## Summary
Rename the repository dependency-resource directory `ragflow_deps/` to
`deps/`, and update every hardcoded reference to that directory name so
the rename does not break resource loading at build/runtime.
This is not a purely cosmetic rename: the Go runtime hardcodes the
directory name as a resource search path (e.g.
`internal/common/model_assets.go` trimming the `deps/` prefix, and the
tokenizers joining `deps/` into candidate paths), and the Dockerfiles
copy assets into `/ragflow/deps`. Those literals must move together with
the directory, otherwise assets fail to resolve.
## Two intentional exceptions (kept unchanged)
The rename deliberately keeps two names that only *coincidentally*
contained the old string:
- The published image tag `infiniflow/ragflow_deps:latest` (used by
`Dockerfile`, `Dockerfile_base`, docs, and CI `image inspect` checks).
- The CI install path `/opt/ragflow_deps` inside the CI runner image
(`build.sh` `SYSTEM_DEPS_TOKENIZER`).
## Changes
- `git mv ragflow_deps deps`.
- `build.sh`: `CL100K_TABLE_RELPATH`, native asset zip path, and related
references updated to `deps/`.
- `tools/scripts/download_dev_deps.py`: `RAGFLOW_DEPS_DIR` points at
`deps/`.
- Go runtime resource search paths (`internal/common`,
`internal/tokenizer`) updated to the `deps/` layout.
- `Dockerfile` / `Dockerfile_base`: container asset path changed to
`/ragflow/deps`; kept tag `infiniflow/ragflow_deps:latest` unchanged.
- Docs / `AGENTS.md` / CI workflow paths updated to the new directory
name.
## Test plan
- Go unit tests in `internal/common` and `internal/tokenizer` updated to
the new `deps/` layout and pass via `bash build.sh --test`.
- Python download scripts import and build URLs correctly (`py_compile`
clean).
- Added `tools/scripts/test_dep_rename_invariants.py` as a regression
guard asserting the two intentional exceptions (`/opt/ragflow_deps` and
`infiniflow/ragflow_deps`) stay intact, so a future blanket rename
cannot silently regress them.
---
## Follow-up fix (commit 2f6857095d)
The original rename used a blanket `sed s/ragflow_deps/deps/g` and only
selectively reverted `build.sh`. That left two intentionally-kept names
rewritten, which this follow-up restores:
- CI install path `/opt/ragflow_deps` — `sep-tests.yml` had been changed
to read `/opt/deps`, breaking the offline cl100k table fallback (the
cached-image path pointed at a directory that never receives the file).
Restored to `/opt/ragflow_deps`.
- Published image tag `infiniflow/ragflow_deps` — left as bare
`infiniflow/deps` in `sep-tests.yml` comments/echo, `.dockerignore`, and
`Dockerfile` / `Dockerfile_base` error messages. Restored to
`infiniflow/ragflow_deps`.
The regression guard `tools/scripts/test_dep_rename_invariants.py` was
added to prevent recurrence.
Research loop
- slot-table action sessions: per-slot research passes, evidence
prefill, shared tool cache and search dedup, near-duplicate retrieval
suppression, one-shot metadata_search guard, navigation ladder with
code-enforced rungs.
- pre-search fan-out: the snippet pool is shared equally between the
channels that actually offer chunks (A's quota no longer consumes the
whole pool), Channel B (hybrid, narrow bypass) re-enabled, Channel C
(metadata title pre-filter) added together with the metadata_search tool
and its no-metadata degradation path.
- evidence pool: session seeded with the full shared pool, raw-snippet
quota kept separate from evidence rows, pre-search capped at 18 chunks.
Tables
- tools/table_view.py renders chunk HTML tables to a Markdown view
(2-column infobox -> key:value, other tables -> full-row pipe table,
units rows dropped, caption kept, rows never pruned). Wired into the
action-session view, the grep/sed narrow output and the SCA evidence
anchor.
- table chunks are never narrowed and never char-trimmed: line-wise
narrowing either dropped the <table> opening tag (the renderer then
refused the fragment and the model received a partial raw-HTML row dump)
or silently dropped the answer rows, and row order/coverage is what
decides table answers.
- grep/sed: match-centred windows over raw chunks, wider per-chunk
output window.
xugangqiang
maoyifeng
Jin Hai
Wang Qi
jay77721
Sbaaoui Idriss
qinling0210
Caobaining1
pullfrog[bot]
Lynn
Zhichang Yu