[MISC] sync spec from unstract-llm-whisperer #756 and regenerate - #39
Merged
Merged
Conversation
Upstream hides the v1 output_mode spellings (line-printer, dump-text) and the internal modes (excel, document_insights) from the published enums, and marks three internal knobs x-internal without removing them. Only the two generated Literal models change; the facade and the wire are untouched. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WQ8fZBmtfZJG13fbm5FSan
chandrasekharan-zipstack
marked this pull request as ready for review
September 18, 2026 10:29
Contributor
 |
johnyrahul
approved these changes
Sep 18, 2026
Contributor
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
specs/llmwhisperer.jsoncopied byte-for-byte from Zipstack/unstract-llm-whisperer#756 (branchspec-hide-internal-params, headc4cc7f14);SPEC_SOURCE_REVintools/gen_sdk.shmoved with it.tools/gen_sdk.shrun (openapi-python-client 0.29.0). Generated diff is limited to two models:models/extract_mode.py:ExtractModeLiteral /EXTRACT_MODE_VALUESloseexcel,document_insightsmodels/extract_output_mode.py:ExtractOutputModeLiteral /EXTRACT_OUTPUT_MODE_VALUESloseline-printer,dump-textwhisper()keepsderotate_threshold,min_table_width,ignore_vertical_text(upstream marks themx-internalbut keeps them declared precisely so this client's forwarding into_get_kwargs()keeps working). Docstrings already list only publicmode/output_modevalues.Why
Upstream decision (Johny, Slack: https://zipstack.slack.com/archives/C058WQU0R6E/p1789714932972689?thread_ts=1786949312.062819&cid=C058WQU0R6E):
line-printer/dump-textare v1 spellings,excelis set by ingestion itself,document_insightsis unreleased. See Zipstack/unstract-llm-whisperer#756.Runtime unchanged. The request path (
client_v2.py_build_request→ generatedextract._get_kwargs) never callscheck_extract_mode/check_extract_output_mode(verified: zero references), and the facade takesstr. A caller still passingmode="excel"oroutput_mode="line-printer"goes to the wire exactly as before; only static type checkers see the narrower Literals. The generator ignoresx-internal(regenerating from a spec with only the marker added produced an empty diff).Version proposal (Chandru decides at dispatch)
client_v2) identical →api-surfacegate green → not major by the skill's rule._sdk_llmwhisperersubpackage.Before leaving draft
SPEC_SOURCE_REVcurrently points at the #756 branch head; rewrite it to the squash-merge sha of #756 once merged, then re-runtools/gen_sdk.sh(no diff expected) and push.Notes on Testing
uv run pytest tests/unit→ 290 passedtests/integration→ 17 failed / 2 passed, identical on origin/main: 15× HTTP 402 "breached your free processing limit of 100 pages max per day" from the key in.env, 1×usage_infomissingcurrent_page_count_document_insightson the target service, unrelated to this change.tests/baseline/) not refreshed — a spec sync alone is not a reason to move the parity reference (perspec-upgradeskill).🤖 Generated with Claude Code
https://claude.ai/code/session_01WQ8fZBmtfZJG13fbm5FSan