docs(plans): fix broken CMU link to EMNLP 2004 Email Speech Acts paper#817
Merged
kovtcharov merged 1 commit intomainfrom Apr 20, 2026
Merged
docs(plans): fix broken CMU link to EMNLP 2004 Email Speech Acts paper#817kovtcharov merged 1 commit intomainfrom
kovtcharov merged 1 commit intomainfrom
Conversation
Swap the `cs.cmu.edu/~tom/EMNLP2004_final.pdf` URL (DNS-failing in CI, see
runs/24595902571) for the canonical ACL Anthology record at W04-3240.
Also restore the paper's actual title ("Learning to Classify Email into
'Speech Acts'") for consistency with the other full-title citations in
this list.
Unblocks the `Verify external URLs` check for every open PR.
Contributor
SummaryOne-line doc fix that swaps a dead Issues FoundNone. Strengths
VerdictApprove — ready to merge. Trivial, correct, and it unblocks CI for other open PRs. |
itomek
approved these changes
Apr 20, 2026
itomek
pushed a commit
that referenced
this pull request
Apr 22, 2026
#817) ## Summary One-line fix: swap the failing `www.cs.cmu.edu/~tom/EMNLP2004_final.pdf` URL in `docs/plans/email-triage-agent.mdx:2601` for the canonical ACL Anthology record at [W04-3240](https://aclanthology.org/W04-3240/). The CMU URL fails DNS resolution in CI (see [recent run](https://github.com/amd/gaia/actions/runs/24595902571/job/72072156929)), breaking the ``Verify external URLs`` check for every open PR that touches docs. ACL Anthology is the permanent archive for ACL/EMNLP papers — stable URL, no more link rot. Also restored the paper's actual full title ("Learning to Classify Email into 'Speech Acts'") for consistency with the other full-title citations in the same references list. ## Test plan - [x] `curl -sI https://aclanthology.org/W04-3240/` returns 200 - [ ] After merge, `Verify external URLs` check should go green on downstream PRs
pull Bot
pushed a commit
to bhardwajRahul/gaia
that referenced
this pull request
Apr 24, 2026
# GAIA v0.17.4 Release Notes
GAIA v0.17.4 is a patch release covering two correctness fixes in the
Agent UI custom-agent path, a null-safety fix in the C++ library for
smaller LLMs, and a broken docs citation.
**Why upgrade:**
- **Custom agents use their declared model** — If a custom agent sets a
model via `kwargs.setdefault("model_id", ...)`, the Agent UI now
respects that setting when the session is at the DB default, instead of
falling back to the session model.
- **Compatibility with smaller LLMs in the C++ library** — The C++ JSON
parser now tolerates `null` values in `"tool"` and `"content"` fields,
which some smaller models emit in place of omitting the field.
---
## What's New
### Custom Agent `model_id` Respected in the Agent UI
`_chat_helpers.py` previously passed `model_id=<session model>`
explicitly to `registry.create_agent()`, which defeated
`kwargs.setdefault("model_id", ...)` in custom agents — `setdefault`
only fires when the key is absent (PR
[amd#841](amd#841)). The Agent UI now builds
`create_kwargs` conditionally, omitting `model_id` when the session is
at the DB default so the agent's `__init__` setdefault governs.
Three-branch precedence is now explicit: `custom_model` setting >
session-explicit model > agent's own `setdefault`.
A follow-up fix (PR [amd#842](amd#842))
restored the pre-construction `model_id` as the agent-cache key. The
initial PR amd#841 landing had switched `_store_agent` to use the
post-construction `_effective_model(agent, model_id)` while
`_get_cached_agent` still looked up with `model_id`, so keys never
matched for custom-model agents and the agent was rebuilt on every turn.
A two-turn cache-hit regression test and a static guard on
`_store_agent` call sites were added alongside the fix.
Supporting refactor: extracted `_build_create_kwargs()` and
`_effective_model()` helpers in `src/gaia/ui/_chat_helpers.py` to
deduplicate the three-branch logic across streaming and non-streaming
paths, and exported `SESSION_DEFAULT_MODEL` from `database.py` as the
single source of truth.
---
### C++ Library: Null-Safety in LLM Response Parsing
`parseLlmResponse()` in `cpp/src/json_utils.cpp` now guards
`.get<std::string>()` calls on the `"tool"` and `"answer"` JSON fields
with `.is_string()` / `.is_null()` checks (PR
[amd#780](amd#780)). This fixes a crash
(`json.exception.type_error.302: type must be string, but is null`) when
smaller LLMs (for example `qwen3.5:9b`) return `null` for those fields
instead of omitting them. `json.contains()` returns `true` for `null`
values, so the existing presence checks were insufficient.
---
## Bug Fixes
- **Email-triage agent plan: broken CMU citation link** (PR
[amd#817](amd#817)) — Swapped the failing
`www.cs.cmu.edu/~tom/EMNLP2004_final.pdf` URL in
`docs/plans/email-triage-agent.mdx` for the canonical ACL Anthology
record at [W04-3240](https://aclanthology.org/W04-3240/). The CMU URL
was failing DNS resolution in CI, breaking the `Verify external URLs`
check on every open docs PR. Restored the paper's full title ("Learning
to Classify Email into 'Speech Acts'") for consistency with other
citations in the same references list.
---
## Full Changelog
**5 commits** since v0.17.3:
- `8fc43f3f` — fix(cpp): add null-safety checks for JSON string fields
in LLM response parsing (amd#780)
- `62722de2` — fix(ui): honor custom agent model_id when session is at
DB default (amd#841)
- `4acfd400` — fix(ui): extract _build_create_kwargs/_effective_model,
import SESSION_DEFAULT_MODEL
- `8f5c7621` — fix(ui): restore intent-key for agent cache store to fix
miss regression (amd#842)
- `a0fdb109` — docs(plans): fix broken CMU link to EMNLP 2004 Email
Speech Acts paper (amd#817)
Full Changelog:
[v0.17.3...v0.17.4](amd/gaia@v0.17.3...v0.17.4)
---
## Release checklist
- [x] `util/validate_release_notes.py docs/releases/v0.17.4.mdx --tag
v0.17.4` passes
- [x] `src/gaia/version.py` → `0.17.4`
- [x] `src/gaia/apps/webui/package.json` → `0.17.4`
- [x] Navbar label in `docs/docs.json` → `v0.17.4 · Lemonade 10.0.0`
- [x] All 5 commits in the range (v0.17.3..HEAD) are represented in the
notes
- [ ] Review from @kovtcharov-amd addressed
---------
Co-authored-by: Tomasz Iniewicz <tomasz.iniewicz@amd.com>
Co-authored-by: Kalin Ovtcharov <kalin@extropolis.ai>
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.
Summary
One-line fix: swap the failing
www.cs.cmu.edu/~tom/EMNLP2004_final.pdfURL indocs/plans/email-triage-agent.mdx:2601for the canonical ACL Anthology record at W04-3240. The CMU URL fails DNS resolution in CI (see recent run), breaking theVerify external URLscheck for every open PR that touches docs. ACL Anthology is the permanent archive for ACL/EMNLP papers — stable URL, no more link rot.Also restored the paper's actual full title ("Learning to Classify Email into 'Speech Acts'") for consistency with the other full-title citations in the same references list.
Test plan
curl -sI https://aclanthology.org/W04-3240/returns 200Verify external URLscheck should go green on downstream PRs