/medium→high, xhigh→max itself; none disables; absent
leaves the server default)
- Passthrough: OpenAI-style reasoning_effort scalar untouched (unblocks
Groq and the rest of the OpenAI-compatible list)
Review-confirmed release blocker fixed: kigi replays Kimi's
reasoning_content (and its private model_id) on input assistant
messages — Kimi consumes these, but DeepSeek documents input
reasoning_content as prefix-mode-only (historically a 400) and other
providers don't know either field. The DeepSeek and Passthrough arms now
strip both; Kimi's own pipeline is untouched. Pinned on both message
shapes.
The 5th registry row: id "anthropic", ANTHROPIC_API_KEY > auth.json
"anthropic" scope, api.anthropic.com/v1 with KIGI_ANTHROPIC_BASE_URL
override, Messages dialect. Two new spec dimensions most future rows
reuse: ListingDialect (Anthropic's /v1/models wants x-api-key +
anthropic-version headers, ?limit=1000, and its own response shape) and
PlatformKeyHeader (Bearer vs x-api-key across listing/validation/
inference, with auth_scheme stamped onto entries).
The 2026 Anthropic listing serves real metadata: the adapter maps
max_input_tokens, per-level effort capabilities (low..max as the menu,
xhigh/max distinct), thinking/image flags — and enrichment fills only
genuine wire gaps (e2e pins wire-1M beating enrichment, and a zero
context filled to 200k).
Two review-confirmed defects fixed red-green:
- Output caps were dropped at three layers, so every sub-128K-output
model (64k Haiku, legacy models) would 400 on EVERY request against
the sampler's 128K max_tokens default. Wire max_tokens and enrichment
limit.output now flow to entry.max_completion_tokens.
- An explicit wire effort-decline was indistinguishable from wire
silence, letting enrichment inject effort menus pre-4.6 models reject
(adaptive thinking 400). The adapter now emits a decline sentinel
(support:false) that enrichment respects — proven end to end.
Also: the Messages client now sends anthropic-version (previously never
sent — real api.anthropic.com rejects such requests; pinned across all
three scheme/backend quadrants), key validation builds per-key-header
requests, missing listing data fails fast, empty-id ghosts drop with a
warning, kimi-import recognizes api.anthropic.com as built-in
automatically.
The 4th registry row: id "openai", OPENAI_API_KEY env > auth.json
"openai" scope (login picker/paste/validation all registry-generic —
zero TUI changes needed, pinned by the picker test), base
https://api.openai.com/v1 with KIGI_OPENAI_BASE_URL override, Responses
dialect via the new PlatformWireApi spec field, enrichment-backed
metadata (wire_serves_metadata=false).
OpenAI's GET /v1/models returns bare ids and is polluted with
tts/whisper/embeddings entries: the listing is restricted to
enrichment-known TOOL-CALLING models (review caught that membership
alone admitted models.dev-known embeddings models, which would 400 on
every agentic request; dropped ids are debug-logged for launch-day
diagnosability). Context windows, effort menus, display names, and
thinking capability come from the enrichment pipeline — wiremock e2e
pins the full contract: polluted live listing + models.dev →
one Responses-backed chat model with a 400k documented context window.
Responses max-effort wiring (closes the P0c-1 debt): canonical effort
rides a CreateResponseWrapper sidecar and patch_reasoning_effort writes
it onto the serialized body at both send sites (all seven levels pinned,
xhigh/max distinct, summary preserved); normalize_effort_echo drops
echoes async-openai's typed enum cannot represent at both the non-stream
and SSE parse seams; the dead typed to_responses_api converter is
deleted. Kimi/moonshot stay byte-identical (ChatCompletions untouched,
wire_api maps to the same default; kimi wire tests green).
kimi-import now recognizes ANY registry platform host as built-in
(was hardcoded moonshot), covering openai and future rows.
ZacharyZhang-NY
雷电芽衣