* feat: add codex sdk runner foundation
* feat: parse codex runtime events
* feat: expose codex runtime mcp tools
* feat: add codex llm runtime
* feat: wire codex llm backend
* test: avoid Array.fromAsync in codex runner test
* docs: document codex llm backend
* fix: tighten codex runtime config ownership
* fix: use codex sdk env and thread options
* fix: parse codex sdk event shapes
* test: add codex backend live smoke
* docs: clarify codex backend isolation
* fix: drive codex loop metrics from mcp events
* fix: enforce codex local step budget
* docs: disclose codex isolation limits
* fix: count all codex agent steps and stream step callbacks live
The agent-loop step budget only counted completed mcp_tool_call items, so
built-in command_execution steps (which the public Codex SDK/CLI surface can
still expose) never decremented the budget, letting ingest/reconciliation run
past stepBudget until Codex stopped on its own. onStepFinish was also replayed
only after the whole stream drained, so live work_unit_step / reconciliation
progress appeared stuck until the Codex process exited.
collectEvents is now the single live step accumulator: it counts every
completed agent-action item via a shared isCompletedAgentStep predicate
(command_execution, mcp_tool_call, file_change, web_search), fires onStepFinish
as each step completes, and enforces the budget on that broader count. A
no-tool turn still counts as one step. toolFailures stays MCP-specific, since a
non-zero command exit is normal agent exploration, not a loop failure.
* test: align ingest llm-guard assertions with codex backend
The skip-llm ingest guard message now lists codex as a valid backend and
mentions a Claude Code/Codex session plus a codex setup hint, but this slow
suite test still asserted the pre-codex wording. Update it to match the
production message (already covered by the local-bundle-runtime unit test) and
add the codex setup-line assertion.
* fix: treat codex error:null tool calls as success
The Codex SDK serializes error: null on successful mcp_tool_call items, so
the failure check (item.error !== undefined) flagged every successful tool
call as failed with the empty-payload default "Codex turn failed". This
killed every ingest work unit under the codex backend before it could
produce a patch.
Key on status === 'failed' (authoritative, always set) and only treat a
populated error object as a failure. Add a regression test built from a
verbatim real-SDK event capture.
* fix: default codex backend to gpt-5.5 and report real probe errors
The previous default gpt-5.3-codex is an API-key-only model that the OpenAI
API rejects under ChatGPT-account (subscription) auth, so codex status/setup
failed with a misleading "authentication is not usable" message even though
auth was fine.
- Default codex model is now gpt-5.5 (works on both subscription and API-key
auth); the curated setup picker offers gpt-5.5 / gpt-5.4 / gpt-5.4-mini and
keeps free-form entry for account-specific ids (e.g. gpt-5.3-codex-spark).
- runCodexAuthProbe now distinguishes "model not available" from an auth
failure and surfaces the real API error: collectEvents retains stream
events when the SDK throws on a non-zero exit, and the API error JSON
envelope is unwrapped to its human-readable message.
- The Codex isolation warning now renders inside the clack setup frame.
- Docs updated to gpt-5.5 with a note that *-codex ids require API-key auth.
* fix: require llm.models.default in status and match codex probe remediation
Status reported a project ready when a non-none LLM backend was configured
without llm.models.default, but the runtime (resolveModelSlots) hard-requires
it, so ingest/scan/memory threw after `ktx status` said the project was usable.
buildLlmStatus now fails for any non-none backend missing models.default and no
longer invents a fallback model for claude-code/codex.
Codex probe failures now carry a category-matched fix: a model-access failure
steers the user at llm.models.default instead of the auth/install remediation.
runCodexAuthProbe returns the fix and status consumes it; the message stays
self-sufficient so setup output is unchanged.
Docs: README now lists the codex backend and local Codex auth; ktx-setup.mdx
states --llm-model only accepts codex/default or gpt-*/codex-* ids.
Repaired four doctor fixtures that configured a backend without models.default
(the now-correctly-blocked config) and added coverage for the new behavior.
* feat(cli): profile ingest runs to find where wall-clock time goes
Add opt-in profiling for `ktx ingest`. Each timed phase, work unit, and
agent loop now records durationMs / step count / token usage in the
trace, and a post-run aggregator rolls them up into a "where did the
time go" report printed to stderr.
Enable per run with KTX_PROFILE_INGEST (1/true -> human table, json ->
raw structured profile) or persistently via `ingest.profile` in
ktx.yaml. The json form emits raw milliseconds, token counts, and a
summary.headline one-line diagnosis so coding agents can parse it
directly; json wins when both env and config request profiling.
- runtime-port: RunLoopMetrics (totalMs, usage, stepCount,
stepBoundariesMs) plus onMetrics callbacks on text/object generation
- ai-sdk + claude-code runtimes: capture per-loop timing and token usage
- work-unit-executor and stages 3/4: thread metrics into trace events
- ingest-bundle.runner: time worktree / triage / clustering / index /
reconcile / squash phases and emit the profile in a finally block
(best-effort; never affects the run outcome)
- ingest-profile: new trace+transcript aggregator with table/json formatters
- config: ingest.profile flag; docs: profiling section in ktx-ingest.mdx
* fix(cli): flush tool-call logs before reading ingest profile
Tool transcripts are appended fire-and-forget so the agent hot path never
blocks on logging. The ingest profiler read them before the writes settled,
so per-work-unit toolMs (and the model-vs-tool split derived from it) could
be incomplete. Track in-flight appends and expose flushToolCallLogs() —
bounded by a timeout so it can never hang — and flush before the profiler
reads the transcript.
* feat(completion): complete known argument values
* fix(completion): hide Commander-hidden subcommands from completions
Replace the `__`-prefix name heuristic with Commander's `_hidden` flag so
internal subcommands registered with { hidden: true } (e.g. `mcp serve-internal`)
are excluded from completions, mirroring `ktx --help`.
* test: cover wiki and sl read command routing
* test: cover raw wiki and sl reads
* feat: add wiki read command
* feat: add sl read command
* feat: complete read command entity names
* docs: document wiki and sl read commands
* test: include read commands in command tree
* feat(sl): read and validate unique sources by name
* feat(sl): make read and validate connection id optional
* fix(completion): dedupe semantic source names
* docs(sl): document connection-optional read and validate
* fix(sl): require connection id for query command
* docs(sl): clarify query connection requirement
* fix(completion): don't resolve option values as subcommands
resolveCommand skipped flag tokens but not the value consumed by a
value-taking option in the `--flag value` form, so a connection id like
`query` was matched as the `sl query` subcommand and yielded no `sl`
completions. Track value-taking options and skip their consumed value
before matching subcommands.
* test(telemetry): assert first-run notice via TELEMETRY_NOTICE constant
CI (which tests this branch merged with main) failed because #243 changed
the first-run notice wording in identity.ts (dropped "anonymous") but left
this test grepping for the old literal 'ktx collects anonymous usage data',
so indexOf returned -1. Assert against the exported TELEMETRY_NOTICE
constant instead so the test tracks the source of truth and cannot drift
when the notice text changes again.
Fast mode (the ktx ingest --fast/--deep database-ingest depth toggle) is removed.
ktx ingest now always builds the full enriched ("deep") context. There is no
structural fallback: a database connection without a configured model and
embeddings fails the enrichment-readiness preflight before any work runs, with
a 'Run ktx setup to configure a model and embeddings' hint.
- Remove --fast/--deep flags, the per-connection context.depth field, and the
ktx setup depth prompt (delete setup-database-context-depth.ts).
- Rename ingest-depth.ts -> connection-drivers.ts; ingest always requests scan
mode 'enriched'; readiness gate (enrichmentReadinessGaps) runs for every
database target.
- Drop the database-context-depth telemetry step (Node + Python schema mirrors
regenerated).
- Update CLI, setup, context-build view, docs, the public ktx skill, and the
release-smoke / artifacts scripts (now assert the no-LLM guard failure).
ktx status --fast (a separate network-probe flag) is unchanged.
Follow-ups: KLO-726 (live progress for ktx ingest --all), KLO-727 (restore
credentialed successful-ingest release smoke coverage).
Notion's setup path read --source-api-key-ref while writing the auth_token_ref
config field, so --source-auth-token-ref was silently dropped. Align Notion to
the flag=field convention every other connector follows: it now reads
--source-auth-token-ref, and --source-api-key-ref becomes Metabase-only.
Also add validation rejecting any credential-ref flag not applicable to the
chosen --source, with a pointer to the correct flag, closing the silent-drop
class for all connectors.
Update CLI-reference docs, the ktx skill Notion example, and tests.
Fixes KLO-724.
* feat(cli): define full warehouse dialect contract
* test(cli): keep dialect edge tests focused
* fix(cli): stabilize dialect contract foundation
* refactor(connectors): own read-only query preparation
* refactor(connectors): resolve dialects through registry
* refactor(connectors): keep concrete dialect classes internal
* chore(workspace): enforce dialect import boundary
* refactor(cli): resolve relationship dialect at scan boundary
* refactor(cli): use dialect display parsing for entity details
* refactor(cli): use dialect display parsing for warehouse catalog
* refactor(cli): use dialect SQL in relationship workflows
* test(cli): verify solid dialect scan workflow closure
* test: split cli tests from source tree
* refactor(cli): standardize BigQuery scope listing
* feat(sqlite): implement connector scope listing
* test(connectors): cover required table listing
* feat(cli): add warehouse driver registry
* refactor(setup): route scope discovery through driver registry
* refactor(cli): route local query execution through driver registry
* refactor(historic-sql): route dialect support through driver registry
* refactor(cli): test warehouse connections through driver registry
* fix(cli): close driver registry type export gaps
* Improve setup daemon diagnostics
* refactor(setup): centralize rail-prefixed diagnostics + query-history fallback
Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput
into clack.ts so the setup wizard, managed daemons, and embedding/agent steps
share one rail-formatted writer. setup-databases.ts also adds a
"disable query history and retry" option when the schema-context build fails
and query history is the likely culprit, surfaced via a new
failed-query-history-unavailable status.
* fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match
The setup picker's KtxTableListEntry was a 2-level { schema, name }, so
qualifiedTableId always wrote db.name into enabled_tables. When BigQuery,
Snowflake, or SQL Server later ran fast ingest, their introspect step filtered
the scope set with scopedTableNames(scope, { catalog: projectId|database, db })
— catalog was non-null on the introspect side but null in the scope refs, so
every entry was rejected, the live-database adapter staged zero table files,
and detect() failed with 'Adapter "live-database" did not recognize fetched
source output'.
Align the picker boundary with the canonical 3-level KtxTableRef:
- Add catalog: string | null to KtxTableListEntry.
- BigQuery/Snowflake/SQL Server listTables populate catalog from the
resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null.
- qualifiedTableId emits catalog.schema.name when catalog is non-null
(resolveEnabledTables already accepts the 3-part shape) and
schemasFromEnabledTables now goes through parseDottedTableEntry so it
recovers the schema correctly from both 2-part and 3-part entries.
- Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker
reuse.
Update listTables expectations in all seven connector tests and the setup /
picker test fixtures. Add a picker regression test that covers the
catalog-bearing round-trip (save + refine).
* fix(cli): allow debug telemetry under opt-out env
* feat(cli): add 'skip context sources' option to database setup menu
After databases are configured, the post-setup menu now offers a 'Skip
context sources' choice equivalent to passing --skip-sources, which
plumbs through KtxSetupDatabasesResult.skipSources to bypass the
context-source step in the same run.
* feat(cli): standardize tree picker UX after clack autocomplete-multiselect
Search is always on (no '/' to enter): typed printable chars feed the
query, Tab toggles selection on the focused node without leaving the
search bar, and Space toggles only after arrow-key navigation
(isNavigating); otherwise it is appended to the query. Esc clears a
non-empty query before quitting, Ctrl+A and Ctrl+N replace bare-letter
bulk bindings, and the cursor refocuses on the first match when the
query change would hide it.
Add --fast to skip checks requiring external communication (Claude Code
auth probe and Postgres pg_stat_statements probe); skipped checks render
as `-` and carry `"status": "skipped"` in JSON output. Always show a new
Local data section sourced from .ktx/db.sqlite (ingest run counts and
last-completed per connection, knowledge page counts by scope, semantic
layer source/dictionary value counts) plus on-disk sizes for .ktx/db.sqlite,
.ktx/cache/, raw-sources/, wiki/global/, and semantic-layer/. Wrap the
remaining slow probes in a @clack/prompts spinner when stdout is a TTY.
* chore: standardize daemon naming on "KTX daemon"
Replace inconsistent names ("KTX Python daemon", "KTX local embeddings
daemon", "KTX managed daemon", "Python daemon") with the single name
"KTX daemon" in CLI output, errors, command descriptions, test
assertions, smoke scripts, docs, AGENTS.md, issue templates, and
codecov flags. The daemon is a portable compute server with endpoints
for SQL analysis, semantic layer, LookML, database introspection, and
embeddings; the previous labels misrepresented it as embeddings-only or
exposed implementation details ("Python", "managed").
The "KTX Python runtime" concept (installed interpreter + packages) is
deliberately left as-is — it is a separate concept from the daemon
process.
* refactor(release): drop release-policy.json runtime dep and next branch
Strips the release-policy.json fallback from release-version.ts so the CLI
reads its version straight from packages/cli/package.json. dev → 0.0.0-private,
installed @kaelio/ktx → the real semver baked into the published package.json.
KtxCliPackageInfo collapses to { name, version, contextPackageName }; /health
no longer depends on version files surviving past a CI run.
Replaces the dual-branch (main + next) semantic-release model with a single-
branch model on main. rcs and stables interleave on the same branch via
{ name: 'main', prerelease: 'rc', channel: 'next' } / ['main']. Drops
@semantic-release/git and @semantic-release/changelog (nothing is committed
back to the repo on any channel) and the workflow's "Prepare next prerelease
branch" step plus the KTX_PRERELEASE_BRANCH plumbing. The git tag plus the
published npm artifact carry the version forward.
Updates docs/release.md, removes the two now-unused devDeps, regenerates
pnpm-lock.yaml. 611/611 @ktx/cli tests, 173/173 script tests, type-check,
biome, knip all clean.
* fix(release): don't throw on non-main branches at config-load time
knip loads .releaserc.cjs on every PR run, where GITHUB_REF_NAME is the
merge ref (e.g. 180/merge). The previous version of releaseBranches threw
immediately when the branch wasn't main, which made knip fail to evaluate
the config and then mis-flag @semantic-release/exec as an unused dep.
semantic-release already refuses to publish when the current branch doesn't
match a configured release branch, so the explicit throw was redundant.
Drop it (and the unused currentBranch helper) and replace the
"rejects releases from non-main" assertion with one that exercises a CI-
shaped GITHUB_REF_NAME and confirms the config loads.
Bare invocations now do the obvious thing instead of erroring out, and mode-as-subcommand patterns collapse into flags on the parent. No new top-level commands.
- `ktx ingest` (bare) ingests every configured connection. The `text` subcommand is gone; capture inline notes with `ktx ingest --text "..."` and files with `ktx ingest --file path` (use `-` for stdin). `--text`/`--file` reject a positional connection id; pass `--connection-id` to tag captured notes.
- `ktx connection` (bare) lists; `ktx connection test` (bare) tests every configured connection.
- `ktx wiki` and `ktx sl` flatten `list`/`search`: bare lists, with a `[query...]` positional searches (multi-word joined with spaces). `sl validate` and `sl query` stay as distinct verbs and now read `--connection-id` from the parent.
- `ktx mcp` (bare) prints daemon status.
Adds a shared `resolveConnectionSelection` helper consumed by ingest and connection test. Updates README, docs-site cli-reference and guides, next-steps strings, agent SKILL templates, and all affected tests. Per-package type-check, unit tests (605), smoke tests, and dead-code checks all pass.
* docs: rewrite Semantic Querying concept with imperative-vs-declarative diagram
Reframe semantic-layer-internals.mdx around the contract the semantic
layer offers an agent: declare what you want (a Semantic Query), KTX
figures out how to compute it. Replaces the old "Context-Aware SQL"
framing with a clear imperative-vs-declarative narrative.
Adds a React Flow component (semantic-layer-flow.tsx) that contrasts a
buggy 4-table agent-authored SQL (chasm trap, LEFT-JOIN-in-WHERE,
hardcoded DATE_TRUNC) against the chasm-safe per-fact CTE SQL the
planner actually emits, including the outer GROUP BY over the requested
dimensions. Both lanes converge into a shared warehouse node and each
SQL card now has parallel bullet notes (failures on the left, KTX
behavior on the right).
Side fixes bundled in:
- include the /ktx basePath in the favicon metadata so the icon resolves
under the production prefix
- migrate docs-site/middleware.ts to docs-site/proxy.ts (Next 16 rename)
- redirect / to /ktx/docs/getting-started/introduction so the apex docs
URL works
- add tests covering the apex redirect, the favicon basePath, and the
middleware-to-proxy rename
- propagate the Semantic Query terminology across the ktx-sl CLI
reference, the context-layer concept page, and the agent-clients /
primary-sources integration pages
* Fix CI dead-code failures
* docs-site: polish semantic-layer-internals code blocks and flow diagram
- Make CodeBlock a server component so children traverse synchronously
under React 19 RSC streaming; previously extractText returned "" in
dev SSR, leaving code blocks empty.
- Add custom JSON/YAML/SQL/code-like tokenizers with theme-aware token
classes; drop the colored file-glyph dot and gradient tab-head.
- Tighten tab-head: subtle grey background, smaller monospace filename
in muted grey, smaller rectangular language pill placed to the left
of the filename.
- Polish the React Flow semantic-layer diagram (controls, fit-view
padding, edge types).
* docs-site: annotate imperative SQL, add section anchor, drop ClickHouse
- Wire numbered red badges to each problematic span in the "Without KTX"
SQL with hover sync between SQL gutter, lines, and the notes list.
- Add #imperative-vs-declarative anchor on the flow section header so
the eyebrow link is shareable; reveals a # glyph on hover/focus.
- Align the compiled-SQL note dots to the first-line midpoint
(mt-[6px] instead of mt-1) so 4px dots sit at y=8 in a 16px line.
- Remove all ClickHouse references from docs-site (primary-sources,
quickstart, ktx-setup, contributing, agents-setup, mechanics test,
warehouse drivers in the flow diagram).
* test: drop ClickHouse contributing-docs assertion
Align the workspace-package mirror test with the ClickHouse removal
from docs-site (75907eb). The connector-clickhouse package still
exists in packages/, but contributing.mdx no longer lists it, so the
test that mirrored docs against the workspace was failing.
* docs: streamline quickstart
* feat(docs): simplify quickstart code-block styling
Remove the fake terminal chrome (traffic lights + zsh header) and language
pill from bash blocks, and the teal left-accent from output blocks. Bash
fences now render as minimal cards; text fences route to a muted "output"
preview. Make detectLanguage recursive and enable addLanguageClass in
source.config.ts so Shiki tokens carry through to the renderer. Switch
Shiki themes to min-light / github-dark and disable monospace ligatures so
flag pairs like --agents keep a visible space.
* fix(docs): restore quickstart CI snippets
* docs: align docs with current KTX behavior
* fix: generate valid agent sl query command
* docs: clarify KTX product mechanics
* fix: use <ol> for runtime pipeline steps in product mechanics
The PipelineStep component renders <li> elements, but the RuntimeDiagram
wrapper was a plain <div> instead of a list element. This produced invalid
HTML and accessibility warnings. IngestionDiagram already used <ol>.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* Add docs favicon
* docs: add semantic layer internals concept
* docs: refine documentation source label
* docs: clarify company documentation examples
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* docs: add CLI component reuse guidance
* docs: add unified ingest ux design
* Refine unified ingest UX design after adversarial review iteration 1
* Refine unified ingest UX design after adversarial review iteration 2
* Refine unified ingest UX design after adversarial review iteration 3
* feat(cli): route public connection ingest command
* feat(cli): hide standalone scan from public help
* feat(cli): plan public ingest depth and query history
* feat(cli): execute public database ingest facets
* feat(ingest): read connection query history config
* fix(cli): use public ingest wording
* fix(config): stop generating ingest adapter allow lists
* docs: document public ingest command
* test: align ingest surface expectations
* docs: add unified ingest public CLI surface plan
* feat(cli): preflight deep public ingest readiness
* feat(setup): store query history in connection context
* feat(setup): store database context depth
* feat(setup): verify context readiness by database depth
* fix(setup): keep context build foreground only
* fix(config): reject reserved ingest connection ids
* test: close unified ingest v1 expectations
* docs: add unified ingest v1 closure plan
* fix(ingest): bypass adapter allow-list for public source ingest
* fix(ingest): honor query history window intent
* fix(ingest): hide scan internals from public database ingest
* feat(ingest): use foreground view for interactive public ingest
* fix(setup): use schema context and query history wording
* test(cli): verify unified ingest public output
* docs: add unified ingest v1 public output closure plan
* fix(setup): forward query history flags
* fix(setup): prompt for postgres query history
* fix(status): report query history readiness
* fix(ingest): remove legacy public guidance
* fix(ingest): polish foreground retry copy
* docs(examples): use unified query history wording
* chore(ingest): finish public query history cleanup
* docs: add unified ingest v1 query history status cleanup plan
* test(docs): cover unified ingest public docs
* docs: align ingest CLI reference with unified UX
* docs: update context build guides for unified ingest
* docs: update setup and primary source ingest wording
* docs: stop advertising adapter-backed example ingest
* docs: close unified ingest public docs gaps
* docs: add unified ingest v1 docs site closure plan
* fix: render unified ingest foreground warnings
* fix: explain query history schema order
* fix: add public ingest retry guidance
* fix: align setup next steps with unified ingest
* fix: remove scan wording from demo progress
* test: verify unified ingest ux closure
* docs: add unified ingest v1 foreground and retry closure plan
* fix(cli): preserve query-history pull config in public ingest
* fix(cli): omit hidden commands from docs command tree
* test(cli): close unified ingest final public surface checks
* docs: add unified ingest v1 final public surface closure plan
* fix(cli): use public source labels in ingest reports
* fix(cli): suppress low-level public ingest output
* test(cli): verify unified ingest public plain output
* docs: add unified ingest v1 public plain output closure plan
* fix(cli): add public ingest copy sanitizers
* fix(cli): sanitize public ingest progress copy
* fix(cli): rename setup schema scope prompt
* docs(plan): add progress copy closure; test: align setup back-nav fixture
Adds the iter9 plan and updates the setup back-navigation test fixture
to pass disableQueryHistory plus listSchemas/listTables stubs that the
unified ingest setup step now requires.
* docs(plan): add final ux labels plan with narrowed label scans
* fix(cli): aggregate unsupported query-history warnings
* fix(cli): align setup database labels
* test(cli): fix setup database test type-check
* fix(cli): remove primary-source wording from setup output
* test(cli): verify unified ingest setup closure
* docs(plan): add unified ingest v1 verification copy closure plan
* fix(cli): remove top-level scan command
* fix(cli): remove legacy ingest and wiki commands
* Merge scan into ingest flow
* feat(cli): split ingest progress into per-phase rows, rename work units to tasks
Each database target in the unified ingest dashboard now renders one row per
real subprocess (Schema, then Query history when enabled) instead of a single
combined bar. Each phase has its own monotonic 0-100% bar so the progress
never snaps back to zero when historic-sql starts after scan completes.
Completed phases keep their final bar, summary, and elapsed time visible as
an inline audit trail; queued and skipped phases are shown explicitly.
Also rename user-facing "work units" / "Failed work units" to "tasks" /
"Failed tasks" in ingest output and parseIngestSummary. The parser still
accepts the legacy "Work units:" wording in captured output for backward
compat. Internal memory-flow event names and type fields are left alone.
* Fix test harness failures
* Fix CI smoke checks
---------
Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
Hide advanced/internal `ktx setup` options from --help output using
.hideHelp() so the command surface is approachable for new users. Remove
the --project, --agent-scope, and --skip-initial-source-ingest flags
that are no longer needed. Update docs and tests to match.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
