fix: indexing failures surface loud, chat envelopes append verbatim by rejojer · Pull Request #421 · VectifyAI/PageIndex

rejojer · 2026-08-21T13:12:31Z

Indexing: dead credentials or a missing model fail the run instead of
storing a document with blank summaries; a 400 (context_length_exceeded)
skips the retry ladder — the prompt will not shrink — and stays a
per-prompt failure the run absorbs; all-empty model replies can no longer
store a retrieval-ready document; the one-sentence doc description
absorbs its own context overflow instead of discarding a fully indexed
document; the heading-less flash refusal points at mode='standard'.

Chat: messages() output is append-verbatim clean — unset response-only
defaults are dropped (no "caller": null the request schema rejects);
Claude cache marks follow the wire routing; model_settings and name are
openai_agent_config parameters; one Anthropic client per backend; lifted
thinking defaults are clamped to the model's output ceiling from
LiteLLM's capability map.

Store and inputs: lone surrogates are scrubbed from page text and the
stored basename, so the returned name is byte-for-byte the stored name
and the rename warning fires; NaN/Infinity metadata is rejected at the
gate; every cloud error now carries its HTTP status.

CLI: the flash lane resolves the summary model through ConfigLoader like
the standard and markdown lanes; an empty flash structure errors like the
SDK instead of writing "structure": [] with exit 0; --summary-model
reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's
whitespace tolerance while the tool layer stays strict.

pypdfium2 stays on the 5.x line for every install; the 4.x code paths are
tested compatibility insurance with their own CI leg; process-pool
construction failure falls back to the sequential parse; a py3.10 GC
flake in text extraction is fixed.

Port of feat/local-chat0667e3b..1993740 (28 commits, 26 files). README and assets untouched — main's newer rewrite stands.

Indexing: dead credentials or a missing model fail the run instead of storing a document with blank summaries; a 400 (context_length_exceeded) skips the retry ladder — the prompt will not shrink — and stays a per-prompt failure the run absorbs; all-empty model replies can no longer store a retrieval-ready document; the one-sentence doc description absorbs its own context overflow instead of discarding a fully indexed document; the heading-less flash refusal points at mode='standard'. Chat: messages() output is append-verbatim clean — unset response-only defaults are dropped (no "caller": null the request schema rejects); Claude cache marks follow the wire routing; model_settings and name are openai_agent_config parameters; one Anthropic client per backend; lifted thinking defaults are clamped to the model's output ceiling from LiteLLM's capability map. Store and inputs: lone surrogates are scrubbed from page text and the stored basename, so the returned name is byte-for-byte the stored name and the rename warning fires; NaN/Infinity metadata is rejected at the gate; every cloud error now carries its HTTP status. CLI: the flash lane resolves the summary model through ConfigLoader like the standard and markdown lanes; an empty flash structure errors like the SDK instead of writing "structure": [] with exit 0; --summary-model reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's whitespace tolerance while the tool layer stays strict. pypdfium2 stays on the 5.x line for every install; the 4.x code paths are tested compatibility insurance with their own CI leg; process-pool construction failure falls back to the sequential parse; a py3.10 GC flake in text extraction is fixed.

+ if _window_depth == 0:
+ d.pop("__spec__", None)
+ d.update(_window_saved)
+ _window_saved = {}


+ import runpy
+ import sys
+
+ import pageindex.flash


+ a_in.set()
+ assert b_in.wait(5)
+ a_out.set()
+ except BaseException as exc: # in-thread failures only warn in pytest


+ with _anonymous_main():
+ b_in.set()
+ assert a_out.wait(5)
+ except BaseException as exc:


The branch had nothing main lacks (its content was squash-ported in #421/#422); this records main as merged so PR #400 spans 0.2.9–0.2.11 with history kept. Claude-Session: https://claude.ai/code/session_01GZLsJ6jmAQvgotcbhQv85Q

rejojer · 2026-08-21T13:12:31Z

Indexing: dead credentials or a missing model fail the run instead of
storing a document with blank summaries; a 400 (context_length_exceeded)
skips the retry ladder — the prompt will not shrink — and stays a
per-prompt failure the run absorbs; all-empty model replies can no longer
store a retrieval-ready document; the one-sentence doc description
absorbs its own context overflow instead of discarding a fully indexed
document; the heading-less flash refusal points at mode='standard'.

Chat: messages() output is append-verbatim clean — unset response-only
defaults are dropped (no "caller": null the request schema rejects);
Claude cache marks follow the wire routing; model_settings and name are
openai_agent_config parameters; one Anthropic client per backend; lifted
thinking defaults are clamped to the model's output ceiling from
LiteLLM's capability map.

Store and inputs: lone surrogates are scrubbed from page text and the
stored basename, so the returned name is byte-for-byte the stored name
and the rename warning fires; NaN/Infinity metadata is rejected at the
gate; every cloud error now carries its HTTP status.

CLI: the flash lane resolves the summary model through ConfigLoader like
the standard and markdown lanes; an empty flash structure errors like the
SDK instead of writing "structure": [] with exit 0; --summary-model
reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's
whitespace tolerance while the tool layer stays strict.

pypdfium2 stays on the 5.x line for every install; the 4.x code paths are
tested compatibility insurance with their own CI leg; process-pool
construction failure falls back to the sequential parse; a py3.10 GC
flake in text extraction is fixed.

Port of feat/local-chat0667e3b..1993740 (28 commits, 26 files). README and assets untouched — main's newer rewrite stands.

Indexing: dead credentials or a missing model fail the run instead of storing a document with blank summaries; a 400 (context_length_exceeded) skips the retry ladder — the prompt will not shrink — and stays a per-prompt failure the run absorbs; all-empty model replies can no longer store a retrieval-ready document; the one-sentence doc description absorbs its own context overflow instead of discarding a fully indexed document; the heading-less flash refusal points at mode='standard'. Chat: messages() output is append-verbatim clean — unset response-only defaults are dropped (no "caller": null the request schema rejects); Claude cache marks follow the wire routing; model_settings and name are openai_agent_config parameters; one Anthropic client per backend; lifted thinking defaults are clamped to the model's output ceiling from LiteLLM's capability map. Store and inputs: lone surrogates are scrubbed from page text and the stored basename, so the returned name is byte-for-byte the stored name and the rename warning fires; NaN/Infinity metadata is rejected at the gate; every cloud error now carries its HTTP status. CLI: the flash lane resolves the summary model through ConfigLoader like the standard and markdown lanes; an empty flash structure errors like the SDK instead of writing "structure": [] with exit 0; --summary-model reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's whitespace tolerance while the tool layer stays strict. pypdfium2 stays on the 5.x line for every install; the 4.x code paths are tested compatibility insurance with their own CI leg; process-pool construction failure falls back to the sequential parse; a py3.10 GC flake in text extraction is fixed.

+ if _window_depth == 0:
+ d.pop("__spec__", None)
+ d.update(_window_saved)
+ _window_saved = {}


+ import runpy
+ import sys
+
+ import pageindex.flash


+ a_in.set()
+ assert b_in.wait(5)
+ a_out.set()
+ except BaseException as exc: # in-thread failures only warn in pytest


+ with _anonymous_main():
+ b_in.set()
+ assert a_out.wait(5)
+ except BaseException as exc:


The branch had nothing main lacks (its content was squash-ported in #421/#422); this records main as merged so PR #400 spans 0.2.9–0.2.11 with history kept. Claude-Session: https://claude.ai/code/session_01GZLsJ6jmAQvgotcbhQv85Q

rejojer · 2026-08-21T13:12:31Z

Indexing: dead credentials or a missing model fail the run instead of
storing a document with blank summaries; a 400 (context_length_exceeded)
skips the retry ladder — the prompt will not shrink — and stays a
per-prompt failure the run absorbs; all-empty model replies can no longer
store a retrieval-ready document; the one-sentence doc description
absorbs its own context overflow instead of discarding a fully indexed
document; the heading-less flash refusal points at mode='standard'.

Chat: messages() output is append-verbatim clean — unset response-only
defaults are dropped (no "caller": null the request schema rejects);
Claude cache marks follow the wire routing; model_settings and name are
openai_agent_config parameters; one Anthropic client per backend; lifted
thinking defaults are clamped to the model's output ceiling from
LiteLLM's capability map.

Store and inputs: lone surrogates are scrubbed from page text and the
stored basename, so the returned name is byte-for-byte the stored name
and the rename warning fires; NaN/Infinity metadata is rejected at the
gate; every cloud error now carries its HTTP status.

CLI: the flash lane resolves the summary model through ConfigLoader like
the standard and markdown lanes; an empty flash structure errors like the
SDK instead of writing "structure": [] with exit 0; --summary-model
reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's
whitespace tolerance while the tool layer stays strict.

pypdfium2 stays on the 5.x line for every install; the 4.x code paths are
tested compatibility insurance with their own CI leg; process-pool
construction failure falls back to the sequential parse; a py3.10 GC
flake in text extraction is fixed.

Port of feat/local-chat0667e3b..1993740 (28 commits, 26 files). README and assets untouched — main's newer rewrite stands.

Indexing: dead credentials or a missing model fail the run instead of storing a document with blank summaries; a 400 (context_length_exceeded) skips the retry ladder — the prompt will not shrink — and stays a per-prompt failure the run absorbs; all-empty model replies can no longer store a retrieval-ready document; the one-sentence doc description absorbs its own context overflow instead of discarding a fully indexed document; the heading-less flash refusal points at mode='standard'. Chat: messages() output is append-verbatim clean — unset response-only defaults are dropped (no "caller": null the request schema rejects); Claude cache marks follow the wire routing; model_settings and name are openai_agent_config parameters; one Anthropic client per backend; lifted thinking defaults are clamped to the model's output ceiling from LiteLLM's capability map. Store and inputs: lone surrogates are scrubbed from page text and the stored basename, so the returned name is byte-for-byte the stored name and the rename warning fires; NaN/Infinity metadata is rejected at the gate; every cloud error now carries its HTTP status. CLI: the flash lane resolves the summary model through ConfigLoader like the standard and markdown lanes; an empty flash structure errors like the SDK instead of writing "structure": [] with exit 0; --summary-model reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's whitespace tolerance while the tool layer stays strict. pypdfium2 stays on the 5.x line for every install; the 4.x code paths are tested compatibility insurance with their own CI leg; process-pool construction failure falls back to the sequential parse; a py3.10 GC flake in text extraction is fixed.

+ if _window_depth == 0:
+ d.pop("__spec__", None)
+ d.update(_window_saved)
+ _window_saved = {}


+ import runpy
+ import sys
+
+ import pageindex.flash


+ a_in.set()
+ assert b_in.wait(5)
+ a_out.set()
+ except BaseException as exc: # in-thread failures only warn in pytest


+ with _anonymous_main():
+ b_in.set()
+ assert a_out.wait(5)
+ except BaseException as exc:


The branch had nothing main lacks (its content was squash-ported in #421/#422); this records main as merged so PR #400 spans 0.2.9–0.2.11 with history kept. Claude-Session: https://claude.ai/code/session_01GZLsJ6jmAQvgotcbhQv85Q

rejojer · 2026-08-21T13:12:31Z

Indexing: dead credentials or a missing model fail the run instead of
storing a document with blank summaries; a 400 (context_length_exceeded)
skips the retry ladder — the prompt will not shrink — and stays a
per-prompt failure the run absorbs; all-empty model replies can no longer
store a retrieval-ready document; the one-sentence doc description
absorbs its own context overflow instead of discarding a fully indexed
document; the heading-less flash refusal points at mode='standard'.

Chat: messages() output is append-verbatim clean — unset response-only
defaults are dropped (no "caller": null the request schema rejects);
Claude cache marks follow the wire routing; model_settings and name are
openai_agent_config parameters; one Anthropic client per backend; lifted
thinking defaults are clamped to the model's output ceiling from
LiteLLM's capability map.

Store and inputs: lone surrogates are scrubbed from page text and the
stored basename, so the returned name is byte-for-byte the stored name
and the rename warning fires; NaN/Infinity metadata is rejected at the
gate; every cloud error now carries its HTTP status.

CLI: the flash lane resolves the summary model through ConfigLoader like
the standard and markdown lanes; an empty flash structure errors like the
SDK instead of writing "structure": [] with exit 0; --summary-model
reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's
whitespace tolerance while the tool layer stays strict.

pypdfium2 stays on the 5.x line for every install; the 4.x code paths are
tested compatibility insurance with their own CI leg; process-pool
construction failure falls back to the sequential parse; a py3.10 GC
flake in text extraction is fixed.

Port of feat/local-chat0667e3b..1993740 (28 commits, 26 files). README and assets untouched — main's newer rewrite stands.

Indexing: dead credentials or a missing model fail the run instead of storing a document with blank summaries; a 400 (context_length_exceeded) skips the retry ladder — the prompt will not shrink — and stays a per-prompt failure the run absorbs; all-empty model replies can no longer store a retrieval-ready document; the one-sentence doc description absorbs its own context overflow instead of discarding a fully indexed document; the heading-less flash refusal points at mode='standard'. Chat: messages() output is append-verbatim clean — unset response-only defaults are dropped (no "caller": null the request schema rejects); Claude cache marks follow the wire routing; model_settings and name are openai_agent_config parameters; one Anthropic client per backend; lifted thinking defaults are clamped to the model's output ceiling from LiteLLM's capability map. Store and inputs: lone surrogates are scrubbed from page text and the stored basename, so the returned name is byte-for-byte the stored name and the rename warning fires; NaN/Infinity metadata is rejected at the gate; every cloud error now carries its HTTP status. CLI: the flash lane resolves the summary model through ConfigLoader like the standard and markdown lanes; an empty flash structure errors like the SDK instead of writing "structure": [] with exit 0; --summary-model reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's whitespace tolerance while the tool layer stays strict. pypdfium2 stays on the 5.x line for every install; the 4.x code paths are tested compatibility insurance with their own CI leg; process-pool construction failure falls back to the sequential parse; a py3.10 GC flake in text extraction is fixed.

+ if _window_depth == 0:
+ d.pop("__spec__", None)
+ d.update(_window_saved)
+ _window_saved = {}


+ import runpy
+ import sys
+
+ import pageindex.flash


+ a_in.set()
+ assert b_in.wait(5)
+ a_out.set()
+ except BaseException as exc: # in-thread failures only warn in pytest


+ with _anonymous_main():
+ b_in.set()
+ assert a_out.wait(5)
+ except BaseException as exc:


The branch had nothing main lacks (its content was squash-ported in #421/#422); this records main as merged so PR #400 spans 0.2.9–0.2.11 with history kept. Claude-Session: https://claude.ai/code/session_01GZLsJ6jmAQvgotcbhQv85Q

rejojer · 2026-08-21T13:12:31Z

Indexing: dead credentials or a missing model fail the run instead of
storing a document with blank summaries; a 400 (context_length_exceeded)
skips the retry ladder — the prompt will not shrink — and stays a
per-prompt failure the run absorbs; all-empty model replies can no longer
store a retrieval-ready document; the one-sentence doc description
absorbs its own context overflow instead of discarding a fully indexed
document; the heading-less flash refusal points at mode='standard'.

Chat: messages() output is append-verbatim clean — unset response-only
defaults are dropped (no "caller": null the request schema rejects);
Claude cache marks follow the wire routing; model_settings and name are
openai_agent_config parameters; one Anthropic client per backend; lifted
thinking defaults are clamped to the model's output ceiling from
LiteLLM's capability map.

Store and inputs: lone surrogates are scrubbed from page text and the
stored basename, so the returned name is byte-for-byte the stored name
and the rename warning fires; NaN/Infinity metadata is rejected at the
gate; every cloud error now carries its HTTP status.

CLI: the flash lane resolves the summary model through ConfigLoader like
the standard and markdown lanes; an empty flash structure errors like the
SDK instead of writing "structure": [] with exit 0; --summary-model
reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's
whitespace tolerance while the tool layer stays strict.

pypdfium2 stays on the 5.x line for every install; the 4.x code paths are
tested compatibility insurance with their own CI leg; process-pool
construction failure falls back to the sequential parse; a py3.10 GC
flake in text extraction is fixed.

Port of feat/local-chat0667e3b..1993740 (28 commits, 26 files). README and assets untouched — main's newer rewrite stands.

Indexing: dead credentials or a missing model fail the run instead of storing a document with blank summaries; a 400 (context_length_exceeded) skips the retry ladder — the prompt will not shrink — and stays a per-prompt failure the run absorbs; all-empty model replies can no longer store a retrieval-ready document; the one-sentence doc description absorbs its own context overflow instead of discarding a fully indexed document; the heading-less flash refusal points at mode='standard'. Chat: messages() output is append-verbatim clean — unset response-only defaults are dropped (no "caller": null the request schema rejects); Claude cache marks follow the wire routing; model_settings and name are openai_agent_config parameters; one Anthropic client per backend; lifted thinking defaults are clamped to the model's output ceiling from LiteLLM's capability map. Store and inputs: lone surrogates are scrubbed from page text and the stored basename, so the returned name is byte-for-byte the stored name and the rename warning fires; NaN/Infinity metadata is rejected at the gate; every cloud error now carries its HTTP status. CLI: the flash lane resolves the summary model through ConfigLoader like the standard and markdown lanes; an empty flash structure errors like the SDK instead of writing "structure": [] with exit 0; --summary-model reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's whitespace tolerance while the tool layer stays strict. pypdfium2 stays on the 5.x line for every install; the 4.x code paths are tested compatibility insurance with their own CI leg; process-pool construction failure falls back to the sequential parse; a py3.10 GC flake in text extraction is fixed.

+ if _window_depth == 0:
+ d.pop("__spec__", None)
+ d.update(_window_saved)
+ _window_saved = {}


+ import runpy
+ import sys
+
+ import pageindex.flash


+ a_in.set()
+ assert b_in.wait(5)
+ a_out.set()
+ except BaseException as exc: # in-thread failures only warn in pytest


+ with _anonymous_main():
+ b_in.set()
+ assert a_out.wait(5)
+ except BaseException as exc:


The branch had nothing main lacks (its content was squash-ported in #421/#422); this records main as merged so PR #400 spans 0.2.9–0.2.11 with history kept. Claude-Session: https://claude.ai/code/session_01GZLsJ6jmAQvgotcbhQv85Q

rejojer · 2026-08-21T13:12:31Z

Indexing: dead credentials or a missing model fail the run instead of
storing a document with blank summaries; a 400 (context_length_exceeded)
skips the retry ladder — the prompt will not shrink — and stays a
per-prompt failure the run absorbs; all-empty model replies can no longer
store a retrieval-ready document; the one-sentence doc description
absorbs its own context overflow instead of discarding a fully indexed
document; the heading-less flash refusal points at mode='standard'.

Chat: messages() output is append-verbatim clean — unset response-only
defaults are dropped (no "caller": null the request schema rejects);
Claude cache marks follow the wire routing; model_settings and name are
openai_agent_config parameters; one Anthropic client per backend; lifted
thinking defaults are clamped to the model's output ceiling from
LiteLLM's capability map.

Store and inputs: lone surrogates are scrubbed from page text and the
stored basename, so the returned name is byte-for-byte the stored name
and the rename warning fires; NaN/Infinity metadata is rejected at the
gate; every cloud error now carries its HTTP status.

CLI: the flash lane resolves the summary model through ConfigLoader like
the standard and markdown lanes; an empty flash structure errors like the
SDK instead of writing "structure": [] with exit 0; --summary-model
reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's
whitespace tolerance while the tool layer stays strict.

pypdfium2 stays on the 5.x line for every install; the 4.x code paths are
tested compatibility insurance with their own CI leg; process-pool
construction failure falls back to the sequential parse; a py3.10 GC
flake in text extraction is fixed.

Port of feat/local-chat0667e3b..1993740 (28 commits, 26 files). README and assets untouched — main's newer rewrite stands.

Indexing: dead credentials or a missing model fail the run instead of storing a document with blank summaries; a 400 (context_length_exceeded) skips the retry ladder — the prompt will not shrink — and stays a per-prompt failure the run absorbs; all-empty model replies can no longer store a retrieval-ready document; the one-sentence doc description absorbs its own context overflow instead of discarding a fully indexed document; the heading-less flash refusal points at mode='standard'. Chat: messages() output is append-verbatim clean — unset response-only defaults are dropped (no "caller": null the request schema rejects); Claude cache marks follow the wire routing; model_settings and name are openai_agent_config parameters; one Anthropic client per backend; lifted thinking defaults are clamped to the model's output ceiling from LiteLLM's capability map. Store and inputs: lone surrogates are scrubbed from page text and the stored basename, so the returned name is byte-for-byte the stored name and the rename warning fires; NaN/Infinity metadata is rejected at the gate; every cloud error now carries its HTTP status. CLI: the flash lane resolves the summary model through ConfigLoader like the standard and markdown lanes; an empty flash structure errors like the SDK instead of writing "structure": [] with exit 0; --summary-model reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's whitespace tolerance while the tool layer stays strict. pypdfium2 stays on the 5.x line for every install; the 4.x code paths are tested compatibility insurance with their own CI leg; process-pool construction failure falls back to the sequential parse; a py3.10 GC flake in text extraction is fixed.

+ if _window_depth == 0:
+ d.pop("__spec__", None)
+ d.update(_window_saved)
+ _window_saved = {}


+ import runpy
+ import sys
+
+ import pageindex.flash


+ a_in.set()
+ assert b_in.wait(5)
+ a_out.set()
+ except BaseException as exc: # in-thread failures only warn in pytest


+ with _anonymous_main():
+ b_in.set()
+ assert a_out.wait(5)
+ except BaseException as exc:


The branch had nothing main lacks (its content was squash-ported in #421/#422); this records main as merged so PR #400 spans 0.2.9–0.2.11 with history kept. Claude-Session: https://claude.ai/code/session_01GZLsJ6jmAQvgotcbhQv85Q

rejojer · 2026-08-21T13:12:31Z

Indexing: dead credentials or a missing model fail the run instead of
storing a document with blank summaries; a 400 (context_length_exceeded)
skips the retry ladder — the prompt will not shrink — and stays a
per-prompt failure the run absorbs; all-empty model replies can no longer
store a retrieval-ready document; the one-sentence doc description
absorbs its own context overflow instead of discarding a fully indexed
document; the heading-less flash refusal points at mode='standard'.

Chat: messages() output is append-verbatim clean — unset response-only
defaults are dropped (no "caller": null the request schema rejects);
Claude cache marks follow the wire routing; model_settings and name are
openai_agent_config parameters; one Anthropic client per backend; lifted
thinking defaults are clamped to the model's output ceiling from
LiteLLM's capability map.

Store and inputs: lone surrogates are scrubbed from page text and the
stored basename, so the returned name is byte-for-byte the stored name
and the rename warning fires; NaN/Infinity metadata is rejected at the
gate; every cloud error now carries its HTTP status.

CLI: the flash lane resolves the summary model through ConfigLoader like
the standard and markdown lanes; an empty flash structure errors like the
SDK instead of writing "structure": [] with exit 0; --summary-model
reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's
whitespace tolerance while the tool layer stays strict.

pypdfium2 stays on the 5.x line for every install; the 4.x code paths are
tested compatibility insurance with their own CI leg; process-pool
construction failure falls back to the sequential parse; a py3.10 GC
flake in text extraction is fixed.

Port of feat/local-chat0667e3b..1993740 (28 commits, 26 files). README and assets untouched — main's newer rewrite stands.

Indexing: dead credentials or a missing model fail the run instead of storing a document with blank summaries; a 400 (context_length_exceeded) skips the retry ladder — the prompt will not shrink — and stays a per-prompt failure the run absorbs; all-empty model replies can no longer store a retrieval-ready document; the one-sentence doc description absorbs its own context overflow instead of discarding a fully indexed document; the heading-less flash refusal points at mode='standard'. Chat: messages() output is append-verbatim clean — unset response-only defaults are dropped (no "caller": null the request schema rejects); Claude cache marks follow the wire routing; model_settings and name are openai_agent_config parameters; one Anthropic client per backend; lifted thinking defaults are clamped to the model's output ceiling from LiteLLM's capability map. Store and inputs: lone surrogates are scrubbed from page text and the stored basename, so the returned name is byte-for-byte the stored name and the rename warning fires; NaN/Infinity metadata is rejected at the gate; every cloud error now carries its HTTP status. CLI: the flash lane resolves the summary model through ConfigLoader like the standard and markdown lanes; an empty flash structure errors like the SDK instead of writing "structure": [] with exit 0; --summary-model reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's whitespace tolerance while the tool layer stays strict. pypdfium2 stays on the 5.x line for every install; the 4.x code paths are tested compatibility insurance with their own CI leg; process-pool construction failure falls back to the sequential parse; a py3.10 GC flake in text extraction is fixed.

+ if _window_depth == 0:
+ d.pop("__spec__", None)
+ d.update(_window_saved)
+ _window_saved = {}


+ import runpy
+ import sys
+
+ import pageindex.flash


+ a_in.set()
+ assert b_in.wait(5)
+ a_out.set()
+ except BaseException as exc: # in-thread failures only warn in pytest


+ with _anonymous_main():
+ b_in.set()
+ assert a_out.wait(5)
+ except BaseException as exc:


The branch had nothing main lacks (its content was squash-ported in #421/#422); this records main as merged so PR #400 spans 0.2.9–0.2.11 with history kept. Claude-Session: https://claude.ai/code/session_01GZLsJ6jmAQvgotcbhQv85Q

rejojer · 2026-08-21T13:12:31Z

Indexing: dead credentials or a missing model fail the run instead of
storing a document with blank summaries; a 400 (context_length_exceeded)
skips the retry ladder — the prompt will not shrink — and stays a
per-prompt failure the run absorbs; all-empty model replies can no longer
store a retrieval-ready document; the one-sentence doc description
absorbs its own context overflow instead of discarding a fully indexed
document; the heading-less flash refusal points at mode='standard'.

Chat: messages() output is append-verbatim clean — unset response-only
defaults are dropped (no "caller": null the request schema rejects);
Claude cache marks follow the wire routing; model_settings and name are
openai_agent_config parameters; one Anthropic client per backend; lifted
thinking defaults are clamped to the model's output ceiling from
LiteLLM's capability map.

Store and inputs: lone surrogates are scrubbed from page text and the
stored basename, so the returned name is byte-for-byte the stored name
and the rename warning fires; NaN/Infinity metadata is rejected at the
gate; every cloud error now carries its HTTP status.

CLI: the flash lane resolves the summary model through ConfigLoader like
the standard and markdown lanes; an empty flash structure errors like the
SDK instead of writing "structure": [] with exit 0; --summary-model
reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's
whitespace tolerance while the tool layer stays strict.

pypdfium2 stays on the 5.x line for every install; the 4.x code paths are
tested compatibility insurance with their own CI leg; process-pool
construction failure falls back to the sequential parse; a py3.10 GC
flake in text extraction is fixed.

Port of feat/local-chat0667e3b..1993740 (28 commits, 26 files). README and assets untouched — main's newer rewrite stands.

Indexing: dead credentials or a missing model fail the run instead of storing a document with blank summaries; a 400 (context_length_exceeded) skips the retry ladder — the prompt will not shrink — and stays a per-prompt failure the run absorbs; all-empty model replies can no longer store a retrieval-ready document; the one-sentence doc description absorbs its own context overflow instead of discarding a fully indexed document; the heading-less flash refusal points at mode='standard'. Chat: messages() output is append-verbatim clean — unset response-only defaults are dropped (no "caller": null the request schema rejects); Claude cache marks follow the wire routing; model_settings and name are openai_agent_config parameters; one Anthropic client per backend; lifted thinking defaults are clamped to the model's output ceiling from LiteLLM's capability map. Store and inputs: lone surrogates are scrubbed from page text and the stored basename, so the returned name is byte-for-byte the stored name and the rename warning fires; NaN/Infinity metadata is rejected at the gate; every cloud error now carries its HTTP status. CLI: the flash lane resolves the summary model through ConfigLoader like the standard and markdown lanes; an empty flash structure errors like the SDK instead of writing "structure": [] with exit 0; --summary-model reaches the markdown lane; the SDK page-spec surface keeps 0.2.10's whitespace tolerance while the tool layer stays strict. pypdfium2 stays on the 5.x line for every install; the 4.x code paths are tested compatibility insurance with their own CI leg; process-pool construction failure falls back to the sequential parse; a py3.10 GC flake in text extraction is fixed.

+ if _window_depth == 0:
+ d.pop("__spec__", None)
+ d.update(_window_saved)
+ _window_saved = {}


+ import runpy
+ import sys
+
+ import pageindex.flash


+ a_in.set()
+ assert b_in.wait(5)
+ a_out.set()
+ except BaseException as exc: # in-thread failures only warn in pytest


+ with _anonymous_main():
+ b_in.set()
+ assert a_out.wait(5)
+ except BaseException as exc:


The branch had nothing main lacks (its content was squash-ported in #421/#422); this records main as merged so PR #400 spans 0.2.9–0.2.11 with history kept. Claude-Session: https://claude.ai/code/session_01GZLsJ6jmAQvgotcbhQv85Q

github-code-qualityBot found potential problems Aug 21, 2026
View reviewed changes

rejojer merged commit 8289729 into mainAug 21, 2026
9 checks passed

Iams4kura mentioned this pull request Aug 21, 2026
fix: keep page text for bookmarked Flash summaries #388
Closed

rejojer mentioned this pull request Aug 25, 2026
review: 0.2.9–0.2.11 — everything since 0.2.8: local mode, agent tools, local chat, Flash, two-sided client #400
Open