mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-11-20 09:47:42 -06:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
184862801a | ||
|
|
79e81b0bd4 | ||
|
|
059cac2848 | ||
|
|
cf4153a9ba | ||
|
|
8e7862411d | ||
|
|
e626db7caa | ||
|
|
c6a25fc622 | ||
|
|
5f837145d8 | ||
|
|
36cd3aff40 | ||
|
|
28de970cc1 | ||
|
|
4b69c79cca | ||
|
|
a1f4222608 | ||
|
|
4783b1145c | ||
|
|
6abcbe5d35 | ||
|
|
b81aa847c2 | ||
|
|
9d6f04fa99 | ||
|
|
652d559edf | ||
|
|
6aee50801d | ||
|
|
55b8d8d898 | ||
|
|
4c4a0f0a42 | ||
|
|
55d323507d | ||
|
|
bed8ec2f8d |
@@ -18,6 +18,10 @@ name: UI Lib Publish
|
||||
# ui-lib-publish.yml, and Environment left blank - this job names no environment, since creating
|
||||
# one needs repository admin. Merging this workflow before that exists leaves the publish step
|
||||
# red on master: the release is late rather than wrong, and re-running the job publishes it.
|
||||
#
|
||||
# The unscoped llama-ui is an alias: once the scoped package is out, the same build is renamed
|
||||
# and published again at the same version, so the two never drift. It is a package of its own
|
||||
# on npm, and needs the same trusted publisher set on it.
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
@@ -128,26 +132,29 @@ jobs:
|
||||
npm publish --access public --provenance --ignore-scripts --tag "$TAG"
|
||||
working-directory: ${{ env.LIB_DIR }}
|
||||
|
||||
- name: Verify it landed
|
||||
if: github.ref == 'refs/heads/master' && steps.version.outputs.should_publish == 'true' && inputs.dry_run != true
|
||||
- name: Rename the build to the unscoped alias
|
||||
# after the scoped publish, so nothing above sees the changed name. Not on a PR: the
|
||||
# advisory check there is about the version, which the alias shares.
|
||||
if: github.event_name != 'pull_request'
|
||||
run: node scripts/alias-package.mjs
|
||||
working-directory: ${{ env.LIB_DIR }}
|
||||
|
||||
- name: Compare the alias with npm
|
||||
id: alias
|
||||
if: github.event_name != 'pull_request'
|
||||
run: node scripts/npm-version-check.mjs
|
||||
working-directory: ${{ env.LIB_DIR }}
|
||||
|
||||
- name: Publish the alias
|
||||
# its own verdict rather than the scoped one's, so an alias that fell behind catches up
|
||||
# on the next run instead of waiting for a bump
|
||||
if: github.ref == 'refs/heads/master' && steps.alias.outputs.should_publish == 'true' && inputs.dry_run != true
|
||||
env:
|
||||
NAME: ${{ steps.version.outputs.name }}
|
||||
VERSION: ${{ steps.version.outputs.version }}
|
||||
TAG: ${{ steps.alias.outputs.tag }}
|
||||
run: |
|
||||
# the registry can serve a new version some time after publish returns, so retry rather
|
||||
# than call a release that worked a failure
|
||||
for try in 1 2 3 4 5 6; do
|
||||
seen=$(npm view "$NAME@$VERSION" version 2>/dev/null || true)
|
||||
if [ "$seen" = "$VERSION" ]; then
|
||||
echo "$NAME@$VERSION is on npm"
|
||||
npm view "$NAME@$VERSION" dist-tags version dist.integrity
|
||||
exit 0
|
||||
fi
|
||||
echo "not visible yet (attempt $try of 6)"
|
||||
sleep 10
|
||||
done
|
||||
echo "::error::$NAME@$VERSION published without error but is not visible on the registry after 6 attempts. The publish did not fail: check the package on npm before publishing again."
|
||||
exit 1
|
||||
test -d dist || { echo "dist/ is missing: nothing was built, so nothing is published"; exit 1; }
|
||||
npm publish --access public --provenance --ignore-scripts --tag "$TAG"
|
||||
working-directory: ${{ env.LIB_DIR }}
|
||||
|
||||
- name: Report
|
||||
if: always()
|
||||
@@ -161,6 +168,11 @@ jobs:
|
||||
NOTE: ${{ steps.version.outputs.note }}
|
||||
SHOULD: ${{ steps.version.outputs.should_publish }}
|
||||
DRY: ${{ inputs.dry_run }}
|
||||
ALIAS_LATEST: ${{ steps.alias.outputs.latest }}
|
||||
ALIAS_VERDICT: ${{ steps.alias.outputs.verdict || 'not reached' }}
|
||||
ALIAS_NOTE: ${{ steps.alias.outputs.note }}
|
||||
ALIAS_SHOULD: ${{ steps.alias.outputs.should_publish }}
|
||||
EVENT: ${{ github.event_name }}
|
||||
run: |
|
||||
if [ "$DRY" = "true" ]; then published="no (dry run)"
|
||||
elif [ "$SHOULD" = "true" ]; then published=yes
|
||||
@@ -177,6 +189,23 @@ jobs:
|
||||
echo
|
||||
echo "> $NOTE"
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
[ "$EVENT" = "pull_request" ] && exit 0
|
||||
if [ "$DRY" = "true" ]; then published="no (dry run)"
|
||||
elif [ "$ALIAS_SHOULD" = "true" ]; then published=yes
|
||||
else published=no
|
||||
fi
|
||||
{
|
||||
echo
|
||||
echo "### llama-ui (alias) $VERSION"
|
||||
echo
|
||||
echo "| | |"
|
||||
echo "| --- | --- |"
|
||||
echo "| npm latest was | ${ALIAS_LATEST:-nothing published yet} |"
|
||||
echo "| verdict | \`$ALIAS_VERDICT\` |"
|
||||
echo "| published | $published |"
|
||||
echo
|
||||
echo "> $ALIAS_NOTE"
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
|
||||
- name: Mind the verdict
|
||||
if: always() && github.event_name != 'pull_request' && steps.version.outcome == 'success'
|
||||
|
||||
@@ -19,6 +19,7 @@ on:
|
||||
'.github/workflows/ui-build-self-hosted.yml',
|
||||
'ui/apps/chat/**.*',
|
||||
'ui/lib/ui/**.*',
|
||||
'ui/lib/voice/**.*',
|
||||
'tools/server/tests/**.*'
|
||||
]
|
||||
pull_request:
|
||||
@@ -28,6 +29,7 @@ on:
|
||||
'.github/workflows/ui-build-self-hosted.yml',
|
||||
'ui/apps/chat/**.*',
|
||||
'ui/lib/ui/**.*',
|
||||
'ui/lib/voice/**.*',
|
||||
'tools/server/tests/**.*'
|
||||
]
|
||||
|
||||
|
||||
@@ -150,6 +150,37 @@ jobs:
|
||||
run: npm run prepack
|
||||
working-directory: ui/lib/ui
|
||||
|
||||
voice-checks:
|
||||
name: Voice checks
|
||||
runs-on: ubuntu-24.04
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v6
|
||||
with:
|
||||
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
|
||||
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: "24"
|
||||
package-manager-cache: false
|
||||
|
||||
- name: Install dependencies
|
||||
run: npm ci
|
||||
working-directory: ui/lib/voice
|
||||
|
||||
- name: Run type checking
|
||||
run: npm run check
|
||||
working-directory: ui/lib/voice
|
||||
|
||||
- name: Run tests
|
||||
run: npm test
|
||||
working-directory: ui/lib/voice
|
||||
|
||||
- name: Build the package
|
||||
run: npm run prepack
|
||||
working-directory: ui/lib/voice
|
||||
|
||||
e2e-tests:
|
||||
name: E2E Tests
|
||||
needs: ui-build
|
||||
|
||||
+9
-1
@@ -3420,12 +3420,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
||||
add_opt(common_arg(
|
||||
{"--ui-mcp-proxy", "--webui-mcp-proxy"},
|
||||
{"--no-ui-mcp-proxy", "--no-webui-mcp-proxy"},
|
||||
"experimental: whether to enable MCP CORS proxy, for Llama Chat to reach public MCP servers without CORS headers; local and private addresses are refused - do not enable in untrusted environments (default: disabled)\n"
|
||||
"experimental: whether to enable MCP CORS proxy, for Llama Chat to reach public MCP servers without CORS headers; local and private addresses are refused unless --ui-mcp-proxy-allow-private-urls is set - do not enable in untrusted environments (default: disabled)\n"
|
||||
"note: for security reasons, this will limit --cors-origins to localhost by default",
|
||||
[](common_params & params, bool value) {
|
||||
params.ui_mcp_proxy = value;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_UI_MCP_PROXY"));
|
||||
add_opt(common_arg(
|
||||
{"--ui-mcp-proxy-allow-private-urls"},
|
||||
"allow the MCP CORS proxy to reach local or private addresses (e.g. MCP servers on localhost or LAN) - anyone who can reach the proxy can then reach your local network (default: disabled, only public addresses)\n"
|
||||
"note: only has effect with --ui-mcp-proxy",
|
||||
[](common_params & params) {
|
||||
params.ui_mcp_proxy_allow_private_urls = true;
|
||||
}
|
||||
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_UI_MCP_PROXY_ALLOW_PRIVATE_URLS"));
|
||||
add_opt(common_arg(
|
||||
{"--tools"}, "TOOL1,TOOL2,...",
|
||||
"experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)\n"
|
||||
|
||||
@@ -702,6 +702,7 @@ struct common_params {
|
||||
// UI configs
|
||||
bool ui = true;
|
||||
bool ui_mcp_proxy = false;
|
||||
bool ui_mcp_proxy_allow_private_urls = false; // allow the MCP CORS proxy to reach local or private addresses
|
||||
std::string ui_config_json;
|
||||
|
||||
// "advanced" endpoints are disabled by default for better security
|
||||
|
||||
@@ -78,6 +78,7 @@ TEXT_MODEL_MAP: dict[str, str] = {
|
||||
"DistilBertForMaskedLM": "bert",
|
||||
"DistilBertForSequenceClassification": "bert",
|
||||
"DistilBertModel": "bert",
|
||||
"DomynEdgeForCausalLM": "domynedge",
|
||||
"Dots1ForCausalLM": "dots1",
|
||||
"Dots3NoteForCausalLM": "dots3",
|
||||
"Dots3NoteForConditionalGeneration": "dots3",
|
||||
|
||||
@@ -2470,6 +2470,9 @@ class TextModel(ModelBase):
|
||||
if chkhsh == "5635e1c8d621dff7b4825f41f2f97b6ceb39bcf2d5c541db28577080d6efd5e5":
|
||||
# ref: https://huggingface.co/thinkingmachines/Inkling-2-Small
|
||||
res = "inkling2"
|
||||
if chkhsh == "32d85c31273f8019248f2559fed492d929ea28b17e51d81d3bb36fff23ca72b3":
|
||||
# ref: https://huggingface.co/domyn/Domyn-Edge-Teacher-IF
|
||||
res = "domyn-edge"
|
||||
|
||||
if res is None:
|
||||
logger.warning("\n")
|
||||
|
||||
@@ -0,0 +1,53 @@
|
||||
from .base import TextModel, ModelBase
|
||||
import gguf
|
||||
|
||||
|
||||
@ModelBase.register("DomynEdgeForCausalLM")
|
||||
@ModelBase.example("domyn/Domyn-Edge-Teacher-IF")
|
||||
class DomynEdgeModel(TextModel):
|
||||
model_arch = gguf.MODEL_ARCH.DOMYN_EDGE
|
||||
|
||||
def set_gguf_parameters(self):
|
||||
super().set_gguf_parameters()
|
||||
hparams = self.hparams
|
||||
self.gguf_writer.add_vocab_size(hparams["vocab_size"])
|
||||
|
||||
position_layers = hparams["position_layers"] # list of "rope"/"nope" strings per layer
|
||||
head_sizes = hparams["head_sizes"] # list of int head dims per layer
|
||||
|
||||
# Per-layer rope/SWA pattern: True="rope", False="nope"
|
||||
rope_pattern = [v == "rope" for v in position_layers]
|
||||
self.gguf_writer.add_rope_pattern(rope_pattern)
|
||||
self.gguf_writer.add_sliding_window_pattern(rope_pattern) # SWA <-> RoPE in domyn-edge
|
||||
|
||||
# window_sizes entries are flash-attn style [left, right] (current token excluded; -1 = full attention),
|
||||
# while llama.cpp's n_swa counts the current token, hence the +1 (matches HF's sliding_window=1025)
|
||||
swa_window = hparams.get("sliding_window")
|
||||
if swa_window is None:
|
||||
window_sizes = hparams.get("window_sizes") # list of [size, offset] pairs per layer
|
||||
if window_sizes is None:
|
||||
raise KeyError("Neither `sliding_window` nor `window_sizes` found among domyn edge hyperparameters")
|
||||
left = next((ws[0] for v, ws in zip(position_layers, window_sizes) if v == "rope"), None)
|
||||
swa_window = left + 1 if left is not None and left > 0 else None
|
||||
if swa_window is None:
|
||||
raise ValueError("No sliding window size found among domyn edge hyperparameters")
|
||||
self.gguf_writer.add_sliding_window(swa_window)
|
||||
|
||||
# Head dims differ between full-attention ("nope") and SWA ("rope") layers
|
||||
full_head_dims = {h for v, h in zip(position_layers, head_sizes) if v == "nope"}
|
||||
swa_head_dims = {h for v, h in zip(position_layers, head_sizes) if v == "rope"}
|
||||
|
||||
if len(full_head_dims) != 1:
|
||||
raise ValueError(f"Expected one head dimension for full attention layers, found {len(full_head_dims)}")
|
||||
full_head_dim = full_head_dims.pop()
|
||||
|
||||
self.gguf_writer.add_key_length(full_head_dim)
|
||||
self.gguf_writer.add_value_length(full_head_dim)
|
||||
|
||||
if len(swa_head_dims) != 1:
|
||||
raise ValueError(f"Expected one head dimension for SWA attention layers, found {len(swa_head_dims)}")
|
||||
swa_head_dim = swa_head_dims.pop()
|
||||
|
||||
self.gguf_writer.add_key_length_swa(swa_head_dim)
|
||||
self.gguf_writer.add_value_length_swa(swa_head_dim)
|
||||
self.gguf_writer.add_rope_dimension_count_swa(swa_head_dim)
|
||||
@@ -168,6 +168,7 @@ models = [
|
||||
{"name": "mmbert", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jhu-clsp/mmBERT-base", },
|
||||
{"name": "k2-horizon", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/IFM/K2-Horizon-36B", },
|
||||
{"name": "inkling2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/thinkingmachines/Inkling-2-Small", },
|
||||
{"name": "domyn-edge", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/domyn/Domyn-Edge-Teacher-IF", },
|
||||
]
|
||||
|
||||
# some models are known to be broken upstream, so we will skip them as exceptions
|
||||
@@ -227,8 +228,6 @@ def download_model(model):
|
||||
repo = model["repo"]
|
||||
tokt = model["tokt"]
|
||||
|
||||
os.makedirs(f"models/tokenizers/{name}", exist_ok=True)
|
||||
|
||||
files = ["config.json", "tokenizer.json", "tokenizer_config.json"]
|
||||
|
||||
if name == "gpt-4o":
|
||||
@@ -243,6 +242,7 @@ def download_model(model):
|
||||
|
||||
if os.path.isdir(repo):
|
||||
# If repo is a path on the file system, copy the directory
|
||||
os.makedirs(f"models/tokenizers/{name}", exist_ok=True)
|
||||
for file in files:
|
||||
src_path = os.path.join(repo, file)
|
||||
dst_path = f"models/tokenizers/{name}/{file}"
|
||||
@@ -484,7 +484,7 @@ for model in models:
|
||||
tokenizer = AutoTokenizer.from_pretrained(f"models/tokenizers/{name}", use_fast=False)
|
||||
else:
|
||||
tokenizer = AutoTokenizer.from_pretrained(f"models/tokenizers/{name}")
|
||||
except (OSError, TypeError) as e:
|
||||
except (OSError, TypeError, ValueError) as e:
|
||||
logger.error(f"Failed to load tokenizer for model {name}. Error: {e}")
|
||||
continue # Skip this model and continue with the next one in the loop
|
||||
|
||||
|
||||
@@ -1474,6 +1474,282 @@ class tinyBLAS_Q0_VXE {
|
||||
const int32_t ith;
|
||||
const int32_t nth;
|
||||
};
|
||||
|
||||
template <typename TA>
|
||||
class tinyBLAS_QK_VXE {
|
||||
public:
|
||||
tinyBLAS_QK_VXE(int64_t k,
|
||||
const TA * A, int64_t lda,
|
||||
const block_q8_K * B, int64_t ldb,
|
||||
float * C, int64_t ldc,
|
||||
int32_t ith, int32_t nth)
|
||||
: A(A), B(B), C(C), k(k), lda(lda), ldb(ldb), ldc(ldc), ith(ith), nth(nth) {
|
||||
}
|
||||
|
||||
void matmul(int64_t m, int64_t n) {
|
||||
const int64_t n4 = n / 4 * 4;
|
||||
const int64_t n2 = n / 2 * 2;
|
||||
gemm<4>(m, 0, n4);
|
||||
gemm<2>(m, n4, n2);
|
||||
gemm<1>(m, n2, n);
|
||||
}
|
||||
|
||||
private:
|
||||
// one block of A is loaded once and used for RN columns of B
|
||||
template <int32_t RN>
|
||||
void gemm(int64_t m, int64_t n0, int64_t n) {
|
||||
const int64_t tiles = m * ((n - n0) / RN);
|
||||
const int64_t duty = (tiles + nth - 1) / nth;
|
||||
const int64_t start = duty * ith;
|
||||
const int64_t end = MIN(start + duty, tiles);
|
||||
|
||||
for (int64_t job = start; job < end; ++job) {
|
||||
const int64_t ii = job % m;
|
||||
const int64_t jj = n0 + RN * (job / m);
|
||||
float32x4_t v_sum[RN] = {};
|
||||
|
||||
for (int64_t l = 0; l < k; ++l) {
|
||||
const TA & x = A[lda * ii + l];
|
||||
|
||||
int8x16_t v_x[n_group];
|
||||
load(x, v_x);
|
||||
|
||||
// scale and minimum of the 16 groups, 8 groups per vector
|
||||
int16x8_t v_scalel, v_scaleh;
|
||||
int16x8_t v_minl, v_minh;
|
||||
load_scale(x, v_scalel, v_scaleh, v_minl, v_minh);
|
||||
|
||||
int16x8_t v_scale[n_group];
|
||||
for (int32_t g = 0; g < n_group; ++g) {
|
||||
v_scale[g] = vec_splats((g < n_group / 2 ? v_scalel : v_scaleh)[g % (n_group / 2)]);
|
||||
}
|
||||
|
||||
const int8_t * y_qs[RN];
|
||||
for (int32_t j = 0; j < RN; ++j) {
|
||||
y_qs[j] = B[ldb * (jj + j) + l].qs;
|
||||
}
|
||||
|
||||
// the columns are in the inner loop, so that their sums do not wait for each other
|
||||
int32x4_t v_dot[RN] = {};
|
||||
for (int32_t g = 0; g < n_group; ++g) {
|
||||
for (int32_t j = 0; j < RN; ++j) {
|
||||
const int8x16_t v_y = vec_xl(0, y_qs[j] + 16 * g);
|
||||
const int16x8_t v_xy = vec_meadd(v_x[g], v_y, vec_mulo(v_x[g], v_y));
|
||||
v_dot[j] = vec_meadd(v_xy, v_scale[g], vec_moadd(v_xy, v_scale[g], v_dot[j]));
|
||||
}
|
||||
}
|
||||
|
||||
const float x_d = unhalf(x.d);
|
||||
for (int32_t j = 0; j < RN; ++j) {
|
||||
const block_q8_K & y = B[ldb * (jj + j) + l];
|
||||
v_sum[j] = vec_madd(vec_float(v_dot[j]), vec_splats(x_d * y.d), v_sum[j]);
|
||||
}
|
||||
|
||||
if (has_min) {
|
||||
const float x_dmin = dmin(x);
|
||||
|
||||
for (int32_t j = 0; j < RN; ++j) {
|
||||
const block_q8_K & y = B[ldb * (jj + j) + l];
|
||||
|
||||
const int16_t * y_bsums = y.bsums;
|
||||
const int16x8_t v_bsumsl = vec_xl(0, y_bsums);
|
||||
const int16x8_t v_bsumsh = vec_xl(0, y_bsums + n_group / 2);
|
||||
|
||||
const int32x4_t v_minsl = vec_meadd(v_bsumsl, v_minl, vec_mulo(v_bsumsl, v_minl));
|
||||
const int32x4_t v_minsh = vec_meadd(v_bsumsh, v_minh, vec_mulo(v_bsumsh, v_minh));
|
||||
v_sum[j] = vec_madd(vec_float(v_minsl + v_minsh), vec_splats(-x_dmin * y.d), v_sum[j]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for (int32_t j = 0; j < RN; ++j) {
|
||||
C[ldc * (jj + j) + ii] = hsum(v_sum[j]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// a block has 16 groups of 16 weights, Q4_K and Q5_K share one scale and minimum per 2 groups
|
||||
static constexpr int32_t n_group = QK_K / 16;
|
||||
|
||||
// Q3_K and Q6_K have no minimum, their weights are loaded as signed values.
|
||||
static constexpr bool has_min = !std::is_same<TA, block_q3_K>::value && !std::is_same<TA, block_q6_K>::value;
|
||||
|
||||
static float dmin(const block_q2_K & x) { return unhalf(x.dmin); }
|
||||
static float dmin(const block_q4_K & x) { return unhalf(x.dmin); }
|
||||
static float dmin(const block_q5_K & x) { return unhalf(x.dmin); }
|
||||
template <typename T> static float dmin(const T &) { return 0.0f; }
|
||||
|
||||
static void load(const block_q2_K & x, int8x16_t * v_x) {
|
||||
const uint8x16_t v_mask = vec_splats((uint8_t)0x03);
|
||||
const uint8_t * x_qs = x.qs;
|
||||
|
||||
for (int32_t g = 0; g < n_group; ++g) {
|
||||
const int32_t qs_offset = 16 * (2 * (g / 8) + g % 2);
|
||||
const int32_t qs_shift = 2 * (g % 8 / 2);
|
||||
|
||||
const uint8x16_t v_qs = vec_xl(0, x_qs + qs_offset);
|
||||
v_x[g] = (int8x16_t)vec_and(vec_sr(v_qs, qs_shift), v_mask);
|
||||
}
|
||||
}
|
||||
|
||||
static void load(const block_q3_K & x, int8x16_t * v_x) {
|
||||
const uint8x16_t v_mask = vec_splats((uint8_t)0x03);
|
||||
const uint8x16_t v_one = vec_splats((uint8_t)0x01);
|
||||
|
||||
const uint8_t * x_qs = x.qs;
|
||||
const uint8_t * x_hmask = x.hmask;
|
||||
|
||||
for (int32_t g = 0; g < n_group; ++g) {
|
||||
const int32_t qs_offset = 16 * (2 * (g / 8) + g % 2);
|
||||
const int32_t qs_shift = 2 * (g % 8 / 2);
|
||||
const int32_t hmask_offset = 16 * (g % 2);
|
||||
const int32_t hmask_shift = g / 2;
|
||||
|
||||
const uint8x16_t v_qs = vec_xl(0, x_qs + qs_offset);
|
||||
const uint8x16_t v_hmask = vec_xl(0, x_hmask + hmask_offset);
|
||||
const uint8x16_t v_lo = vec_and(vec_sr(v_qs, qs_shift), v_mask);
|
||||
const uint8x16_t v_hi = vec_sl(vec_and(vec_sr(v_hmask, hmask_shift), v_one), 2);
|
||||
v_x[g] = (int8x16_t)vec_or(v_lo, v_hi) - vec_splats((int8_t)4);
|
||||
}
|
||||
}
|
||||
|
||||
static void load(const block_q4_K & x, int8x16_t * v_x) {
|
||||
const uint8x16_t v_mask = vec_splats((uint8_t)0x0F);
|
||||
const uint8_t * x_qs = x.qs;
|
||||
|
||||
for (int32_t g = 0; g < n_group; ++g) {
|
||||
const int32_t qs_offset = 16 * (2 * (g / 4) + g % 2);
|
||||
const bool qs_low = g % 4 < 2;
|
||||
|
||||
const uint8x16_t v_qs = vec_xl(0, x_qs + qs_offset);
|
||||
v_x[g] = (int8x16_t)(qs_low ? vec_and(v_qs, v_mask) : vec_sr(v_qs, 4));
|
||||
}
|
||||
}
|
||||
|
||||
static void load(const block_q5_K & x, int8x16_t * v_x) {
|
||||
const uint8x16_t v_mask = vec_splats((uint8_t)0x0F);
|
||||
const uint8x16_t v_one = vec_splats((uint8_t)0x01);
|
||||
const uint8_t * x_qs = x.qs;
|
||||
const uint8_t * x_qh = x.qh;
|
||||
|
||||
for (int32_t g = 0; g < n_group; ++g) {
|
||||
const int32_t qs_offset = 16 * (2 * (g / 4) + g % 2);
|
||||
const bool qs_low = g % 4 < 2;
|
||||
const int32_t qh_offset = 16 * (g % 2);
|
||||
const int32_t qh_shift = g / 2;
|
||||
|
||||
const uint8x16_t v_qs = vec_xl(0, x_qs + qs_offset);
|
||||
const uint8x16_t v_qh = vec_xl(0, x_qh + qh_offset);
|
||||
const uint8x16_t v_lo = qs_low ? vec_and(v_qs, v_mask) : vec_sr(v_qs, 4);
|
||||
const uint8x16_t v_hi = vec_sl(vec_and(vec_sr(v_qh, qh_shift), v_one), 4);
|
||||
v_x[g] = (int8x16_t)vec_or(v_lo, v_hi);
|
||||
}
|
||||
}
|
||||
|
||||
static void load(const block_q6_K & x, int8x16_t * v_x) {
|
||||
const uint8x16_t v_mask4 = vec_splats((uint8_t)0x0F);
|
||||
const uint8x16_t v_mask2 = vec_splats((uint8_t)0x03);
|
||||
const uint8_t * x_ql = x.ql;
|
||||
const uint8_t * x_qh = x.qh;
|
||||
|
||||
for (int32_t g = 0; g < n_group; ++g) {
|
||||
const int32_t ql_offset = 16 * (4 * (g / 8) + 2 * (g % 4 / 2) + g % 2);
|
||||
const bool ql_low = g % 8 < 4;
|
||||
const int32_t qh_offset = 16 * (2 * (g / 8) + g % 2);
|
||||
const int32_t qh_shift = 2 * (g % 8 / 2);
|
||||
|
||||
const uint8x16_t v_ql = vec_xl(0, x_ql + ql_offset);
|
||||
const uint8x16_t v_qh = vec_xl(0, x_qh + qh_offset);
|
||||
const uint8x16_t v_lo = ql_low ? vec_and(v_ql, v_mask4) : vec_sr(v_ql, 4);
|
||||
const uint8x16_t v_hi = vec_sl(vec_and(vec_sr(v_qh, qh_shift), v_mask2), 4);
|
||||
v_x[g] = (int8x16_t)vec_or(v_lo, v_hi) - vec_splats((int8_t)32);
|
||||
}
|
||||
}
|
||||
|
||||
static void load_scale(const block_q2_K & x, int16x8_t & v_scalel, int16x8_t & v_scaleh, int16x8_t & v_minl, int16x8_t & v_minh) {
|
||||
const uint8_t * x_scales = x.scales;
|
||||
const uint8x16_t v_s = vec_xl(0, x_scales);
|
||||
const uint8x16_t v_scale = vec_and(v_s, vec_splats((uint8_t)0x0F));
|
||||
const uint8x16_t v_min = vec_sr(v_s, 4);
|
||||
|
||||
v_scalel = (int16x8_t)vec_unpackh(v_scale);
|
||||
v_scaleh = (int16x8_t)vec_unpackl(v_scale);
|
||||
v_minl = (int16x8_t)vec_unpackh(v_min);
|
||||
v_minh = (int16x8_t)vec_unpackl(v_min);
|
||||
}
|
||||
|
||||
static void load_scale(const block_q3_K & x, int16x8_t & v_scalel, int16x8_t & v_scaleh, int16x8_t & v_minl, int16x8_t & v_minh) {
|
||||
// 6-bit scales: low 4 bits in scales[0..7], high 2 bits in scales[8..11]
|
||||
const uint8x16_t v_lo_byte = { 4, 5, 6, 7, 8, 9, 10, 11, 4, 5, 6, 7, 8, 9, 10, 11 };
|
||||
const uint8x16_t v_lo_shift = { 0, 0, 0, 0, 0, 0, 0, 0, 4, 4, 4, 4, 4, 4, 4, 4 };
|
||||
const uint8x16_t v_hi_byte = { 12, 13, 14, 15, 12, 13, 14, 15, 12, 13, 14, 15, 12, 13, 14, 15 };
|
||||
const uint8x16_t v_hi_shift = { 0, 0, 0, 0, 2, 2, 2, 2, 4, 4, 4, 4, 6, 6, 6, 6 };
|
||||
|
||||
// the load starts 4 bytes before scales, so that it stays inside the block
|
||||
const uint8_t * x_qs = x.qs;
|
||||
const uint8x16_t v_s = vec_xl(0, x_qs + sizeof(x.qs) - 4);
|
||||
const uint8x16_t v_lo = vec_and(vec_sr(vec_perm(v_s, v_s, v_lo_byte), v_lo_shift), vec_splats((uint8_t)0x0F));
|
||||
const uint8x16_t v_hi = vec_sl(vec_and(vec_sr(vec_perm(v_s, v_s, v_hi_byte), v_hi_shift), vec_splats((uint8_t)0x03)), 4);
|
||||
const int8x16_t v_scale = (int8x16_t)vec_or(v_lo, v_hi) - vec_splats((int8_t)32);
|
||||
|
||||
v_scalel = vec_unpackh(v_scale);
|
||||
v_scaleh = vec_unpackl(v_scale);
|
||||
v_minl = vec_splats((int16_t)0);
|
||||
v_minh = vec_splats((int16_t)0);
|
||||
}
|
||||
|
||||
static void load_scale(const block_q4_K & x, int16x8_t & v_scalel, int16x8_t & v_scaleh, int16x8_t & v_minl, int16x8_t & v_minh) {
|
||||
load_scale_min_k4(x.scales, v_scalel, v_scaleh, v_minl, v_minh);
|
||||
}
|
||||
|
||||
static void load_scale(const block_q5_K & x, int16x8_t & v_scalel, int16x8_t & v_scaleh, int16x8_t & v_minl, int16x8_t & v_minh) {
|
||||
load_scale_min_k4(x.scales, v_scalel, v_scaleh, v_minl, v_minh);
|
||||
}
|
||||
|
||||
static void load_scale(const block_q6_K & x, int16x8_t & v_scalel, int16x8_t & v_scaleh, int16x8_t & v_minl, int16x8_t & v_minh) {
|
||||
const int8_t * x_scales = x.scales;
|
||||
const int8x16_t v_scale = vec_xl(0, x_scales);
|
||||
|
||||
v_scalel = vec_unpackh(v_scale);
|
||||
v_scaleh = vec_unpackl(v_scale);
|
||||
v_minl = vec_splats((int16_t)0);
|
||||
v_minh = vec_splats((int16_t)0);
|
||||
}
|
||||
|
||||
// 8 scales and 8 minimums of 6 bits, same packing as get_scale_min_k4 in ggml-quants.c
|
||||
static void load_scale_min_k4(const uint8_t * q, int16x8_t & v_scalel, int16x8_t & v_scaleh, int16x8_t & v_minl, int16x8_t & v_minh) {
|
||||
// bytes 0..3 and 4..7 have the high 2 bits of scale 4..7 and minimum 4..7, move them to bytes 8..11
|
||||
const uint8x16_t v_hi_scale = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 2, 3, 0, 0, 0, 0 };
|
||||
const uint8x16_t v_hi_min = { 0, 0, 0, 0, 0, 0, 0, 0, 4, 5, 6, 7, 0, 0, 0, 0 };
|
||||
// each scale and minimum is for 2 groups
|
||||
const uint8x16_t v_group_scale = { 0, 0, 1, 1, 2, 2, 3, 3, 24, 24, 25, 25, 26, 26, 27, 27 };
|
||||
const uint8x16_t v_group_min = { 4, 4, 5, 5, 6, 6, 7, 7, 24, 24, 25, 25, 26, 26, 27, 27 };
|
||||
|
||||
// the 4 bytes after the 12 scale bytes are in the same block
|
||||
const uint8x16_t v_s = vec_xl(0, q);
|
||||
const uint8x16_t v_lo = vec_and(v_s, vec_splats((uint8_t)0x3F));
|
||||
const uint8x16_t v_hi = vec_sl(vec_sr(v_s, 6), 4);
|
||||
const uint8x16_t v_scale_47 = vec_or(vec_and(v_s, vec_splats((uint8_t)0x0F)), vec_perm(v_hi, v_hi, v_hi_scale));
|
||||
const uint8x16_t v_min_47 = vec_or(vec_sr(v_s, 4), vec_perm(v_hi, v_hi, v_hi_min));
|
||||
const uint8x16_t v_scale = vec_perm(v_lo, v_scale_47, v_group_scale);
|
||||
const uint8x16_t v_min = vec_perm(v_lo, v_min_47, v_group_min);
|
||||
|
||||
v_scalel = (int16x8_t)vec_unpackh(v_scale);
|
||||
v_scaleh = (int16x8_t)vec_unpackl(v_scale);
|
||||
v_minl = (int16x8_t)vec_unpackh(v_min);
|
||||
v_minh = (int16x8_t)vec_unpackl(v_min);
|
||||
}
|
||||
|
||||
const TA * const A;
|
||||
const block_q8_K * const B;
|
||||
float * const C;
|
||||
const int64_t k;
|
||||
const int64_t lda;
|
||||
const int64_t ldb;
|
||||
const int64_t ldc;
|
||||
const int32_t ith;
|
||||
const int32_t nth;
|
||||
};
|
||||
#endif
|
||||
|
||||
#if defined(__ARM_FEATURE_DOTPROD)
|
||||
@@ -4488,6 +4764,91 @@ bool llamafile_sgemm(const struct ggml_compute_params * params, int64_t m, int64
|
||||
#endif
|
||||
}
|
||||
|
||||
case GGML_TYPE_Q2_K: {
|
||||
if (Btype != GGML_TYPE_Q8_K) {
|
||||
return false;
|
||||
}
|
||||
#if defined(__VXE__) || defined(__VXE2__)
|
||||
tinyBLAS_QK_VXE<block_q2_K> tb{
|
||||
k, (const block_q2_K *)A, lda,
|
||||
(const block_q8_K *)B, ldb,
|
||||
(float *)C, ldc,
|
||||
params->ith, params->nth};
|
||||
tb.matmul(m, n);
|
||||
return true;
|
||||
#else
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
|
||||
case GGML_TYPE_Q3_K: {
|
||||
if (Btype != GGML_TYPE_Q8_K) {
|
||||
return false;
|
||||
}
|
||||
#if defined(__VXE__) || defined(__VXE2__)
|
||||
tinyBLAS_QK_VXE<block_q3_K> tb{
|
||||
k, (const block_q3_K *)A, lda,
|
||||
(const block_q8_K *)B, ldb,
|
||||
(float *)C, ldc,
|
||||
params->ith, params->nth};
|
||||
tb.matmul(m, n);
|
||||
return true;
|
||||
#else
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
|
||||
case GGML_TYPE_Q4_K: {
|
||||
if (Btype != GGML_TYPE_Q8_K) {
|
||||
return false;
|
||||
}
|
||||
#if defined(__VXE__) || defined(__VXE2__)
|
||||
tinyBLAS_QK_VXE<block_q4_K> tb{
|
||||
k, (const block_q4_K *)A, lda,
|
||||
(const block_q8_K *)B, ldb,
|
||||
(float *)C, ldc,
|
||||
params->ith, params->nth};
|
||||
tb.matmul(m, n);
|
||||
return true;
|
||||
#else
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
|
||||
case GGML_TYPE_Q5_K: {
|
||||
if (Btype != GGML_TYPE_Q8_K) {
|
||||
return false;
|
||||
}
|
||||
#if defined(__VXE__) || defined(__VXE2__)
|
||||
tinyBLAS_QK_VXE<block_q5_K> tb{
|
||||
k, (const block_q5_K *)A, lda,
|
||||
(const block_q8_K *)B, ldb,
|
||||
(float *)C, ldc,
|
||||
params->ith, params->nth};
|
||||
tb.matmul(m, n);
|
||||
return true;
|
||||
#else
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
|
||||
case GGML_TYPE_Q6_K: {
|
||||
if (Btype != GGML_TYPE_Q8_K) {
|
||||
return false;
|
||||
}
|
||||
#if defined(__VXE__) || defined(__VXE2__)
|
||||
tinyBLAS_QK_VXE<block_q6_K> tb{
|
||||
k, (const block_q6_K *)A, lda,
|
||||
(const block_q8_K *)B, ldb,
|
||||
(float *)C, ldc,
|
||||
params->ith, params->nth};
|
||||
tb.matmul(m, n);
|
||||
return true;
|
||||
#else
|
||||
return false;
|
||||
#endif
|
||||
}
|
||||
|
||||
case GGML_TYPE_IQ4_NL: {
|
||||
if (Btype != GGML_TYPE_Q8_0)
|
||||
return false;
|
||||
|
||||
@@ -6798,7 +6798,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
|
||||
case GGML_OP_RWKV_WKV7:
|
||||
return true;
|
||||
case GGML_OP_GATED_DELTA_NET:
|
||||
return true;
|
||||
return ggml_are_same_stride(op->src[0], op->src[1]);
|
||||
case GGML_OP_DSV4_HC_COMB:
|
||||
return op->src[0]->type == GGML_TYPE_F32 && op->src[1]->type == GGML_TYPE_F32 &&
|
||||
op->src[2]->type == GGML_TYPE_F32 && op->type == GGML_TYPE_F32;
|
||||
|
||||
@@ -778,6 +778,7 @@ class MODEL_ARCH(IntEnum):
|
||||
KOLIBRI1 = auto()
|
||||
LIMITE = auto()
|
||||
INKLING2 = auto()
|
||||
DOMYN_EDGE = auto()
|
||||
|
||||
|
||||
class VISION_PROJECTOR_TYPE(IntEnum):
|
||||
@@ -1778,6 +1779,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
|
||||
MODEL_ARCH.KOLIBRI1: "kolibri1",
|
||||
MODEL_ARCH.LIMITE: "limite",
|
||||
MODEL_ARCH.INKLING2: "inkling2",
|
||||
MODEL_ARCH.DOMYN_EDGE: "domynedge",
|
||||
}
|
||||
|
||||
VISION_PROJECTOR_TYPE_NAMES: dict[VISION_PROJECTOR_TYPE, str] = {
|
||||
@@ -7085,6 +7087,22 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
|
||||
MODEL_TENSOR.FFN_POST_CONV,
|
||||
MODEL_TENSOR.FFN_RES_QUERY,
|
||||
],
|
||||
MODEL_ARCH.DOMYN_EDGE: [
|
||||
MODEL_TENSOR.TOKEN_EMBD,
|
||||
MODEL_TENSOR.ATTN_Q,
|
||||
MODEL_TENSOR.ATTN_K,
|
||||
MODEL_TENSOR.ATTN_V,
|
||||
MODEL_TENSOR.ATTN_OUT,
|
||||
MODEL_TENSOR.ATTN_K_NORM,
|
||||
MODEL_TENSOR.ATTN_NORM,
|
||||
MODEL_TENSOR.ATTN_POST_NORM,
|
||||
MODEL_TENSOR.FFN_PRE_NORM,
|
||||
MODEL_TENSOR.FFN_POST_NORM,
|
||||
MODEL_TENSOR.FFN_DOWN,
|
||||
MODEL_TENSOR.FFN_UP,
|
||||
MODEL_TENSOR.FFN_GATE,
|
||||
MODEL_TENSOR.OUTPUT_NORM,
|
||||
],
|
||||
}
|
||||
|
||||
# tensors that will not be serialized
|
||||
|
||||
@@ -272,6 +272,7 @@ class TensorNameMap:
|
||||
"model.layers.{bid}.pre_attention_layernorm", # kormo
|
||||
"head.layers.{bid}.norm1", # laya
|
||||
"model.layers.{bid}.attn_norm", # inkling2
|
||||
"model.layers.{bid}.pre_attention_norm", # domynedge
|
||||
),
|
||||
|
||||
# Attention norm 2
|
||||
@@ -440,6 +441,7 @@ class TensorNameMap:
|
||||
"model.layers.{bid}.post_attn_norm", # kolibri1
|
||||
"model.layers.layers.{bid}.post_mixer_norm.weight", # plamo2
|
||||
"model.layers.{bid}.post_operator_norm", # lfm3
|
||||
"model.layers.{bid}.post_attention_norm", # domynedge
|
||||
),
|
||||
|
||||
# Rotary embeddings
|
||||
@@ -579,6 +581,7 @@ class TensorNameMap:
|
||||
"layers.{bid}.pre_feedforward_layernorm", # embeddinggemma
|
||||
"model.layers.{bid}.pre_ff_layernorm.weight",
|
||||
"model.layers.{bid}.pre_mlp_layernorm", # afmoe
|
||||
"model.layers.{bid}.pre_feedforward_norm", # domynedge
|
||||
),
|
||||
|
||||
MODEL_TENSOR.FFN_PRE_NORM_2: (
|
||||
@@ -603,6 +606,7 @@ class TensorNameMap:
|
||||
"model.layers.{bid}.feed_forward.up_proj",
|
||||
"model.layers.{bid}.post_moe_norm", # grok-2
|
||||
"model.layers.{bid}.post_ffn_norm", # lfm3
|
||||
"model.layers.{bid}.post_feedforward_norm", # domynedge
|
||||
),
|
||||
|
||||
MODEL_TENSOR.FFN_POST_NORM_1: (
|
||||
@@ -692,6 +696,7 @@ class TensorNameMap:
|
||||
"encoder.layers.{bid}.mlp.dense_h_to_4h", # chatglm
|
||||
"transformer.h.{bid}.mlp.c_fc_1", # exaone
|
||||
"model.layers.{bid}.feed_forward.up_proj", # llama4 jamba granite-hybrid
|
||||
"model.layers.{bid}.feedforward.up_proj", # domynedge
|
||||
"transformer_encoder.{bid}.ffn.w12", # neobert
|
||||
"model.layers.{bid}.block_sparse_moe.up", # smallthinker
|
||||
"model.transformer.blocks.{bid}.up_proj", # llada
|
||||
@@ -755,6 +760,7 @@ class TensorNameMap:
|
||||
"layers.{bid}.mlp.gate_proj", # qwen3-embedding
|
||||
"model.layers.{bid}.mlp.language_mlp.gate_proj", # cogvlm
|
||||
"model.blocks.{bid}.mlp.mlp_gate", # talkie
|
||||
"model.layers.{bid}.feedforward.gate_proj", # domynedge
|
||||
),
|
||||
|
||||
MODEL_TENSOR.FFN_GATE_EXP: (
|
||||
@@ -923,6 +929,7 @@ class TensorNameMap:
|
||||
"encoder.layers.{bid}.mlp.dense_4h_to_h", # chatglm
|
||||
"model.layers.h.{bid}.mlp.c_proj", # exaone
|
||||
"model.layers.{bid}.feed_forward.down_proj", # llama4 jamba granite-hybrid
|
||||
"model.layers.{bid}.feedforward.down_proj", # domynedge
|
||||
"transformer_encoder.{bid}.ffn.w3", # neobert
|
||||
"model.layers.{bid}.block_sparse_moe.down", # smallthinker
|
||||
"model.transformer.blocks.{bid}.ff_out", # llada
|
||||
@@ -997,6 +1004,7 @@ class TensorNameMap:
|
||||
"layers.{bid}.self_attn.k_norm", # qwen3-embedding
|
||||
"model.layers.{bid}.self_attn.k_rope_only_layernorm", # dots3note
|
||||
"model.layers.{bid}.attention.key_layernorm", # apertus
|
||||
"model.layers.{bid}.attention.k_norm", # domynedge
|
||||
),
|
||||
|
||||
MODEL_TENSOR.ROPE_FREQS: (
|
||||
|
||||
@@ -264,7 +264,7 @@ def benchmark(
|
||||
|
||||
bin_max = np.ceil(token_t_last) + 1
|
||||
plt.figure()
|
||||
plt.hist(token_t, np.linspace(0, bin_max, bin_max, endpoint=False).tolist())
|
||||
plt.hist(token_t, np.linspace(0, bin_max, int(bin_max), endpoint=False).tolist())
|
||||
plt.xlim(0, bin_max + 1)
|
||||
plt.title(name or "")
|
||||
plt.xlabel("Time [s]")
|
||||
|
||||
@@ -184,6 +184,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
|
||||
{ LLM_ARCH_KOLIBRI1, "kolibri1" },
|
||||
{ LLM_ARCH_RICURSIVE, "ricursive" },
|
||||
{ LLM_ARCH_INKLING2, "inkling2" },
|
||||
{ LLM_ARCH_DOMYN_EDGE, "domynedge" },
|
||||
{ LLM_ARCH_UNKNOWN, "(unknown)" },
|
||||
};
|
||||
|
||||
|
||||
@@ -188,6 +188,7 @@ enum llm_arch {
|
||||
LLM_ARCH_LIMITE,
|
||||
LLM_ARCH_RICURSIVE,
|
||||
LLM_ARCH_INKLING2,
|
||||
LLM_ARCH_DOMYN_EDGE,
|
||||
LLM_ARCH_UNKNOWN,
|
||||
};
|
||||
|
||||
|
||||
+9
-36
@@ -2911,42 +2911,15 @@ void llama_context::output_reorder() {
|
||||
//
|
||||
|
||||
uint32_t llama_context::graph_max_nodes() const {
|
||||
uint32_t res;
|
||||
if (model.arch == LLM_ARCH_KIMI_K3 || model.arch == LLM_ARCH_KIMI_K31 || model.arch == LLM_ARCH_GLM5_NEXT ||
|
||||
model.arch == LLM_ARCH_HRM_TEXT) {
|
||||
res = std::max<uint32_t>(1024u, 64u * model.n_tensors());
|
||||
} else if (model.arch == LLM_ARCH_QWEN3NEXT ||
|
||||
model.arch == LLM_ARCH_KIMI_LINEAR ||
|
||||
model.arch == LLM_ARCH_METIS16 ||
|
||||
model.arch == LLM_ARCH_BAILINGMOE3 ||
|
||||
model.arch == LLM_ARCH_QWEN35 ||
|
||||
model.arch == LLM_ARCH_QWEN35MOE ||
|
||||
model.arch == LLM_ARCH_ZONOS3 ||
|
||||
model.arch == LLM_ARCH_CLEF ||
|
||||
model.arch == LLM_ARCH_CLOVER_MOE ||
|
||||
model.arch == LLM_ARCH_QWEN4EXP ||
|
||||
model.arch == LLM_ARCH_DEEPSEEK4 ||
|
||||
model.arch == LLM_ARCH_DEEPSEEK41 ||
|
||||
model.arch == LLM_ARCH_XING4_0 ||
|
||||
(model.arch == LLM_ARCH_DFLASH && model.hparams.dsv4_hc_mult > 0) ||
|
||||
model.arch == LLM_ARCH_NANBEIGE ||
|
||||
model.arch == LLM_ARCH_MINIMAX_01 ||
|
||||
model.arch == LLM_ARCH_MINIMAX_M3 ||
|
||||
model.arch == LLM_ARCH_HY_V4 ||
|
||||
model.arch == LLM_ARCH_INKLING2) {
|
||||
res = std::max<uint32_t>(1024u, 32u * model.n_tensors());
|
||||
} else if (model.arch == LLM_ARCH_DFLASH && model.hparams.dflash_selector_rank > 0) {
|
||||
// DFlash2's convolutions and selector are shape work rather than matmuls,
|
||||
// so they cost ~8.6 nodes per tensor against ~5.9 for a plain DFlash draft.
|
||||
// The selector lattice scales with the draft block size; 12u was calibrated
|
||||
// on block-8 drafters, so scale the budget for larger blocks (e.g. Ripple's 16).
|
||||
const uint32_t block_scale = std::max<uint32_t>(1u, model.hparams.dflash_block_size/8u);
|
||||
res = std::max<uint32_t>(1024u, 12u*block_scale*model.n_tensors());
|
||||
} else {
|
||||
res = std::max<uint32_t>(1024u, 8u*model.n_tensors());
|
||||
for (const auto & lora : model.loras) {
|
||||
res += lora->get_n_nodes();
|
||||
}
|
||||
uint32_t res = std::max<uint32_t>(1024u, model.graph_nodes_per_tensor()*model.n_tensors());
|
||||
for (const auto & lora : model.loras) {
|
||||
res += lora->get_n_nodes();
|
||||
}
|
||||
|
||||
// the MoE cache adds a lookup to each MoE layer, and a second expert path with a CPU share (up to ~16 tensors per layer),
|
||||
// which the per-tensor estimates above do not cover for models with few tensors per layer
|
||||
if (cparams.moe_cache_size > 0) {
|
||||
res += 32u*model.hparams.n_layer_all;
|
||||
}
|
||||
|
||||
// every sampler builds n_outputs_max_per_seq chains, see llm_graph_context::build_sampling
|
||||
|
||||
@@ -314,11 +314,8 @@ llama_kv_cache::llama_kv_cache(
|
||||
ggml_is_quantized(type_k) &&
|
||||
hparams.n_embd_head_k() % 64 == 0;
|
||||
|
||||
// always create Hadamard rotation tensors for DeepSeek lightning indexers
|
||||
if ((model.arch == LLM_ARCH_DEEPSEEK32 || model.arch == LLM_ARCH_DEEPSEEK4 ||
|
||||
model.arch == LLM_ARCH_GLM_DSA || model.arch == LLM_ARCH_DOTS3NOTE ||
|
||||
model.arch == LLM_ARCH_MISTRAL_LARGE4) &&
|
||||
hparams.n_embd_head_k_full == hparams.indexer_head_size) {
|
||||
// always create Hadamard rotation tensors for lightning indexer keys
|
||||
if (model.lid_k_hdmd() && hparams.n_embd_head_k_full == hparams.indexer_head_size) {
|
||||
attn_rot_k = true;
|
||||
}
|
||||
|
||||
|
||||
@@ -394,6 +394,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params
|
||||
return new llama_model_k2_horizon(params);
|
||||
case LLM_ARCH_KOLIBRI1:
|
||||
return new llama_model_kolibri1(params);
|
||||
case LLM_ARCH_DOMYN_EDGE:
|
||||
return new llama_model_domyn_edge(params);
|
||||
default:
|
||||
throw std::runtime_error(std::string("unsupported model architecture: '") + llm_arch_name(arch) + "'");
|
||||
}
|
||||
@@ -1909,6 +1911,12 @@ bool llama_model_base::load_tensors(llama_model_loader & ml) {
|
||||
}
|
||||
if (!layer.ffn_up_exps_s && layer.ffn_up_exps) {
|
||||
layer.ffn_up_exps_s = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
|
||||
if (layer.ffn_up_exps_s && layer.ffn_gate_up_exps) {
|
||||
throw std::runtime_error(format("ffn_up_exps.scale and ffn_gate_up_exps.weight both exist for layer %d", i));
|
||||
}
|
||||
}
|
||||
if (!layer.ffn_up_exps_s && layer.ffn_gate_up_exps) {
|
||||
layer.ffn_up_exps_s = create_tensor(tn(LLM_TENSOR_FFN_GATE_UP_EXPS, "scale", i), {n_expert}, TENSOR_NOT_REQUIRED);
|
||||
}
|
||||
|
||||
// recurrent / linear-attention weight scales (per-tensor, shape {1})
|
||||
@@ -3873,6 +3881,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
|
||||
case LLM_ARCH_HRM_TEXT:
|
||||
case LLM_ARCH_BEAM:
|
||||
case LLM_ARCH_KOLIBRI1:
|
||||
case LLM_ARCH_DOMYN_EDGE:
|
||||
return LLAMA_ROPE_TYPE_NEOX;
|
||||
|
||||
case LLM_ARCH_DFLASH:
|
||||
|
||||
@@ -1052,6 +1052,12 @@ struct llama_model {
|
||||
|
||||
llama_memory_i * create_memory(const llama_memory_params & params, const llama_cparams & cparams) const;
|
||||
|
||||
// graph size budget: max graph nodes per model tensor
|
||||
virtual uint32_t graph_nodes_per_tensor() const { return 8; }
|
||||
|
||||
// apply Hadamard transform to the lightning indexer keys
|
||||
virtual bool lid_k_hdmd() const { return false; }
|
||||
|
||||
ggml_cgraph * build_graph(const llm_graph_params & params) const;
|
||||
|
||||
virtual void load_stats (llama_model_loader & ml) = 0;
|
||||
|
||||
+2
-1
@@ -2566,7 +2566,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
|
||||
tokenizer_pre == "qwen2" ||
|
||||
tokenizer_pre == "deepseek-r1-qwen" ||
|
||||
tokenizer_pre == "kormo" ||
|
||||
tokenizer_pre == "f2llmv2") {
|
||||
tokenizer_pre == "f2llmv2" ||
|
||||
tokenizer_pre == "domyn-edge") {
|
||||
pre_type = LLAMA_VOCAB_PRE_TYPE_QWEN2;
|
||||
clean_spaces = false;
|
||||
} else if (
|
||||
|
||||
@@ -125,6 +125,20 @@ void llama_model_dflash::load_arch_tensors(llama_model_loader &) {
|
||||
}
|
||||
}
|
||||
|
||||
uint32_t llama_model_dflash::graph_nodes_per_tensor() const {
|
||||
if (hparams.dsv4_hc_mult > 0) {
|
||||
return 32;
|
||||
}
|
||||
if (hparams.dflash_selector_rank > 0) {
|
||||
// DFlash2's convolutions and selector are shape work rather than matmuls,
|
||||
// so they cost ~8.6 nodes per tensor against ~5.9 for a plain DFlash draft.
|
||||
// The selector lattice scales with the draft block size; 12u was calibrated
|
||||
// on block-8 drafters, so scale the budget for larger blocks (e.g. Ripple's 16).
|
||||
return 12u*std::max<uint32_t>(1u, hparams.dflash_block_size/8u);
|
||||
}
|
||||
return llama_model_base::graph_nodes_per_tensor();
|
||||
}
|
||||
|
||||
void llama_model_dflash::load_tensors_layers_base() {
|
||||
LLAMA_LOAD_LOCALS;
|
||||
|
||||
|
||||
@@ -0,0 +1,164 @@
|
||||
#include "models.h"
|
||||
|
||||
void llama_model_domyn_edge::load_arch_hparams(llama_model_loader & ml) {
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
|
||||
ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa);
|
||||
// required: the base loader defaults it to n_rot_full if the key is not found
|
||||
ml.get_key(LLM_KV_ROPE_DIMENSION_COUNT_SWA, hparams.n_rot_swa);
|
||||
// RoPE cannot rotate more dims than the SWA head has: CPU aborts, GPU backends read past the row
|
||||
if (hparams.n_rot_swa > hparams.n_embd_head_k_swa) {
|
||||
throw std::runtime_error(format("invalid n_rot_swa: %u, max %u", hparams.n_rot_swa, hparams.n_embd_head_k_swa));
|
||||
}
|
||||
|
||||
hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
|
||||
|
||||
ml.get_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl);
|
||||
ml.get_arr(LLM_KV_ATTENTION_ROPE_PATTERN, hparams.rope_pattern);
|
||||
|
||||
// only for print_info / saver; get_rope_params uses cparams
|
||||
hparams.rope_freq_base_train_swa = hparams.rope_freq_base_train;
|
||||
hparams.rope_freq_scale_train_swa = hparams.rope_freq_scale_train;
|
||||
|
||||
switch (hparams.n_layer()) {
|
||||
case 36: type = LLM_TYPE_4B; break;
|
||||
default: type = LLM_TYPE_UNKNOWN;
|
||||
}
|
||||
}
|
||||
|
||||
void llama_model_domyn_edge::load_arch_tensors(llama_model_loader &) {
|
||||
LLAMA_LOAD_LOCALS;
|
||||
|
||||
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
|
||||
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
|
||||
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
|
||||
|
||||
// if output is NULL, init from the input tok embed
|
||||
if (output == NULL) {
|
||||
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
|
||||
}
|
||||
|
||||
for (int i = 0; i < n_layer; ++i) {
|
||||
auto & layer = layers[i];
|
||||
const int64_t n_embd_head_i = hparams.n_embd_head_k(i);
|
||||
const int64_t n_embd_k_i = hparams.n_embd_k_gqa(i);
|
||||
const int64_t n_embd_v_i = hparams.n_embd_v_gqa(i);
|
||||
|
||||
layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
|
||||
layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", i), {n_embd}, 0);
|
||||
|
||||
const int64_t n_embd_q_i = n_embd_head_i * n_head;
|
||||
create_tensor_qkv(layer, i, n_embd, n_embd_q_i, n_embd_k_i, n_embd_v_i, 0);
|
||||
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_i * n_head, n_embd}, 0);
|
||||
|
||||
// K-norm has a learnable weight; Q-norm does not
|
||||
layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd_head_i}, 0);
|
||||
|
||||
layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
|
||||
layer.ffn_post_norm = create_tensor(tn(LLM_TENSOR_FFN_POST_NORM, "weight", i), {n_embd}, 0);
|
||||
|
||||
layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, 0);
|
||||
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
|
||||
layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, 0);
|
||||
}
|
||||
}
|
||||
|
||||
llama_rope_params llama_model_domyn_edge::get_rope_params(const llama_cparams & cparams, int il) const {
|
||||
auto res = llama_model::get_rope_params(cparams, il);
|
||||
|
||||
// the SWA layers use the global base and scale
|
||||
res.freq_base = cparams.rope_freq_base;
|
||||
res.freq_scale = cparams.rope_freq_scale;
|
||||
|
||||
return res;
|
||||
}
|
||||
|
||||
llama_model_domyn_edge::graph::graph(const llm_graph_params & params)
|
||||
: llm_graph_context(params) {
|
||||
ggml_tensor * cur;
|
||||
ggml_tensor * inpL = build_inp_embd(model.tok_embd);
|
||||
ggml_tensor * inp_pos = build_inp_pos();
|
||||
|
||||
auto * inp_attn = build_attn_inp_kv_iswa();
|
||||
|
||||
ggml_tensor * inp_out_ids = build_inp_out_ids();
|
||||
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
const auto & layer = model.layers[il];
|
||||
const int64_t n_embd_head = hparams.n_embd_head_k(il);
|
||||
const int64_t n_head_il = hparams.n_head(il);
|
||||
const int64_t n_head_kv_il = hparams.n_head_kv(il);
|
||||
const float kq_scale = 1.0f / sqrtf((float)n_embd_head);
|
||||
|
||||
ggml_tensor * residual = inpL;
|
||||
|
||||
// pre-attention norm
|
||||
cur = build_norm(inpL, layer.attn_norm, NULL, LLM_NORM_RMS, il);
|
||||
cb(cur, "attn_norm", il);
|
||||
|
||||
auto [Qcur, Kcur, Vcur] = build_qkv(layer, cur, n_embd_head, n_head_il, n_head_kv_il, il);
|
||||
|
||||
// Q-norm: RMSNorm without learnable weight (elementwise_affine=False)
|
||||
Qcur = build_norm(Qcur, NULL, NULL, LLM_NORM_RMS, il);
|
||||
cb(Qcur, "Qcur_normed", il);
|
||||
|
||||
// K-norm: RMSNorm with learnable weight
|
||||
Kcur = build_norm(Kcur, layer.attn_k_norm, NULL, LLM_NORM_RMS, il);
|
||||
cb(Kcur, "Kcur_normed", il);
|
||||
|
||||
// build_rope already applies RoPE only if the current layer is a RoPE layer
|
||||
Qcur = build_rope(Qcur, inp_pos, il);
|
||||
cb(Qcur, "Qcur_rope", il);
|
||||
|
||||
Kcur = build_rope(Kcur, inp_pos, il);
|
||||
cb(Kcur, "Kcur_rope", il);
|
||||
|
||||
cur = build_attn(inp_attn,
|
||||
layer.wo, NULL, layer.wo_s,
|
||||
Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
|
||||
cb(cur, "attn_out", il);
|
||||
|
||||
// post-attention norm applied to attn output before residual add
|
||||
cur = build_norm(cur, layer.attn_post_norm, NULL, LLM_NORM_RMS, il);
|
||||
cb(cur, "attn_post_norm", il);
|
||||
|
||||
if (il == n_layer - 1 && inp_out_ids) {
|
||||
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
|
||||
residual = ggml_get_rows(ctx0, residual, inp_out_ids);
|
||||
}
|
||||
|
||||
ggml_tensor * ffn_inp = ggml_add(ctx0, cur, residual);
|
||||
cb(ffn_inp, "ffn_inp", il);
|
||||
|
||||
// pre-FFN norm
|
||||
cur = build_norm(ffn_inp, layer.ffn_norm, NULL, LLM_NORM_RMS, il);
|
||||
cb(cur, "ffn_norm", il);
|
||||
|
||||
// SwiGLU FFN
|
||||
cur = build_ffn(cur,
|
||||
layer.ffn_up, NULL, NULL,
|
||||
layer.ffn_gate, NULL, NULL,
|
||||
layer.ffn_down, NULL, NULL, NULL,
|
||||
LLM_FFN_SILU, LLM_FFN_PAR, il);
|
||||
cb(cur, "ffn_out", il);
|
||||
|
||||
// post-FFN norm applied to ffn output before residual add
|
||||
cur = build_norm(cur, layer.ffn_post_norm, NULL, LLM_NORM_RMS, il);
|
||||
cb(cur, "ffn_post_norm", il);
|
||||
|
||||
cur = ggml_add(ctx0, cur, ffn_inp);
|
||||
inpL = build_cvec(cur, il);
|
||||
cb(inpL, "l_out", il);
|
||||
}
|
||||
|
||||
cur = build_norm(inpL, model.output_norm, NULL, LLM_NORM_RMS, -1);
|
||||
cb(cur, "result_norm", -1);
|
||||
res->t_embd = cur;
|
||||
|
||||
cur = build_lora_mm(model.output, cur, model.output_s);
|
||||
cb(cur, "result_output", -1);
|
||||
res->t_logits = cur;
|
||||
}
|
||||
|
||||
std::unique_ptr<llm_graph_context> llama_model_domyn_edge::build_arch_graph(const llm_graph_params & params) const {
|
||||
return std::make_unique<graph>(params);
|
||||
}
|
||||
+151
-17
@@ -157,6 +157,29 @@ static ggml_tensor * gemma4_view_2d_slice(ggml_context * ctx0, ggml_tensor * x,
|
||||
return ggml_view_2d(ctx0, x, x->ne[0], x->ne[1], x->nb[1], idx * x->nb[2]);
|
||||
}
|
||||
|
||||
class llm_graph_input_gemma4_prune : public llm_graph_input_i {
|
||||
int64_t n_slices;
|
||||
int64_t n_slice_tokens;
|
||||
int64_t n_slice_outputs;
|
||||
public:
|
||||
ggml_tensor * full_mask = nullptr;
|
||||
ggml_tensor * full_mask_swa = nullptr;
|
||||
ggml_tensor * out_mask = nullptr;
|
||||
ggml_tensor * out_mask_swa = nullptr;
|
||||
ggml_tensor * inp_prune_ids = nullptr;
|
||||
ggml_tensor * inp_prune_keep = nullptr;
|
||||
llm_graph_input_gemma4_prune(int64_t n_slices, int64_t n_slice_tokens, int64_t n_slice_outputs)
|
||||
: n_slices(n_slices), n_slice_tokens(n_slice_tokens), n_slice_outputs(n_slice_outputs) {}
|
||||
|
||||
void set_input(const llama_ubatch * ubatch) override;
|
||||
|
||||
bool can_reuse(const llm_graph_params & params) override;
|
||||
|
||||
static int64_t max_outputs_per_slice(
|
||||
const llama_ubatch & ubatch, int64_t n_slices, int64_t n_slice_tokens
|
||||
);
|
||||
};
|
||||
|
||||
llama_model_gemma4::graph::graph(const llm_graph_params & params) :
|
||||
llm_graph_context(params),
|
||||
n_embd_per_layer(model.hparams.n_embd_per_layer) {
|
||||
@@ -181,11 +204,8 @@ llama_model_gemma4::graph::graph(const llm_graph_params & params) :
|
||||
// TODO: is causal == true correct? might need some changes
|
||||
auto * inp_attn = build_attn_inp_kv_iswa();
|
||||
|
||||
auto inp_attn_full = *inp_attn;
|
||||
auto inp_attn_prune = *inp_attn;
|
||||
|
||||
ggml_tensor * inp_out_ids = build_inp_out_ids();
|
||||
|
||||
if (model.per_layer_tok_embd) {
|
||||
// fold per_layer_input_scale (1/sqrt(2)) from project_per_layer_inputs() into tok_embd_scale
|
||||
const float tok_embd_scale = sqrtf((float) n_embd_per_layer) / sqrtf(2.0f);
|
||||
@@ -197,34 +217,57 @@ llama_model_gemma4::graph::graph(const llm_graph_params & params) :
|
||||
inp_per_layer = project_per_layer_inputs(inpL, inp_per_layer);
|
||||
}
|
||||
|
||||
const bool needs_unmasked_nextn =
|
||||
cparams.embeddings_nextn && !cparams.embeddings_nextn_masked;
|
||||
|
||||
// KV-shared layers do not write to the KV cache, so prune non-output token rows before the first KV-shared layer
|
||||
bool prune_shared = crop_before_nextn(inp_out_ids) &&
|
||||
bool prune_shared = !needs_unmasked_nextn &&
|
||||
hparams.n_layer_kv_from_start > 0 && hparams.n_layer_kv_from_start < n_layer &&
|
||||
!cparams.embeddings && cparams.n_seq_max == 1;
|
||||
!cparams.embeddings;
|
||||
for (int il = (int) hparams.n_layer_kv_from_start; prune_shared && il <= n_layer; ++il) {
|
||||
prune_shared = !cparams.embeddings_layer_inp[il];
|
||||
}
|
||||
|
||||
int64_t n_rows = n_tokens;
|
||||
|
||||
ggml_tensor * inp_prune_ids = nullptr;
|
||||
ggml_tensor * inp_prune_keep = nullptr;
|
||||
ggml_tensor * inp_out_ids = prune_shared ? nullptr : build_inp_out_ids();
|
||||
|
||||
for (int il = 0; il < n_layer; ++il) {
|
||||
if (prune_shared && il == (int) hparams.n_layer_kv_from_start) {
|
||||
inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
|
||||
inp_pos = ggml_reshape_1d(ctx0, ggml_get_rows(ctx0, ggml_reshape_2d(ctx0, inp_pos, 1, n_tokens), inp_out_ids), n_outputs);
|
||||
ggml_tensor * full = inp_attn->self_attn_mask.raw;
|
||||
ggml_tensor * full_swa = inp_attn->self_attn_mask_swa.raw;
|
||||
|
||||
// TODO: instead of doing get_rows here, extend llm_attn_mask to have a `out` mask that
|
||||
// is construted during set_input to contain just the pruned output cells
|
||||
// this can be used to enable pruning with more than 1 sequence, both with unified and split KV cache
|
||||
// ref: https://github.com/ggml-org/llama.cpp/pull/31356#discussion_r4455286628
|
||||
inp_attn_prune.self_attn_mask.raw = ggml_get_rows(ctx0, inp_attn_full.self_attn_mask.raw, inp_out_ids);
|
||||
inp_attn_prune.self_attn_mask_swa.raw = ggml_get_rows(ctx0, inp_attn_full.self_attn_mask_swa.raw, inp_out_ids);
|
||||
const int64_t n_slices = full->ne[3], n_slice_tokens = full->ne[1];
|
||||
const int64_t n_slice_outputs = llm_graph_input_gemma4_prune::max_outputs_per_slice(ubatch, n_slices, n_slice_tokens);
|
||||
|
||||
inp_attn_prune.self_attn_mask.raw = ggml_cast(ctx0, inp_attn_prune.self_attn_mask.raw, GGML_TYPE_F16);
|
||||
inp_attn_prune.self_attn_mask_swa.raw = ggml_cast(ctx0, inp_attn_prune.self_attn_mask_swa.raw, GGML_TYPE_F16);
|
||||
n_rows = n_slices * n_slice_outputs;
|
||||
|
||||
n_rows = n_outputs;
|
||||
auto prune_input = std::make_unique<llm_graph_input_gemma4_prune>(n_slices, n_slice_tokens, n_slice_outputs);
|
||||
prune_input->full_mask = full;
|
||||
prune_input->full_mask_swa = full_swa;
|
||||
prune_input->out_mask = ggml_new_tensor_4d(ctx0, full->type, full->ne[0], n_slice_outputs, 1, n_slices);
|
||||
prune_input->out_mask_swa = ggml_new_tensor_4d(ctx0, full_swa->type, full_swa->ne[0], n_slice_outputs, 1, n_slices);
|
||||
prune_input->inp_prune_ids = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_rows);
|
||||
prune_input->inp_prune_keep = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_outputs);
|
||||
|
||||
ggml_set_input(prune_input->out_mask);
|
||||
ggml_set_input(prune_input->out_mask_swa);
|
||||
ggml_set_input(prune_input->inp_prune_ids);
|
||||
ggml_set_input(prune_input->inp_prune_keep);
|
||||
|
||||
inp_prune_ids = prune_input->inp_prune_ids;
|
||||
inp_prune_keep = prune_input->inp_prune_keep;
|
||||
|
||||
inpL = ggml_get_rows(ctx0, inpL, inp_prune_ids);
|
||||
inp_pos = ggml_reshape_1d(ctx0, ggml_get_rows(ctx0, ggml_reshape_2d(ctx0, inp_pos, 1, n_tokens), inp_prune_ids), n_rows);
|
||||
|
||||
inp_attn_prune.self_attn_mask.raw = prune_input->out_mask;
|
||||
inp_attn_prune.self_attn_mask_swa.raw = prune_input->out_mask_swa;
|
||||
inp_attn = &inp_attn_prune;
|
||||
|
||||
res->add_input(std::move(prune_input));
|
||||
}
|
||||
|
||||
const int64_t n_embd_head = hparams.n_embd_head_k(il);
|
||||
@@ -406,7 +449,9 @@ llama_model_gemma4::graph::graph(const llm_graph_params & params) :
|
||||
|
||||
ggml_tensor * inp_this_layer = gemma4_view_2d_slice(ctx0, inp_per_layer, il); // [n_embd_per_layer, n_tokens]
|
||||
|
||||
if ((prune_shared && !hparams.has_kv(il)) || (il == n_layer - 1 && crop_before_nextn(inp_out_ids))) {
|
||||
if (prune_shared && !hparams.has_kv(il)) {
|
||||
inp_this_layer = ggml_get_rows(ctx0, inp_this_layer, inp_prune_ids);
|
||||
} else if (il == n_layer - 1 && crop_before_nextn(inp_out_ids)) {
|
||||
inp_this_layer = ggml_get_rows(ctx0, inp_this_layer, inp_out_ids);
|
||||
}
|
||||
|
||||
@@ -432,6 +477,9 @@ llama_model_gemma4::graph::graph(const llm_graph_params & params) :
|
||||
inpL = cur;
|
||||
}
|
||||
cur = inpL;
|
||||
if (prune_shared) {
|
||||
cur = ggml_get_rows(ctx0, cur, inp_prune_keep);
|
||||
}
|
||||
|
||||
cur = build_norm(cur,
|
||||
model.output_norm, nullptr,
|
||||
@@ -558,3 +606,89 @@ ggml_tensor * llama_model_gemma4::graph::project_per_layer_inputs(ggml_tensor *
|
||||
// permute to shape: [n_embd_per_layer, n_tokens, n_layer]
|
||||
return ggml_permute(ctx0, inp_per_layer, 0, 2, 1, 3);
|
||||
}
|
||||
|
||||
void llm_graph_input_gemma4_prune::set_input(const llama_ubatch * ubatch) {
|
||||
std::vector<std::vector<int32_t>> selected(n_slices);
|
||||
|
||||
for (int32_t s = 0; s < n_slices; ++s) {
|
||||
for (int32_t t = 0; t < n_slice_tokens; ++t) {
|
||||
const int32_t i = s * n_slice_tokens + t;
|
||||
if (ubatch->output[i]) {
|
||||
selected[s].push_back(i);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
std::vector<int32_t> take, keep;
|
||||
for (int32_t s = 0; s < n_slices; ++s) {
|
||||
const auto & ids = selected[s];
|
||||
|
||||
for (int32_t j = 0; j < int32_t(ids.size()); ++j) {
|
||||
keep.push_back(s * n_slice_outputs + j);
|
||||
}
|
||||
|
||||
take.insert(take.end(), ids.begin(), ids.end());
|
||||
const int32_t dummy = ids.empty() ? s * n_slice_tokens : ids.back();
|
||||
take.insert(take.end(), n_slice_outputs - ids.size(), dummy);
|
||||
}
|
||||
|
||||
GGML_ASSERT(take.size() == size_t(inp_prune_ids->ne[0]));
|
||||
if (!take.empty()) {
|
||||
ggml_backend_tensor_set(inp_prune_ids, take.data(), 0,
|
||||
take.size() * sizeof(int32_t));
|
||||
}
|
||||
|
||||
auto copy_mask = [&](const ggml_tensor * full, ggml_tensor * out) {
|
||||
if (take.empty() || !out->buffer) {
|
||||
return;
|
||||
}
|
||||
|
||||
GGML_ASSERT(full->buffer && ggml_backend_buffer_is_host(full->buffer));
|
||||
const size_t row_bytes = full->ne[0] * ggml_element_size(full);
|
||||
const auto * src = static_cast<const uint8_t *>(full->data);
|
||||
std::vector<uint8_t> packed(take.size() * row_bytes);
|
||||
|
||||
for (size_t j = 0; j < take.size(); ++j) {
|
||||
memcpy(packed.data() + j * row_bytes,
|
||||
src + take[j] * row_bytes,
|
||||
row_bytes);
|
||||
}
|
||||
|
||||
ggml_backend_tensor_set(out, packed.data(), 0, packed.size());
|
||||
};
|
||||
|
||||
copy_mask(full_mask, out_mask);
|
||||
copy_mask(full_mask_swa, out_mask_swa);
|
||||
|
||||
if (!keep.empty()) {
|
||||
ggml_backend_tensor_set(
|
||||
inp_prune_keep, keep.data(), 0,
|
||||
keep.size() * sizeof(int32_t));
|
||||
}
|
||||
}
|
||||
|
||||
bool llm_graph_input_gemma4_prune::can_reuse(const llm_graph_params & params) {
|
||||
const auto & ubatch = params.ubatch;
|
||||
|
||||
if (ubatch.n_tokens != n_slices * n_slice_tokens || !ubatch.output) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return max_outputs_per_slice(ubatch, n_slices, n_slice_tokens) == n_slice_outputs;
|
||||
}
|
||||
|
||||
int64_t llm_graph_input_gemma4_prune::max_outputs_per_slice(const llama_ubatch & ubatch, int64_t n_slices, int64_t n_slice_tokens) {
|
||||
int64_t res = 0;
|
||||
|
||||
for (int32_t s = 0; s < n_slices; ++s) {
|
||||
int64_t m = 0;
|
||||
for (int32_t t = 0; t < n_slice_tokens; ++t) {
|
||||
const int32_t i = s * n_slice_tokens + t;
|
||||
if (ubatch.output[i]) {
|
||||
m++;
|
||||
}
|
||||
}
|
||||
res = std::max(res, m);
|
||||
}
|
||||
return res;
|
||||
}
|
||||
|
||||
@@ -372,7 +372,10 @@ llama_model_inkling2::graph::graph(const llm_graph_params & params) : llm_graph_
|
||||
LLAMA_EXPERT_GATING_FUNC_TYPE_SIGMOID,
|
||||
il,
|
||||
nullptr,
|
||||
layer.ffn_gate_up_exps);
|
||||
layer.ffn_gate_up_exps,
|
||||
layer.ffn_up_exps_s,
|
||||
layer.ffn_gate_exps_s,
|
||||
layer.ffn_down_exps_s);
|
||||
|
||||
cur = convolve(cur, layer.ffn_post_conv, nullptr, state, history, recr, 2*n_embd_k_gqa + n_embd);
|
||||
cb(cur, "ffn_out", il);
|
||||
|
||||
@@ -442,6 +442,7 @@ struct llama_model_nanbeige : public llama_model_base {
|
||||
llama_model_nanbeige(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
int n_loops = 1;
|
||||
int n_layer_phys = 0;
|
||||
@@ -801,6 +802,7 @@ struct llama_model_zonos3 : public llama_model_base {
|
||||
llama_model_zonos3(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -1244,6 +1246,7 @@ struct llama_model_deepseek32 : public llama_model_base {
|
||||
llama_model_deepseek32(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
bool lid_k_hdmd() const override { return true; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -1260,6 +1263,7 @@ struct llama_model_dots3note : public llama_model_base {
|
||||
llama_model_dots3note(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
bool lid_k_hdmd() const override { return true; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -1282,6 +1286,8 @@ struct llama_model_deepseek4 : public llama_model_base {
|
||||
llama_model_deepseek4(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
bool lid_k_hdmd() const override { return true; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
struct no_build {};
|
||||
@@ -1439,6 +1445,7 @@ struct llama_model_xing4_0 : public llama_model_base {
|
||||
llama_model_xing4_0(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llama_model & model, const llm_graph_params & params);
|
||||
@@ -1481,6 +1488,7 @@ struct llama_model_deepseek41 : public llama_model_deepseek4 {
|
||||
llama_model_deepseek41(const struct llama_model_params & params) : llama_model_deepseek4(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
bool lid_k_hdmd() const override { return false; }
|
||||
|
||||
// Engram: the hash constants are hparams.ple_* (one module per Engram layer), hashed on the host (ggml has no int64 mul/xor/mod)
|
||||
int engram_index(int il) const;
|
||||
@@ -1539,6 +1547,7 @@ struct llama_model_glm_dsa : public llama_model_base {
|
||||
llama_model_glm_dsa(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
bool lid_k_hdmd() const override { return true; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -1571,6 +1580,7 @@ struct llama_model_dflash : public llama_model_base {
|
||||
llama_model_dflash(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override;
|
||||
|
||||
enum variant_type {
|
||||
VARIANT_DFLASH,
|
||||
@@ -1672,6 +1682,7 @@ struct llama_model_mistral_large4 : public llama_model_base {
|
||||
llama_model_mistral_large4(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
bool lid_k_hdmd() const override { return true; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -1833,6 +1844,7 @@ struct llama_model_metis16 : public llama_model_base {
|
||||
llama_model_metis16(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
uint32_t n_pass = 1;
|
||||
uint32_t n_stream = 1;
|
||||
@@ -2134,6 +2146,7 @@ struct llama_model_hrm_text : public llama_model_base {
|
||||
llama_model_hrm_text(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 64; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -2176,6 +2189,7 @@ struct llama_model_bailingmoe3 : public llama_model_base {
|
||||
llama_model_bailingmoe3(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -2346,6 +2360,7 @@ struct llama_model_hy_v4 : public llama_model_base {
|
||||
llama_model_hy_v4(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -2475,6 +2490,7 @@ struct llama_model_inkling2 : public llama_model_base {
|
||||
llama_model_inkling2(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -2599,6 +2615,7 @@ struct llama_model_minimax_01 : public llama_model_base {
|
||||
llama_model_minimax_01(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -2629,6 +2646,7 @@ struct llama_model_minimax_m3 : public llama_model_base {
|
||||
llama_model_minimax_m3(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
msa_params msa_p;
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -2673,6 +2691,7 @@ struct llama_model_qwen3next : public llama_model_base {
|
||||
llama_model_qwen3next(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -2715,6 +2734,7 @@ struct llama_model_qwen35 : public llama_model_base {
|
||||
llama_model_qwen35(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -2851,6 +2871,7 @@ struct llama_model_qwen4exp : public llama_model_base {
|
||||
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -2965,6 +2986,7 @@ struct llama_model_qwen35moe : public llama_model_base {
|
||||
llama_model_qwen35moe(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -3007,6 +3029,7 @@ struct llama_model_clover_moe : public llama_model_base {
|
||||
llama_model_clover_moe(const llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -3055,6 +3078,7 @@ struct llama_model_kimi_k3 : public llama_model_base {
|
||||
llama_model_kimi_k3(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 64; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -3095,6 +3119,7 @@ struct llama_model_kimi_k31 : public llama_model_base {
|
||||
llama_model_kimi_k31(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 64; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -3141,6 +3166,7 @@ struct llama_model_glm5_next : public llama_model_base {
|
||||
llama_model_glm5_next(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 64; }
|
||||
|
||||
// k-pool indexer inputs on top of the generic hybrid input
|
||||
class llm_graph_input_kpool;
|
||||
@@ -3225,6 +3251,7 @@ struct llama_model_kimi_linear : public llama_model_base {
|
||||
llama_model_kimi_linear(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
uint32_t graph_nodes_per_tensor() const override { return 32; }
|
||||
|
||||
struct graph : public llm_build_delta_net_base {
|
||||
graph(const llm_graph_params & params);
|
||||
@@ -3308,3 +3335,16 @@ struct llama_model_kolibri1 : public llama_model_base {
|
||||
|
||||
std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
|
||||
};
|
||||
|
||||
struct llama_model_domyn_edge : public llama_model_base {
|
||||
llama_model_domyn_edge(const struct llama_model_params & params) : llama_model_base(params) {}
|
||||
void load_arch_hparams(llama_model_loader & ml) override;
|
||||
void load_arch_tensors(llama_model_loader & ml) override;
|
||||
llama_rope_params get_rope_params(const llama_cparams & cparams, int il) const override;
|
||||
|
||||
struct graph : public llm_graph_context {
|
||||
graph(const llm_graph_params & params);
|
||||
};
|
||||
|
||||
std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
|
||||
};
|
||||
|
||||
@@ -65,6 +65,8 @@ deepseek4 ,0 ,any ,UNARY+SQRT+ADD+ARGSORT+GET_ROWS+SUM_ROWS+CLAM
|
||||
deepseek41 ,0 ,any ,MUL+ADD , 12
|
||||
deepseek41 ,0 ,any ,RMS_NORM+MUL , 29
|
||||
deepseek41 ,0 ,any ,UNARY+SQRT+ADD+ARGSORT+GET_ROWS+SUM_ROWS+SCALE+DIV, 6
|
||||
domynedge ,0 ,any ,RMS_NORM+MUL , 8
|
||||
domynedge ,0 ,any ,RMS_NORM+MUL+ADD , 3
|
||||
dots1 ,0 ,any ,ADD+ADD , 1
|
||||
dots1 ,0 ,any ,MUL+ADD , 2
|
||||
dots1 ,0 ,any ,RMS_NORM+MUL , 9
|
||||
|
||||
|
@@ -496,16 +496,22 @@ static gguf_context_ptr get_gguf_ctx(const llm_arch arch, const bool moe, const
|
||||
ms.add_kv(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, pattern);
|
||||
} else if (arch == LLM_ARCH_COHERE2MOE || arch == LLM_ARCH_MIMO2 || arch == LLM_ARCH_STEP35 || arch == LLM_ARCH_SPARK2_5 ||
|
||||
arch == LLM_ARCH_MUSE_GLIMMER || arch == LLM_ARCH_MUSE_SPARK || arch == LLM_ARCH_GRANITE_SWA || arch == LLM_ARCH_DOTS3NOTE ||
|
||||
arch == LLM_ARCH_KOLIBRI1 || arch == LLM_ARCH_MAPLE || arch == LLM_ARCH_FLINT || arch == LLM_ARCH_BEAM || arch == LLM_ARCH_RICURSIVE) {
|
||||
arch == LLM_ARCH_KOLIBRI1 || arch == LLM_ARCH_MAPLE || arch == LLM_ARCH_FLINT || arch == LLM_ARCH_BEAM || arch == LLM_ARCH_RICURSIVE || arch == LLM_ARCH_DOMYN_EDGE) {
|
||||
std::vector<uint32_t> pattern;
|
||||
pattern.reserve(n_layer);
|
||||
for (uint32_t il = 0; il < n_layer; il++) {
|
||||
pattern.push_back(il % 2);
|
||||
}
|
||||
ms.add_kv(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, pattern);
|
||||
if (arch == LLM_ARCH_FLINT) {
|
||||
if (arch == LLM_ARCH_FLINT || arch == LLM_ARCH_DOMYN_EDGE) {
|
||||
ms.add_kv(LLM_KV_ATTENTION_ROPE_PATTERN, pattern);
|
||||
}
|
||||
if (arch == LLM_ARCH_DOMYN_EDGE) {
|
||||
// SWA (rope) layers use a smaller head dim than the full-attention (nope) layers
|
||||
ms.add_kv(LLM_KV_ATTENTION_KEY_LENGTH_SWA, n_embd_head/2);
|
||||
ms.add_kv(LLM_KV_ATTENTION_VALUE_LENGTH_SWA, n_embd_head/2);
|
||||
ms.add_kv(LLM_KV_ROPE_DIMENSION_COUNT_SWA, n_embd_head/2);
|
||||
}
|
||||
} else if (arch == LLM_ARCH_LFM3) {
|
||||
ms.add_kv(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, std::vector<uint32_t>({0, 0, 1}));
|
||||
ms.add_kv(LLM_KV_ROPE_FREQ_BASE_SWA, 10000.0f);
|
||||
|
||||
@@ -80,6 +80,7 @@ class LibLlamaModel:
|
||||
raise RuntimeError("error: failed to load model '%s'" % path_model)
|
||||
if isinstance(cparams, dict):
|
||||
cparams = libllama.context_default_params(**cparams)
|
||||
self.vocab = self.lib.llama_model_get_vocab(self.model)
|
||||
self.ctx = self.lib.llama_init_from_model(self.model, cparams)
|
||||
if not self.ctx:
|
||||
raise RuntimeError("error: failed to create context for model '%s'" % path_model)
|
||||
@@ -98,10 +99,10 @@ class LibLlamaModel:
|
||||
|
||||
def tokenize(self, text: str, add_special: bool = False, parse_special: bool = False) -> list[int]:
|
||||
encoded_text: bytes = text.encode("utf-8")
|
||||
num = self.lib.llama_tokenize(self.model, encoded_text, len(encoded_text), self.token_ids, len(self.token_ids), add_special, parse_special)
|
||||
num = self.lib.llama_tokenize(self.vocab, encoded_text, len(encoded_text), self.token_ids, len(self.token_ids), add_special, parse_special)
|
||||
while num < 0 and len(self.token_ids) < (16 << 20):
|
||||
self.token_ids = self.ffi.new("llama_token[]", -2 * num)
|
||||
num = self.lib.llama_tokenize(self.model, encoded_text, len(encoded_text), self.token_ids, len(self.token_ids), add_special, parse_special)
|
||||
num = self.lib.llama_tokenize(self.vocab, encoded_text, len(encoded_text), self.token_ids, len(self.token_ids), add_special, parse_special)
|
||||
return list(self.token_ids[0:num])
|
||||
|
||||
def detokenize(self, ids: list[int], remove_special: bool = False, unparse_special: bool = False) -> str:
|
||||
@@ -109,10 +110,10 @@ class LibLlamaModel:
|
||||
self.token_ids = self.ffi.new("llama_token[]", 2 * len(ids))
|
||||
for i, id in enumerate(ids):
|
||||
self.token_ids[i] = id
|
||||
num = self.lib.llama_detokenize(self.model, self.token_ids, len(ids), self.text_buff, len(self.text_buff), remove_special, unparse_special)
|
||||
num = self.lib.llama_detokenize(self.vocab, self.token_ids, len(ids), self.text_buff, len(self.text_buff), remove_special, unparse_special)
|
||||
while num < 0 and len(self.text_buff) < (16 << 20):
|
||||
self.text_buff = self.ffi.new("uint8_t[]", -2 * num)
|
||||
num = self.lib.llama_detokenize(self.model, self.token_ids, len(ids), self.text_buff, len(self.text_buff), remove_special, unparse_special)
|
||||
num = self.lib.llama_detokenize(self.vocab, self.token_ids, len(ids), self.text_buff, len(self.text_buff), remove_special, unparse_special)
|
||||
return str(self.ffi.buffer(self.text_buff, num), encoding="utf-8", errors="replace") # replace errors with '\uFFFD' # pyright: ignore[reportArgumentType]
|
||||
|
||||
|
||||
|
||||
@@ -202,7 +202,8 @@ For the full list of features, please refer to [server's changelog](https://gith
|
||||
| `--api-prefix PREFIX` | prefix path the server serves from, without the trailing slash (default: )<br/>(env: LLAMA_ARG_API_PREFIX) |
|
||||
| `--ui-config, --webui-config JSON` | JSON that provides default UI settings (overrides UI defaults)<br/>(env: LLAMA_ARG_UI_CONFIG) |
|
||||
| `--ui-config-file, --webui-config-file PATH` | JSON file that provides default UI settings (overrides UI defaults)<br/>(env: LLAMA_ARG_UI_CONFIG_FILE) |
|
||||
| `--ui-mcp-proxy, --webui-mcp-proxy, --no-ui-mcp-proxy, --no-webui-mcp-proxy` | experimental: whether to enable MCP CORS proxy, for Llama Chat to reach public MCP servers without CORS headers; local and private addresses are refused - do not enable in untrusted environments (default: disabled)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_UI_MCP_PROXY) |
|
||||
| `--ui-mcp-proxy, --webui-mcp-proxy, --no-ui-mcp-proxy, --no-webui-mcp-proxy` | experimental: whether to enable MCP CORS proxy, for Llama Chat to reach public MCP servers without CORS headers; local and private addresses are refused unless --ui-mcp-proxy-allow-private-urls is set - do not enable in untrusted environments (default: disabled)<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_UI_MCP_PROXY) |
|
||||
| `--ui-mcp-proxy-allow-private-urls` | allow the MCP CORS proxy to reach local or private addresses (e.g. MCP servers on localhost or LAN) - anyone who can reach the proxy can then reach your local network (default: disabled, only public addresses)<br/>note: only has effect with --ui-mcp-proxy<br/>(env: LLAMA_ARG_UI_MCP_PROXY_ALLOW_PRIVATE_URLS) |
|
||||
| `--tools TOOL1,TOOL2,...` | experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)<br/>specify "all" to enable all tools<br/>available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_info<br/>note: for security reasons, this will limit --cors-origins to localhost by default<br/>(env: LLAMA_ARG_TOOLS) |
|
||||
| `--tools-runtime OPTION` | experimental: run tools in a separate runtime environment (default: none, use host environment)<br/>available options:<br/> 'docker:<image>', 'podman:<image>': spin up a new container and reuse it for all invocations, clean up on server exit<br/> 'docker-container:<id>', 'podman-container:<id>': use an existing container by ID, won't stop on server exit<br/> 'ssh:<target>': run tools on a remote POSIX host over SSH, key-based auth and a trusted host key are required<br/><br/>(env: LLAMA_ARG_TOOLS_RUNTIME) |
|
||||
| `--allow-unauthenticated-tools` | allow server tools, MCP servers or MCP proxy on a non-loopback address without an API key - only for trusted networks (default: disabled)<br/>(env: LLAMA_ARG_ALLOW_UNAUTHENTICATED_TOOLS) |
|
||||
@@ -393,7 +394,7 @@ Every server is spawned once at startup to list its tools, then stopped, and res
|
||||
|
||||
The child process runs with the same privileges as the server, so only declare commands you trust. As with `--tools`, `--cors-origins` then defaults to `localhost`.
|
||||
|
||||
Note: `--ui-mcp-proxy` is unrelated, it only lets Llama Chat reach public MCP servers that do not send CORS headers. It refuses local and private addresses (loopback, LAN, link-local); connect to those from Llama Chat directly.
|
||||
Note: `--ui-mcp-proxy` is unrelated, it only lets Llama Chat reach public MCP servers that do not send CORS headers. By default it refuses local and private addresses (loopback, LAN, link-local); either connect to those from Llama Chat directly (the MCP server must send CORS headers), or add `--ui-mcp-proxy-allow-private-urls`.
|
||||
|
||||
Any server written against the [MCP specification](https://modelcontextprotocol.io) works as is, whether it uses an official SDK or not: the transport is one JSON-RPC message per line on stdio, so a script wrapping an existing program is a valid server too.
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ static std::string proxy_header_to_lower(std::string header) {
|
||||
return header;
|
||||
}
|
||||
|
||||
static server_http_res_ptr proxy_request(const server_http_req & req, std::string method) {
|
||||
static server_http_res_ptr proxy_request(const server_http_req & req, std::string method, bool allow_private_urls) {
|
||||
std::string target_url = req.get_param("url");
|
||||
common_http_url parsed_url = common_http_parse_url(target_url);
|
||||
|
||||
@@ -70,8 +70,7 @@ static server_http_res_ptr proxy_request(const server_http_req & req, std::strin
|
||||
req.should_stop,
|
||||
600, // timeout_read (default to 10 minutes)
|
||||
600, // timeout_write (default to 10 minutes)
|
||||
// test-only escape hatch
|
||||
server_resolve_public_addr(parsed_url.host, !common_get_env("LLAMA_SERVER_DEBUG_PROXY_ALLOW_PRIVATE").empty())
|
||||
server_resolve_public_addr(parsed_url.host, allow_private_urls)
|
||||
);
|
||||
|
||||
// route redirects back through the proxy, so each hop is checked
|
||||
@@ -86,10 +85,8 @@ static server_http_res_ptr proxy_request(const server_http_req & req, std::strin
|
||||
return proxy;
|
||||
}
|
||||
|
||||
static server_http_context::handler_t proxy_handler_post = [](const server_http_req & req) -> server_http_res_ptr {
|
||||
return proxy_request(req, "POST");
|
||||
};
|
||||
|
||||
static server_http_context::handler_t proxy_handler_get = [](const server_http_req & req) -> server_http_res_ptr {
|
||||
return proxy_request(req, "GET");
|
||||
};
|
||||
static server_http_context::handler_t proxy_make_handler(const std::string & method, bool allow_private_urls) {
|
||||
return [method, allow_private_urls](const server_http_req & req) -> server_http_res_ptr {
|
||||
return proxy_request(req, method, allow_private_urls);
|
||||
};
|
||||
}
|
||||
|
||||
@@ -281,9 +281,11 @@ static bool server_setup_features(
|
||||
|
||||
// CORS proxy (EXPERIMENTAL, only used by Llama Chat for MCP)
|
||||
if (params.ui_mcp_proxy) {
|
||||
ctx_http.get ("/cors-proxy", ex_wrapper(proxy_handler_get));
|
||||
ctx_http.post("/cors-proxy", ex_wrapper(proxy_handler_post));
|
||||
warn_names.push_back("MCP proxy (experimental)");
|
||||
ctx_http.get ("/cors-proxy", ex_wrapper(proxy_make_handler("GET", params.ui_mcp_proxy_allow_private_urls)));
|
||||
ctx_http.post("/cors-proxy", ex_wrapper(proxy_make_handler("POST", params.ui_mcp_proxy_allow_private_urls)));
|
||||
warn_names.push_back(params.ui_mcp_proxy_allow_private_urls
|
||||
? "MCP proxy (experimental, local and private addresses allowed)"
|
||||
: "MCP proxy (experimental)");
|
||||
} else {
|
||||
ctx_http.get ("/cors-proxy", ex_wrapper(res_403));
|
||||
ctx_http.post("/cors-proxy", ex_wrapper(res_403));
|
||||
|
||||
@@ -6,4 +6,5 @@ numpy~=2.5.4; python_version >= "3.14"
|
||||
openai~=2.14.0
|
||||
prometheus-client~=0.20.0
|
||||
requests~=2.32.3
|
||||
websockets~=15.0
|
||||
wget~=3.2
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import base64
|
||||
import pytest
|
||||
import requests
|
||||
import struct
|
||||
@@ -135,3 +136,78 @@ def test_speech_router():
|
||||
server = ServerPreset.router()
|
||||
server.start()
|
||||
assert_wav(post_audio("/v1/audio/speech", model=model))
|
||||
|
||||
|
||||
#
|
||||
# tts only model, with voice cloning
|
||||
#
|
||||
|
||||
def pocket_tts(path: str = "/v1/audio/speech", **extra) -> requests.Response:
|
||||
body = {"input": "Hello there.", "seed": 42, "n_predict": 8, **extra}
|
||||
return requests.post(server.make_url(path), json=body, timeout=DEFAULT_REQUEST_TIMEOUT)
|
||||
|
||||
|
||||
def test_tts_only():
|
||||
global server
|
||||
server = ServerPreset.tinypockettts()
|
||||
server.start()
|
||||
res = server.make_request("GET", "/props")
|
||||
assert not res.body.get("voices") # this slice has no predefined voices
|
||||
res = server.make_request("GET", "/v1/models")
|
||||
assert res.body["data"][0]["architecture"]["output_modalities"] == ["audio"]
|
||||
res = pocket_tts()
|
||||
assert_wav(res)
|
||||
assert res.content == pocket_tts().content
|
||||
|
||||
|
||||
def test_tts_only_speaker_ref():
|
||||
global server
|
||||
server = ServerPreset.tinypockettts()
|
||||
server.start()
|
||||
ref_a = make_wav(seconds=2.0, rate=24000, freq=220)
|
||||
ref_b = make_wav(seconds=2.0, rate=24000, freq=440)
|
||||
res = pocket_tts("/tts", speaker_ref_b64=base64.b64encode(ref_a).decode())
|
||||
assert_wav(res)
|
||||
assert res.content != pocket_tts("/tts").content
|
||||
assert res.content != pocket_tts("/tts", speaker_ref_b64=base64.b64encode(ref_b).decode()).content
|
||||
# the same reference as an uploaded file
|
||||
fields = {"input": (None, "Hello there."), "seed": (None, "42"), "n_predict": (None, "8"), "speaker_ref": ("ref.wav", ref_a)}
|
||||
res_file = requests.post(server.make_url("/tts"), files=fields, timeout=DEFAULT_REQUEST_TIMEOUT)
|
||||
assert res_file.content == res.content
|
||||
# /v1/audio/speech passes it through
|
||||
assert pocket_tts(speaker_ref_b64=base64.b64encode(ref_a).decode()).content == res.content
|
||||
|
||||
|
||||
@pytest.mark.parametrize("speaker_ref_b64,message", [
|
||||
("!!!", "not valid base64"),
|
||||
(base64.b64encode(b"not an audio file").decode(), "failed to decode"),
|
||||
])
|
||||
def test_tts_only_invalid_speaker_ref(speaker_ref_b64: str, message: str):
|
||||
global server
|
||||
server = ServerPreset.tinypockettts()
|
||||
server.start()
|
||||
res = pocket_tts("/tts", speaker_ref_b64=speaker_ref_b64)
|
||||
assert res.status_code == 400
|
||||
assert message in res.json()["error"]["message"]
|
||||
|
||||
|
||||
def test_tts_only_end_of_speech():
|
||||
global server
|
||||
server = ServerPreset.tinypockettts()
|
||||
server.start()
|
||||
# the end-of-speech head stops the generation before n_predict
|
||||
res = pocket_tts(n_predict=16)
|
||||
assert_wav(res)
|
||||
assert res.content == pocket_tts(n_predict=1000).content
|
||||
|
||||
|
||||
@pytest.mark.parametrize("path", ["/v1/chat/completions", "/v1/audio/transcriptions"])
|
||||
def test_tts_only_no_text_output(path: str):
|
||||
global server
|
||||
server = ServerPreset.tinypockettts()
|
||||
server.start()
|
||||
if path == "/v1/audio/transcriptions":
|
||||
res = requests.post(server.make_url(path), files={"file": ("audio.wav", make_wav())}, timeout=DEFAULT_REQUEST_TIMEOUT)
|
||||
else:
|
||||
res = requests.post(server.make_url(path), json={"messages": [{"role": "user", "content": "hello"}]}, timeout=DEFAULT_REQUEST_TIMEOUT)
|
||||
assert res.status_code == 501
|
||||
|
||||
@@ -0,0 +1,144 @@
|
||||
import base64
|
||||
import json
|
||||
import pytest
|
||||
import requests
|
||||
from utils import *
|
||||
|
||||
server: ServerProcess
|
||||
|
||||
MP3_PATH = os.path.join(os.path.dirname(__file__), "../../../mtmd/test-2.mp3")
|
||||
|
||||
# full random sampling, so that the output depends on the audio
|
||||
SAMPLING_RANDOM = {"temperature": 1.0, "top_k": 0, "top_p": 1.0, "min_p": 0.0, "seed": 42}
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def create_server():
|
||||
global server
|
||||
server = ServerPreset.tinylfm3omni()
|
||||
server.jinja = True
|
||||
server.reasoning = "off"
|
||||
|
||||
|
||||
def post_transcription(path: str = "/v1/audio/transcriptions", audio: bytes | None = None, filename: str = "audio.wav", **fields) -> requests.Response:
|
||||
data = {"max_tokens": "8", **fields}
|
||||
files = {"file": (filename, make_wav() if audio is None else audio)}
|
||||
return requests.post(server.make_url(path), data=data, files=files, timeout=DEFAULT_REQUEST_TIMEOUT)
|
||||
|
||||
|
||||
def chat_with_audio(audio: bytes, fmt: str = "wav", extra: dict | None = None) -> str:
|
||||
res = server.make_request("POST", "/v1/chat/completions", data={
|
||||
"max_tokens": 8,
|
||||
"messages": [{"role": "user", "content": [
|
||||
{"type": "input_audio", "input_audio": {"data": base64.b64encode(audio).decode(), "format": fmt}},
|
||||
]}],
|
||||
**(extra or {}),
|
||||
})
|
||||
assert res.status_code == 200, res.body
|
||||
return res.body["choices"][0]["message"]["content"]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("path", ["/v1/audio/transcriptions", "/audio/transcriptions"])
|
||||
def test_transcription(path: str):
|
||||
server.start()
|
||||
res = post_transcription(path)
|
||||
assert res.status_code == 200
|
||||
body = res.json()
|
||||
assert body["type"] == "transcript.text.done"
|
||||
assert len(body["text"]) > 0
|
||||
assert 0 < body["usage"]["output_tokens"] <= 8
|
||||
assert body["usage"]["input_tokens"] > 0
|
||||
|
||||
|
||||
def test_transcription_mp3():
|
||||
server.start()
|
||||
with open(MP3_PATH, "rb") as f:
|
||||
res = post_transcription(audio=f.read(), filename="audio.mp3")
|
||||
assert res.status_code == 200
|
||||
assert len(res.json()["text"]) > 0
|
||||
|
||||
|
||||
def test_transcription_stream():
|
||||
server.start()
|
||||
res = post_transcription(stream="true")
|
||||
assert res.status_code == 200
|
||||
lines = [line[len("data: "):] for line in res.text.splitlines() if line.startswith("data: ")]
|
||||
assert lines[-1] == "[DONE]"
|
||||
events = [json.loads(line) for line in lines[:-1]]
|
||||
assert len(events) > 1
|
||||
assert all(ev["type"] == "transcript.text.delta" for ev in events[:-1])
|
||||
assert events[-1]["type"] == "transcript.text.done"
|
||||
text = "".join(ev["delta"] for ev in events[:-1])
|
||||
assert text == events[-1]["text"]
|
||||
assert text == post_transcription().json()["text"]
|
||||
|
||||
|
||||
def test_transcription_language():
|
||||
server.start()
|
||||
# the LFM3 template puts the language in the system prompt
|
||||
n_default = post_transcription().json()["usage"]["input_tokens"]
|
||||
n_fr = post_transcription(language="fr").json()["usage"]["input_tokens"]
|
||||
assert n_fr > n_default
|
||||
|
||||
|
||||
@pytest.mark.parametrize("fields,files,message", [
|
||||
({"response_format": "text"}, None, "response_format"),
|
||||
({}, {"file": ("audio.wav", b"not an audio file")}, None),
|
||||
({}, {"other": ("audio.wav", b"")}, None),
|
||||
])
|
||||
def test_transcription_invalid_request(fields: dict, files: dict | None, message: str | None):
|
||||
server.start()
|
||||
res = requests.post(server.make_url("/v1/audio/transcriptions"), data={"max_tokens": "8", **fields},
|
||||
files=files or {"file": ("audio.wav", make_wav())}, timeout=DEFAULT_REQUEST_TIMEOUT)
|
||||
assert res.status_code == 400
|
||||
if message:
|
||||
assert message in res.json()["error"]["message"]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("preset", [
|
||||
"tinyllama2", # no audio input
|
||||
"tinyvoxtralrt", # live transcription only
|
||||
])
|
||||
def test_transcription_not_supported(preset: str):
|
||||
global server
|
||||
server = getattr(ServerPreset, preset)()
|
||||
server.start()
|
||||
assert post_transcription().status_code == 501 # ERROR_TYPE_NOT_SUPPORTED
|
||||
|
||||
|
||||
def test_transcription_router():
|
||||
global server
|
||||
model = server.model_hf_repo
|
||||
server = ServerPreset.router()
|
||||
server.start()
|
||||
res = post_transcription(model=model)
|
||||
assert res.status_code == 200
|
||||
assert res.json()["type"] == "transcript.text.done"
|
||||
|
||||
|
||||
def test_chat_input_audio():
|
||||
server.start()
|
||||
a = make_wav(freq=220)
|
||||
b = make_wav(freq=880)
|
||||
assert chat_with_audio(a, extra=SAMPLING_RANDOM) == chat_with_audio(a, extra=SAMPLING_RANDOM)
|
||||
assert chat_with_audio(a, extra=SAMPLING_RANDOM) != chat_with_audio(b, extra=SAMPLING_RANDOM)
|
||||
|
||||
|
||||
def test_chat_input_audio_mp3():
|
||||
server.start()
|
||||
with open(MP3_PATH, "rb") as f:
|
||||
assert len(chat_with_audio(f.read(), fmt="mp3")) > 0
|
||||
|
||||
|
||||
def test_chat_input_audio_no_audio_model():
|
||||
global server
|
||||
server = ServerPreset.tinyllama2()
|
||||
server.start()
|
||||
res = server.make_request("POST", "/v1/chat/completions", data={
|
||||
"max_tokens": 8,
|
||||
"messages": [{"role": "user", "content": [
|
||||
{"type": "input_audio", "input_audio": {"data": base64.b64encode(make_wav()).decode(), "format": "wav"}},
|
||||
]}],
|
||||
})
|
||||
assert res.status_code != 200
|
||||
assert "audio input is not supported" in res.body["error"]["message"]
|
||||
@@ -35,7 +35,7 @@ def test_mcp_proxy():
|
||||
def test_mcp_proxy_custom_port():
|
||||
global server
|
||||
server.ui_mcp_proxy = True
|
||||
server.debug_proxy_allow_private = True
|
||||
server.ui_mcp_proxy_allow_private_urls = True
|
||||
server.start()
|
||||
|
||||
# try getting the server's models API via the proxy
|
||||
@@ -61,7 +61,7 @@ def test_mcp_proxy_no_content():
|
||||
try:
|
||||
global server
|
||||
server.ui_mcp_proxy = True
|
||||
server.debug_proxy_allow_private = True
|
||||
server.ui_mcp_proxy_allow_private_urls = True
|
||||
server.start()
|
||||
|
||||
res = server.make_request("POST", f"/cors-proxy?url=http://127.0.0.1:{target.server_port}/", data={})
|
||||
@@ -116,7 +116,7 @@ def test_mcp_proxy_redirect_goes_through_proxy():
|
||||
try:
|
||||
global server
|
||||
server.ui_mcp_proxy = True
|
||||
server.debug_proxy_allow_private = True
|
||||
server.ui_mcp_proxy_allow_private_urls = True
|
||||
server.start()
|
||||
|
||||
url = server.make_url(f"/cors-proxy?url=http://127.0.0.1:{target.server_port}/start")
|
||||
|
||||
@@ -0,0 +1,410 @@
|
||||
import base64
|
||||
import json
|
||||
import time
|
||||
import pytest
|
||||
from websockets.exceptions import ConnectionClosed
|
||||
from websockets.sync.client import connect, ClientConnection
|
||||
from websockets.sync.connection import Connection
|
||||
from utils import *
|
||||
|
||||
server: ServerProcess
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def create_server():
|
||||
global server
|
||||
server = ServerPreset.tinylfm3omni()
|
||||
server.jinja = True
|
||||
server.reasoning = "off"
|
||||
|
||||
|
||||
def ws_connect(path: str = "/v1/realtime") -> ClientConnection:
|
||||
return connect(server.make_url(path).replace("http://", "ws://", 1), max_size=None, open_timeout=DEFAULT_REQUEST_TIMEOUT)
|
||||
|
||||
|
||||
def send(ws: Connection, type: str, **fields):
|
||||
ws.send(json.dumps({"type": type, **fields}))
|
||||
|
||||
|
||||
def send_audio(ws: Connection, pcm: bytes):
|
||||
send(ws, "input_audio_buffer.append", audio=base64.b64encode(pcm).decode())
|
||||
|
||||
|
||||
def send_text(ws: Connection, text: str):
|
||||
send(ws, "conversation.item.create", item={"type": "message", "role": "user", "content": [{"type": "input_text", "text": text}]})
|
||||
|
||||
|
||||
def recv(ws: Connection) -> dict:
|
||||
return json.loads(ws.recv(timeout=DEFAULT_REQUEST_TIMEOUT))
|
||||
|
||||
|
||||
def recv_until(ws: Connection, type: str) -> list[dict]:
|
||||
events = []
|
||||
while True:
|
||||
ev = recv(ws)
|
||||
events.append(ev)
|
||||
if ev["type"] == type:
|
||||
return events
|
||||
assert ev["type"] != "error", ev
|
||||
|
||||
|
||||
def recv_all(ws: Connection) -> list[dict]:
|
||||
""" read events until the server closes the socket """
|
||||
events = []
|
||||
try:
|
||||
while True:
|
||||
events.append(recv(ws))
|
||||
except ConnectionClosed:
|
||||
return events
|
||||
|
||||
|
||||
def get_transcripts(events: list[dict]) -> list[tuple[str, str]]:
|
||||
""" (item_id, transcript) of each completed item, checked against its deltas """
|
||||
deltas: dict[str, str] = {}
|
||||
out = []
|
||||
for ev in events:
|
||||
assert ev["type"] != "error", ev
|
||||
if ev["type"] == "conversation.item.input_audio_transcription.delta":
|
||||
deltas[ev["item_id"]] = deltas.get(ev["item_id"], "") + ev["delta"]
|
||||
elif ev["type"] == "conversation.item.input_audio_transcription.completed":
|
||||
assert ev["transcript"] == deltas.get(ev["item_id"], "")
|
||||
out.append((ev["item_id"], ev["transcript"]))
|
||||
return out
|
||||
|
||||
|
||||
def session_update(ws: Connection, **session) -> dict:
|
||||
send(ws, "session.update", session=session)
|
||||
return recv_until(ws, "session.updated")[-1]["session"]
|
||||
|
||||
|
||||
#
|
||||
# live transcription
|
||||
#
|
||||
|
||||
LIVE_ASR = [
|
||||
# a chat model with an "asr" chat template, live only in sessions opened with ?intent=transcription
|
||||
("tinylfm3omni", "/v1/realtime?intent=transcription"),
|
||||
# no chat, the text follows the audio by a few tokens
|
||||
("tinyvoxtralrt", "/v1/realtime"),
|
||||
]
|
||||
|
||||
|
||||
def start_live_asr(preset: str):
|
||||
global server
|
||||
if preset != "tinylfm3omni":
|
||||
server = getattr(ServerPreset, preset)()
|
||||
server.start()
|
||||
|
||||
|
||||
@pytest.mark.parametrize("preset,path", LIVE_ASR)
|
||||
def test_live_asr(preset: str, path: str):
|
||||
start_live_asr(preset)
|
||||
with ws_connect(path) as ws:
|
||||
session = recv(ws)
|
||||
assert session["type"] == "session.created"
|
||||
assert session["session"]["object"] == "realtime.transcription_session"
|
||||
assert session["session"]["audio"]["input"]["format"] == {"type": "audio/pcm", "rate": 16000}
|
||||
send_audio(ws, make_pcm16())
|
||||
send(ws, "input_audio_buffer.commit")
|
||||
send_audio(ws, make_pcm16(freq=880))
|
||||
send(ws, "input_audio_buffer.commit", final=True)
|
||||
events = recv_all(ws)
|
||||
committed = [ev for ev in events if ev["type"] == "input_audio_buffer.committed"]
|
||||
assert len(committed) == 1
|
||||
assert committed[0]["previous_item_id"] is None
|
||||
transcripts = get_transcripts(events)
|
||||
assert len(transcripts) == 2
|
||||
assert transcripts[0][0] == committed[0]["item_id"]
|
||||
assert transcripts[1][0] != transcripts[0][0]
|
||||
assert all(len(text) > 0 for _, text in transcripts)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("preset,path", LIVE_ASR)
|
||||
def test_live_asr_chunked_audio(preset: str, path: str):
|
||||
start_live_asr(preset)
|
||||
pcm = make_pcm16()
|
||||
results = []
|
||||
for n_chunks in [1, 7]:
|
||||
size = len(pcm) // n_chunks // 2 * 2
|
||||
with ws_connect(path) as ws:
|
||||
recv(ws)
|
||||
for i in range(0, len(pcm), size):
|
||||
send_audio(ws, pcm[i:i + size])
|
||||
send(ws, "input_audio_buffer.commit", final=True)
|
||||
results.append([text for _, text in get_transcripts(recv_all(ws))])
|
||||
assert results[0] == results[1]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("preset,path", LIVE_ASR)
|
||||
def test_live_asr_input_rate(preset: str, path: str):
|
||||
start_live_asr(preset)
|
||||
with ws_connect(path) as ws:
|
||||
recv(ws)
|
||||
send(ws, "session.update", session={"audio": {"input": {"format": {"type": "audio/pcm", "rate": 4000}}}})
|
||||
assert "between 8000 and 192000" in recv_until(ws, "error")[-1]["error"]["message"]
|
||||
send(ws, "session.update", session={"audio": {"input": {"format": {"type": "audio/pcm", "rate": 24000}}}})
|
||||
assert recv_until(ws, "session.updated")[-1]["session"]["audio"]["input"]["format"]["rate"] == 24000
|
||||
send_audio(ws, make_pcm16(rate=24000))
|
||||
send(ws, "input_audio_buffer.commit", final=True)
|
||||
transcripts = get_transcripts(recv_all(ws))
|
||||
assert len(transcripts) == 1
|
||||
assert len(transcripts[0][1]) > 0
|
||||
|
||||
|
||||
@pytest.mark.parametrize("preset,path", LIVE_ASR)
|
||||
def test_live_asr_invalid_events(preset: str, path: str):
|
||||
start_live_asr(preset)
|
||||
with ws_connect(path) as ws:
|
||||
recv(ws)
|
||||
ws.send("not json")
|
||||
assert recv_until(ws, "error")[-1]["error"]["message"] == "invalid JSON"
|
||||
send(ws, "response.create")
|
||||
assert "unknown event type" in recv_until(ws, "error")[-1]["error"]["message"]
|
||||
send(ws, "input_audio_buffer.clear")
|
||||
recv_until(ws, "input_audio_buffer.cleared")
|
||||
# the session still works
|
||||
send_audio(ws, make_pcm16())
|
||||
send(ws, "input_audio_buffer.commit", final=True)
|
||||
assert len(get_transcripts(recv_all(ws))) == 1
|
||||
|
||||
|
||||
def test_live_asr_depends_on_audio():
|
||||
# the random weights of this model give a different text for each input
|
||||
start_live_asr("tinyvoxtralrt")
|
||||
results = []
|
||||
for freq in [220, 880, 220]:
|
||||
with ws_connect() as ws:
|
||||
recv(ws)
|
||||
send_audio(ws, make_pcm16(freq=freq))
|
||||
send(ws, "input_audio_buffer.commit", final=True)
|
||||
results.append(get_transcripts(recv_all(ws))[0][1])
|
||||
assert results[0] != results[1]
|
||||
assert results[0] == results[2]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("preset", ["tinypockettts", "tinyllama2"])
|
||||
def test_realtime_not_supported(preset: str):
|
||||
global server
|
||||
server = getattr(ServerPreset, preset)()
|
||||
server.start()
|
||||
with ws_connect() as ws:
|
||||
events = recv_all(ws)
|
||||
assert len(events) == 1
|
||||
assert events[0]["type"] == "error"
|
||||
assert "does not support realtime" in events[0]["error"]["message"]
|
||||
|
||||
|
||||
#
|
||||
# realtime conversation
|
||||
#
|
||||
|
||||
def test_conversation_text():
|
||||
server.start()
|
||||
with ws_connect() as ws:
|
||||
session = recv(ws)
|
||||
assert session["type"] == "session.created"
|
||||
assert session["session"]["object"] == "realtime.session"
|
||||
assert session["session"]["audio"]["output"]["format"]["rate"] > 0
|
||||
session_update(ws, output_modalities=["text"], max_output_tokens=8)
|
||||
send_text(ws, "hello")
|
||||
user_item = recv_until(ws, "conversation.item.done")[-1]["item"]
|
||||
assert user_item["role"] == "user"
|
||||
assert user_item["content"] == [{"type": "input_text", "text": "hello"}]
|
||||
send(ws, "response.create")
|
||||
events = recv_until(ws, "response.done")
|
||||
|
||||
types = [ev["type"] for ev in events]
|
||||
n_deltas = types.count("response.output_text.delta")
|
||||
assert n_deltas == 8
|
||||
assert types == [
|
||||
"response.created",
|
||||
"response.output_item.added",
|
||||
"response.content_part.added",
|
||||
*["response.output_text.delta"] * n_deltas,
|
||||
"response.output_text.done",
|
||||
"response.content_part.done",
|
||||
"response.output_item.done",
|
||||
"response.done",
|
||||
]
|
||||
response = events[-1]["response"]
|
||||
assert response["status"] == "completed"
|
||||
assert response["id"] == events[0]["response"]["id"]
|
||||
assert response["usage"]["output_tokens"] == 8
|
||||
text = "".join(ev["delta"] for ev in events if ev["type"] == "response.output_text.delta")
|
||||
assert response["output"][0]["role"] == "assistant"
|
||||
assert response["output"][0]["content"] == [{"type": "output_text", "text": text}]
|
||||
|
||||
|
||||
def test_conversation_audio():
|
||||
server.start()
|
||||
with ws_connect() as ws:
|
||||
recv(ws)
|
||||
session_update(ws, output_modalities=["audio"], max_output_tokens=8)
|
||||
send_audio(ws, make_pcm16())
|
||||
# response.create commits the pending audio
|
||||
send(ws, "response.create")
|
||||
events = recv_until(ws, "response.done")
|
||||
types = [ev["type"] for ev in events]
|
||||
assert types[:3] == ["input_audio_buffer.committed", "conversation.item.added", "conversation.item.done"]
|
||||
assert events[2]["item"]["content"] == [{"type": "input_audio"}]
|
||||
assert "response.output_text.delta" not in types
|
||||
audio = b"".join(base64.b64decode(ev["delta"]) for ev in events if ev["type"] == "response.output_audio.delta")
|
||||
assert len(audio) > 0 and len(audio) % 2 == 0
|
||||
response = events[-1]["response"]
|
||||
assert response["status"] == "completed"
|
||||
assert response["output"][0]["content"][0]["type"] == "output_audio"
|
||||
|
||||
|
||||
def test_conversation_multi_turn():
|
||||
server.start()
|
||||
with ws_connect() as ws:
|
||||
recv(ws)
|
||||
session_update(ws, output_modalities=["text"], max_output_tokens=4)
|
||||
send_text(ws, "hello")
|
||||
recv_until(ws, "conversation.item.done")
|
||||
send(ws, "response.create")
|
||||
first = recv_until(ws, "response.done")[-1]["response"]
|
||||
send_audio(ws, make_pcm16())
|
||||
send(ws, "input_audio_buffer.commit")
|
||||
committed = recv_until(ws, "input_audio_buffer.committed")[-1]
|
||||
assert committed["previous_item_id"] == first["output"][0]["id"]
|
||||
send(ws, "response.create")
|
||||
second = recv_until(ws, "response.done")[-1]["response"]
|
||||
assert second["status"] == "completed"
|
||||
assert second["id"] != first["id"]
|
||||
|
||||
|
||||
def test_conversation_cancel():
|
||||
server.start()
|
||||
with ws_connect() as ws:
|
||||
recv(ws)
|
||||
session_update(ws, output_modalities=["text"])
|
||||
send_text(ws, "hello")
|
||||
send(ws, "response.create")
|
||||
recv_until(ws, "response.output_text.delta")
|
||||
send(ws, "response.cancel")
|
||||
assert recv_until(ws, "response.done")[-1]["response"]["status"] == "cancelled"
|
||||
# the session still works
|
||||
send_text(ws, "hello again")
|
||||
send(ws, "response.create", response={"max_output_tokens": 4})
|
||||
response = recv_until(ws, "response.done")[-1]["response"]
|
||||
assert response["status"] == "completed"
|
||||
assert response["usage"]["output_tokens"] == 4
|
||||
|
||||
|
||||
def test_conversation_session_update():
|
||||
server.start()
|
||||
tools = [{"type": "function", "name": "get_weather", "description": "Get the weather",
|
||||
"parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}}]
|
||||
with ws_connect() as ws:
|
||||
recv(ws)
|
||||
session = session_update(ws, instructions="Be brief.", tools=tools, tool_choice="none", max_output_tokens=16,
|
||||
audio={"output": {"voice": {"id": "male"}}})
|
||||
assert session["instructions"] == "Be brief."
|
||||
assert session["tools"] == tools
|
||||
assert session["tool_choice"] == "none"
|
||||
assert session["max_output_tokens"] == 16
|
||||
assert session["audio"]["output"]["voice"] == "male"
|
||||
session = session_update(ws, max_output_tokens="inf", output_modalities=["text", "audio"])
|
||||
assert session["max_output_tokens"] == "inf"
|
||||
assert session["output_modalities"] == ["text", "audio"]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("events,message", [
|
||||
([{"type": "response.create"}], "commit audio or create a message first"),
|
||||
([{"type": "input_audio_buffer.commit"}], "the buffer is empty"),
|
||||
([{"type": "conversation.item.create", "item": {"type": "message", "role": "assistant", "content": []}}], "only user messages"),
|
||||
([{"type": "conversation.item.create", "item": {"type": "message", "role": "user", "content": [{"type": "input_image"}]}}], "unsupported content type"),
|
||||
([{"type": "conversation.item.create", "item": {"type": "function_call_output", "call_id": "x", "output": "{}"}}], "must follow the response"),
|
||||
([{"type": "session.update", "session": {"type": "foo"}}], "unknown session type"),
|
||||
([{"type": "session.update", "session": {"output_modalities": []}}], "non-empty array"),
|
||||
([{"type": "session.update", "session": {"output_modalities": ["video"]}}], "unknown modality"),
|
||||
([{"type": "session.update", "session": {"max_output_tokens": 0}}], "max_output_tokens"),
|
||||
([{"type": "session.update", "session": {"tool_choice": "maybe"}}], "tool_choice"),
|
||||
([{"type": "session.update", "session": {"audio": {"output": {"voice": "alloy"}}}}], "unknown voice"),
|
||||
([{"type": "conversation.item.create", "item": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "hi"}]}},
|
||||
{"type": "session.update", "session": {"instructions": "Be brief."}}], "cannot change after"),
|
||||
([{"type": "conversation.item.create", "item": {"type": "message", "role": "user", "content": [{"type": "input_text", "text": "hi"}]}},
|
||||
{"type": "session.update", "session": {"type": "transcription"}}], "cannot change after"),
|
||||
])
|
||||
def test_conversation_invalid_events(events: list[dict], message: str):
|
||||
server.start()
|
||||
with ws_connect() as ws:
|
||||
recv(ws)
|
||||
for ev in events:
|
||||
ws.send(json.dumps(ev))
|
||||
err = recv_until(ws, "error")[-1]
|
||||
assert message in err["error"]["message"]
|
||||
|
||||
|
||||
def test_transcription_session():
|
||||
server.start()
|
||||
with ws_connect() as ws:
|
||||
recv(ws)
|
||||
session = session_update(ws, type="transcription", max_output_tokens=8,
|
||||
audio={"input": {"transcription": {"language": "fr"}}})
|
||||
assert session["object"] == "realtime.transcription_session"
|
||||
assert session["audio"]["input"]["transcription"]["language"] == "fr"
|
||||
send_text(ws, "hello")
|
||||
assert "not supported in a transcription session" in recv_until(ws, "error")[-1]["error"]["message"]
|
||||
transcripts = []
|
||||
for freq in [440, 880]:
|
||||
send_audio(ws, make_pcm16(freq=freq))
|
||||
send(ws, "input_audio_buffer.commit")
|
||||
committed = recv_until(ws, "input_audio_buffer.committed")[-1]
|
||||
events = recv_until(ws, "conversation.item.input_audio_transcription.completed")
|
||||
transcripts += get_transcripts(events)
|
||||
assert transcripts[-1][0] == committed["item_id"]
|
||||
assert len(transcripts) == 2
|
||||
assert all(len(text) > 0 for _, text in transcripts)
|
||||
|
||||
|
||||
#
|
||||
# slot and server state
|
||||
#
|
||||
|
||||
@pytest.mark.parametrize("path", ["/v1/realtime", "/v1/realtime?intent=transcription"])
|
||||
def test_realtime_disconnect_frees_slot(path: str):
|
||||
server.n_slots = 1
|
||||
server.start()
|
||||
with ws_connect(path) as ws:
|
||||
recv(ws)
|
||||
send_audio(ws, make_pcm16())
|
||||
if path == "/v1/realtime":
|
||||
send(ws, "response.create")
|
||||
recv_until(ws, "response.output_item.added")
|
||||
# the socket is closed in the middle of the session
|
||||
res = server.make_request("POST", "/v1/chat/completions", data={
|
||||
"max_tokens": 4,
|
||||
"messages": [{"role": "user", "content": "hello"}],
|
||||
})
|
||||
assert res.status_code == 200
|
||||
|
||||
|
||||
def test_realtime_router():
|
||||
global server
|
||||
model = server.model_hf_repo
|
||||
server = ServerPreset.router()
|
||||
server.start()
|
||||
with ws_connect(f"/v1/realtime?model={model}") as ws:
|
||||
assert recv(ws)["type"] == "session.created"
|
||||
session_update(ws, output_modalities=["text"], max_output_tokens=4)
|
||||
send_text(ws, "hello")
|
||||
send(ws, "response.create")
|
||||
assert recv_until(ws, "response.done")[-1]["response"]["status"] == "completed"
|
||||
|
||||
|
||||
def test_realtime_sleep():
|
||||
server.sleep_idle_seconds = 1
|
||||
server.start()
|
||||
start = time.time()
|
||||
while not server.make_request("GET", "/props").body["is_sleeping"]:
|
||||
assert time.time() - start < 10, "server did not go to sleep"
|
||||
time.sleep(0.1)
|
||||
# the session wakes the server up
|
||||
with ws_connect() as ws:
|
||||
assert recv(ws)["type"] == "session.created"
|
||||
session_update(ws, output_modalities=["text"], max_output_tokens=4)
|
||||
send_text(ws, "hello")
|
||||
send(ws, "response.create")
|
||||
assert recv_until(ws, "response.done")[-1]["response"]["status"] == "completed"
|
||||
@@ -314,7 +314,7 @@ def test_cors_proxy_only_forwards_explicit_proxy_headers():
|
||||
server = ServerPreset.tinyllama2()
|
||||
server.api_key = TEST_API_KEY
|
||||
server.ui_mcp_proxy = True
|
||||
server.debug_proxy_allow_private = True
|
||||
server.ui_mcp_proxy_allow_private_urls = True
|
||||
server.start()
|
||||
|
||||
res = server.make_request("GET", f"/cors-proxy?url=http://127.0.0.1:{target.server_port}/capture", headers={
|
||||
|
||||
@@ -5,6 +5,10 @@
|
||||
|
||||
import subprocess
|
||||
import os
|
||||
import io
|
||||
import math
|
||||
import struct
|
||||
import wave
|
||||
|
||||
TMP_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), "tmp")
|
||||
import re
|
||||
@@ -126,7 +130,7 @@ class ServerProcess:
|
||||
no_cache_idle_slots: bool = False
|
||||
log_path: str | None = None
|
||||
ui_mcp_proxy: bool = False
|
||||
debug_proxy_allow_private: bool = False # test-only: lets the CORS proxy reach local servers
|
||||
ui_mcp_proxy_allow_private_urls: bool = False
|
||||
media_allow_private_urls: bool = False
|
||||
allow_unauthenticated_tools: bool = False
|
||||
backend_sampling: bool = False
|
||||
@@ -155,8 +159,6 @@ class ServerProcess:
|
||||
**os.environ,
|
||||
"LLAMA_SERVER_DEBUG_FAKE_TIMING": "1",
|
||||
}
|
||||
if self.debug_proxy_allow_private:
|
||||
env["LLAMA_SERVER_DEBUG_PROXY_ALLOW_PRIVATE"] = "1"
|
||||
if self.llama_cache is not None:
|
||||
env["LLAMA_CACHE"] = self.llama_cache
|
||||
elif "LLAMA_CACHE" not in os.environ:
|
||||
@@ -313,6 +315,8 @@ class ServerProcess:
|
||||
server_args.append("--no-cache-idle-slots")
|
||||
if self.ui_mcp_proxy:
|
||||
server_args.append("--ui-mcp-proxy")
|
||||
if self.ui_mcp_proxy_allow_private_urls:
|
||||
server_args.append("--ui-mcp-proxy-allow-private-urls")
|
||||
if self.media_allow_private_urls:
|
||||
server_args.append("--media-allow-private-urls")
|
||||
if self.allow_unauthenticated_tools:
|
||||
@@ -726,6 +730,36 @@ class ServerPreset:
|
||||
server.seed = 42
|
||||
return server
|
||||
|
||||
@staticmethod
|
||||
def tinypockettts() -> ServerProcess:
|
||||
# tts only, with voice cloning
|
||||
server = ServerProcess()
|
||||
server.offline = True # will be downloaded by load_all()
|
||||
# mmproj is already provided by HF registry API
|
||||
server.model_hf_file = None
|
||||
server.model_hf_repo = "ggml-org-dev/tinyPocketTTS-for-testing-gguf:Q8_0"
|
||||
server.model_alias = "tinypockettts"
|
||||
server.n_ctx = 1024
|
||||
server.n_batch = 512
|
||||
server.n_slots = 1
|
||||
server.seed = 42
|
||||
return server
|
||||
|
||||
@staticmethod
|
||||
def tinyvoxtralrt() -> ServerProcess:
|
||||
# live transcription only, no chat
|
||||
server = ServerProcess()
|
||||
server.offline = True # will be downloaded by load_all()
|
||||
# mmproj is already provided by HF registry API
|
||||
server.model_hf_file = None
|
||||
server.model_hf_repo = "ggml-org-dev/tinyVoxtral-Realtime-for-testing-gguf:Q8_0"
|
||||
server.model_alias = "tinyvoxtralrt"
|
||||
server.n_ctx = 1024
|
||||
server.n_batch = 512
|
||||
server.n_slots = 1
|
||||
server.seed = 42
|
||||
return server
|
||||
|
||||
@staticmethod
|
||||
def router() -> ServerProcess:
|
||||
server = ServerProcess()
|
||||
@@ -832,3 +866,19 @@ def get_lan_ip(server: ServerProcess) -> str | None:
|
||||
|
||||
def is_slow_test_allowed():
|
||||
return os.environ.get("SLOW_TESTS") == "1" or os.environ.get("SLOW_TESTS") == "ON"
|
||||
|
||||
|
||||
def make_pcm16(seconds: float = 1.0, rate: int = 16000, freq: float = 440.0) -> bytes:
|
||||
""" sine tone as raw PCM16 mono samples """
|
||||
n = int(seconds * rate)
|
||||
return struct.pack(f"<{n}h", *(int(0.3 * 32767 * math.sin(2 * math.pi * freq * i / rate)) for i in range(n)))
|
||||
|
||||
|
||||
def make_wav(seconds: float = 1.0, rate: int = 16000, freq: float = 440.0) -> bytes:
|
||||
buf = io.BytesIO()
|
||||
with wave.open(buf, "wb") as w:
|
||||
w.setnchannels(1)
|
||||
w.setsampwidth(2)
|
||||
w.setframerate(rate)
|
||||
w.writeframes(make_pcm16(seconds, rate, freq))
|
||||
return buf.getvalue()
|
||||
|
||||
+3
-2
@@ -86,8 +86,9 @@ int main(int argc, char ** argv) {
|
||||
}
|
||||
|
||||
mtmd_context_params mtmd_params = mtmd_context_params_default();
|
||||
mtmd_params.use_gpu = params.mmproj_use_gpu;
|
||||
mtmd_params.device = params.mmproj_device;
|
||||
mtmd_params.use_gpu = params.mmproj_use_gpu;
|
||||
mtmd_params.device = params.mmproj_device;
|
||||
mtmd_params.n_threads = params.cpuparams.n_threads;
|
||||
mtmd::context_ptr mctx(mtmd_init_from_file(params.mmproj.path.c_str(), model, mtmd_params));
|
||||
if (!mctx) {
|
||||
LOG_ERR("failed to load mmproj %s\n", params.mmproj.path.c_str());
|
||||
|
||||
+6
-2
@@ -5,7 +5,8 @@ The UI of llama.cpp: the packages in `lib` and the apps built on them.
|
||||
```text
|
||||
ui/
|
||||
├── lib/
|
||||
│ └── ui/ @ggml-org/llama-ui: design tokens, fonts, surfaces and components
|
||||
│ ├── ui/ @ggml-org/llama-ui: design tokens, fonts, surfaces and components
|
||||
│ └── voice/ @ggml-org/llama-voice: microphone capture, transcription and dictation
|
||||
└── apps/
|
||||
└── chat/ Llama Chat, the chat app that llama-server serves
|
||||
```
|
||||
@@ -13,12 +14,15 @@ ui/
|
||||
- [`lib/ui`](lib/ui/README.md) draws the parts and handles interaction, with no business logic. It is built with
|
||||
`@sveltejs/package` and published to npm as `@ggml-org/llama-ui`. Apps in this repo skip the package: they compile
|
||||
its sources as part of their own build, so they hold no copy of a component, a token or a font.
|
||||
- [`lib/voice`](lib/voice/README.md) records the microphone and turns speech into text through llama-server, with no
|
||||
UI: Llama UI draws the voice parts. It is plain TypeScript built with `tsc`, plus a Svelte entry
|
||||
(`@ggml-org/llama-voice/svelte`). Apps in this repo compile its sources too. It is not published to npm yet.
|
||||
- [`apps/chat`](apps/chat/README.md) talks to llama-server, stores conversations and runs the agentic loop. CMake
|
||||
builds it into llama-server (see `scripts/ui-assets.cmake`), and it is published to npm as `@ggml-org/llama-chat`
|
||||
(with `llama-chat` as its short name), so `npx llama-chat` runs it against any llama-server.
|
||||
|
||||
Each folder is its own npm package with its own `package-lock.json`: run `npm ci` in the one you work on. Building,
|
||||
checking and testing `apps/chat` needs no install in `lib/ui`.
|
||||
checking and testing `apps/chat` needs no install in `lib/ui` or `lib/voice`.
|
||||
|
||||
## Releases
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ const config: StorybookConfig = {
|
||||
'../tests/stories/**/*.stories.@(js|ts|svelte)',
|
||||
{
|
||||
directory: '../../../lib/ui/tests/stories',
|
||||
files: '{foundations,components,app,models,mockups}/**/*.stories.svelte'
|
||||
files: '{foundations,components,app,models,mockups,voice}/**/*.stories.svelte'
|
||||
}
|
||||
],
|
||||
addons: [
|
||||
|
||||
+200
-191
@@ -38,35 +38,21 @@ colors:
|
||||
art-night-sky: 'oklch(0.33 0.07 256)'
|
||||
art-cinder: 'oklch(0.68 0.18 46)'
|
||||
art-cinder-light: 'oklch(0.85 0.065 46)'
|
||||
cool-gray-50: 'oklch(0.958 0.002 250)'
|
||||
cool-gray-100: 'oklch(0.938 0.004 250)'
|
||||
cool-gray-200: 'oklch(0.91 0.005 250)'
|
||||
cool-gray-300: 'oklch(0.86 0.007 250)'
|
||||
cool-gray-400: 'oklch(0.81 0.01 250)'
|
||||
red-400: 'oklch(0.69 0.2 27)'
|
||||
red-450: 'oklch(0.635 0.229 28)'
|
||||
red-500: 'oklch(0.6 0.235 27)'
|
||||
red-550: 'oklch(0.588 0.236 28)'
|
||||
red-600: 'oklch(0.55 0.22 27)'
|
||||
red-800: 'oklch(0.43 0.17 27)'
|
||||
yellow-300: 'oklch(0.9 0.14 84)'
|
||||
yellow-400: 'oklch(0.85 0.17 84)'
|
||||
yellow-800: 'oklch(0.5 0.1 84)'
|
||||
green-400: 'oklch(0.81 0.16 148)'
|
||||
green-450: 'oklch(0.756 0.197 147)'
|
||||
green-500: 'oklch(0.73 0.2 148)'
|
||||
green-550: 'oklch(0.669 0.197 147)'
|
||||
green-650: 'oklch(0.52 0.17 147)'
|
||||
green-800: 'oklch(0.45 0.14 148)'
|
||||
amber-250: 'oklch(0.842 0.165 84)'
|
||||
amber-400: 'oklch(0.752 0.157 78)'
|
||||
amber-650: 'oklch(0.547 0.116 74)'
|
||||
blue-400: 'oklch(0.7 0.163 255)'
|
||||
blue-450: 'oklch(0.67 0.173 256)'
|
||||
blue-500: 'oklch(0.62 0.15 255)'
|
||||
blue-550: 'oklch(0.587 0.177 256)'
|
||||
blue-650: 'oklch(0.535 0.177 256)'
|
||||
blue-800: 'oklch(0.42 0.11 255)'
|
||||
white-a2: 'oklch(1 0 0 / 0.02)'
|
||||
white-a4: 'oklch(1 0 0 / 0.04)'
|
||||
white-a6: 'oklch(1 0 0 / 0.06)'
|
||||
@@ -75,7 +61,6 @@ colors:
|
||||
white-a18: 'oklch(1 0 0 / 0.18)'
|
||||
white-a20: 'oklch(1 0 0 / 0.2)'
|
||||
white-a30: 'oklch(1 0 0 / 0.3)'
|
||||
white-a40: 'oklch(1 0 0 / 0.4)'
|
||||
white-a50: 'oklch(1 0 0 / 0.5)'
|
||||
white-a85: 'oklch(1 0 0 / 0.85)'
|
||||
black-a3: 'oklch(0 0 0 / 0.03)'
|
||||
@@ -83,15 +68,8 @@ colors:
|
||||
black-a5: 'oklch(0 0 0 / 0.05)'
|
||||
black-a6: 'oklch(0 0 0 / 0.06)'
|
||||
black-a8: 'oklch(0 0 0 / 0.08)'
|
||||
black-a10: 'oklch(0 0 0 / 0.1)'
|
||||
black-a12: 'oklch(0 0 0 / 0.12)'
|
||||
black-a18: 'oklch(0 0 0 / 0.18)'
|
||||
black-a25: 'oklch(0 0 0 / 0.25)'
|
||||
black-a30: 'oklch(0 0 0 / 0.3)'
|
||||
black-a35: 'oklch(0 0 0 / 0.35)'
|
||||
black-a40: 'oklch(0 0 0 / 0.4)'
|
||||
black-a55: 'oklch(0 0 0 / 0.55)'
|
||||
black-a60: 'oklch(0 0 0 / 0.6)'
|
||||
surface-page: '{colors.neutral-25}'
|
||||
surface-muted: '{colors.neutral-100}'
|
||||
surface-emphasis: '{colors.neutral-150}'
|
||||
@@ -103,6 +81,7 @@ colors:
|
||||
surface-code: '{colors.neutral-100}'
|
||||
surface-overlay: '{colors.black-a40}'
|
||||
fg-default: '{colors.neutral-950}'
|
||||
fg-soft: 'color-mix(in oklch, {colors.fg-default} 70%, transparent)'
|
||||
fg-muted: '{colors.neutral-500}'
|
||||
fg-on-action: '{colors.neutral-50}'
|
||||
fg-on-danger: '{colors.neutral-0}'
|
||||
@@ -128,39 +107,21 @@ colors:
|
||||
line-warning-soft: 'color-mix(in oklab, {colors.fill-warning} 34%, {colors.line-default})'
|
||||
line-danger-soft: 'color-mix(in oklab, {colors.fill-danger} 34%, {colors.line-default})'
|
||||
line-info-soft: 'color-mix(in oklab, {colors.fill-info} 34%, {colors.line-default})'
|
||||
edge-rest-side: '{colors.cool-gray-200}'
|
||||
edge-rest-mid: '{colors.cool-gray-100}'
|
||||
edge-focus-side: '{colors.cool-gray-400}'
|
||||
edge-focus-mid: '{colors.cool-gray-300}'
|
||||
edge-ambient-side: '{colors.cool-gray-100}'
|
||||
edge-ambient-mid: '{colors.cool-gray-50}'
|
||||
edge-faint: '{colors.cool-gray-100}'
|
||||
edge-rest: '{colors.cool-gray-200}'
|
||||
edge-focus: '{colors.cool-gray-400}'
|
||||
edge-ambient: '{colors.cool-gray-100}'
|
||||
edge-raised: '{colors.cool-gray-200}'
|
||||
action-primary: '{colors.neutral-900}'
|
||||
action-primary-hover: 'oklch(0.205 0 0 / 0.9)'
|
||||
action-primary-hover: 'color-mix(in oklch, {colors.action-primary} 90%, transparent)'
|
||||
action-danger: '{colors.fill-danger}'
|
||||
action-danger-hover: 'color-mix(in oklch, {colors.fill-danger} 90%, transparent)'
|
||||
action-danger-hover: 'color-mix(in oklch, {colors.action-danger} 90%, transparent)'
|
||||
action-quiet: 'oklch(0.97 0 0 / 0.3)'
|
||||
action-quiet-hover: '{colors.neutral-100}'
|
||||
action-ghost-hover: 'oklch(0.556 0 0 / 0.1)'
|
||||
field-background: '{colors.neutral-0}'
|
||||
field-shade: '{colors.black-a6}'
|
||||
status-danger: '{colors.fill-danger}'
|
||||
status-danger-rim: '{colors.red-400}'
|
||||
status-danger-glyph: '{colors.red-800}'
|
||||
status-warning: '{colors.fill-warning}'
|
||||
status-warning-rim: '{colors.yellow-300}'
|
||||
status-warning-glyph: '{colors.yellow-800}'
|
||||
status-success: '{colors.fill-success}'
|
||||
status-success-rim: '{colors.green-400}'
|
||||
status-success-glyph: '{colors.green-800}'
|
||||
status-info: '{colors.fill-info}'
|
||||
status-info-rim: '{colors.blue-400}'
|
||||
status-info-glyph: '{colors.blue-800}'
|
||||
highlight-inner: '{colors.white-a50}'
|
||||
highlight-inverse: '{colors.white-a12}'
|
||||
sheen-start: '{colors.white-a20}'
|
||||
sheen-end: 'transparent'
|
||||
elevation-ring: '{colors.black-a5}'
|
||||
surface-page-matte: '{colors.neutral-0}'
|
||||
surface-glass-matte: 'oklch(0.97 0 0 / 0.6)'
|
||||
@@ -180,13 +141,14 @@ colors:
|
||||
surface-glass-dark: 'oklch(0.269 0 0 / 0.75)'
|
||||
surface-code-dark: '{colors.neutral-900}'
|
||||
fg-default-dark: '{colors.neutral-50}'
|
||||
fg-soft-dark: 'color-mix(in oklch, {colors.fg-default-dark} 70%, transparent)'
|
||||
fg-muted-dark: '{colors.neutral-400}'
|
||||
fg-on-action-dark: '{colors.neutral-900}'
|
||||
fg-code-dark: '{colors.neutral-300}'
|
||||
fg-danger-dark: '{colors.red-450}'
|
||||
fg-success-dark: '{colors.green-450}'
|
||||
fg-warning-dark: '{colors.amber-250}'
|
||||
fg-info-dark: '{colors.blue-400}'
|
||||
fg-danger-dark: '{colors.fill-danger-dark}'
|
||||
fg-success-dark: '{colors.fill-success-dark}'
|
||||
fg-warning-dark: '{colors.fill-warning-dark}'
|
||||
fg-info-dark: '{colors.fill-info-dark}'
|
||||
line-default-dark: '{colors.white-a30}'
|
||||
line-field-dark: '{colors.white-a30}'
|
||||
line-control-dark: '{colors.white-a12}'
|
||||
@@ -204,27 +166,18 @@ colors:
|
||||
line-warning-soft-dark: 'color-mix(in oklab, {colors.fill-warning-dark} 38%, {colors.line-default-dark})'
|
||||
line-danger-soft-dark: 'color-mix(in oklab, {colors.fill-danger-dark} 38%, {colors.line-default-dark})'
|
||||
line-info-soft-dark: 'color-mix(in oklab, {colors.fill-info-dark} 38%, {colors.line-default-dark})'
|
||||
edge-rest-side-dark: '{colors.white-a6}'
|
||||
edge-rest-mid-dark: '{colors.white-a4}'
|
||||
edge-focus-side-dark: '{colors.white-a18}'
|
||||
edge-focus-mid-dark: '{colors.white-a12}'
|
||||
edge-ambient-side-dark: '{colors.white-a4}'
|
||||
edge-ambient-mid-dark: '{colors.white-a2}'
|
||||
edge-faint-dark: '{colors.white-a4}'
|
||||
edge-rest-dark: '{colors.white-a6}'
|
||||
edge-focus-dark: '{colors.white-a18}'
|
||||
edge-ambient-dark: '{colors.white-a4}'
|
||||
edge-raised-dark: '{colors.white-a9}'
|
||||
action-primary-dark: '{colors.neutral-200}'
|
||||
action-primary-hover-dark: 'oklch(0.922 0 0 / 0.9)'
|
||||
action-primary-hover-dark: 'color-mix(in oklch, {colors.action-primary-dark} 90%, transparent)'
|
||||
action-danger-dark: 'color-mix(in oklch, {colors.fill-danger-dark} 58%, transparent)'
|
||||
action-danger-hover-dark: 'color-mix(in oklch, {colors.fill-danger-dark} 68%, transparent)'
|
||||
action-quiet-dark: 'oklch(0.708 0 0 / 0.15)'
|
||||
action-quiet-hover-dark: 'oklch(0.708 0 0 / 0.25)'
|
||||
action-ghost-hover-dark: 'oklch(0.708 0 0 / 0.1)'
|
||||
field-background-dark: '{colors.white-a9}'
|
||||
field-shade-dark: '{colors.black-a30}'
|
||||
status-danger-dark: '{colors.fill-danger-dark}'
|
||||
status-warning-dark: '{colors.fill-warning-dark}'
|
||||
status-success-dark: '{colors.fill-success-dark}'
|
||||
status-info-dark: '{colors.fill-info-dark}'
|
||||
highlight-inner-dark: '{colors.white-a4}'
|
||||
sheen-start-dark: '{colors.white-a2}'
|
||||
elevation-ring-dark: '{colors.white-a18}'
|
||||
@@ -254,6 +207,11 @@ typography:
|
||||
fontSize: 0.75rem
|
||||
fontWeight: 400
|
||||
lineHeight: 1rem
|
||||
caption-sm:
|
||||
fontFamily: 'Llama Sans'
|
||||
fontSize: 0.625rem
|
||||
fontWeight: 400
|
||||
lineHeight: 0.875rem
|
||||
title:
|
||||
fontFamily: 'Llama Sans'
|
||||
fontSize: 1.125rem
|
||||
@@ -264,18 +222,24 @@ typography:
|
||||
fontSize: 1.5rem
|
||||
fontWeight: 600
|
||||
lineHeight: 2rem
|
||||
display:
|
||||
fontFamily: 'Llama Sans'
|
||||
fontSize: 1.875rem
|
||||
fontWeight: 600
|
||||
lineHeight: 2.25rem
|
||||
code:
|
||||
fontFamily: 'Llama Mono'
|
||||
fontSize: 0.875rem
|
||||
fontWeight: 400
|
||||
lineHeight: 1.25rem
|
||||
rounded:
|
||||
control: 0.5rem
|
||||
panel: 0.625rem
|
||||
card: 0.875rem
|
||||
container: 1rem
|
||||
surface: 1.5rem
|
||||
surface-lg: 2rem
|
||||
sm: 6px
|
||||
md: 8px
|
||||
lg: 10px
|
||||
xl: 14px
|
||||
2xl: 16px
|
||||
3xl: 24px
|
||||
4xl: 32px
|
||||
full: 9999px
|
||||
spacing:
|
||||
xs: 4px
|
||||
@@ -288,7 +252,7 @@ components:
|
||||
chat-form:
|
||||
backgroundColor: '#f9f9f9'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.surface}'
|
||||
rounded: '{rounded.3xl}'
|
||||
typography: '{typography.body}'
|
||||
chat-form-dark:
|
||||
backgroundColor: '#202020'
|
||||
@@ -298,47 +262,47 @@ components:
|
||||
chat-form-placeholder-dark:
|
||||
textColor: '{colors.fg-muted-dark}'
|
||||
chat-form-edge:
|
||||
backgroundColor: '{colors.edge-rest-side}'
|
||||
backgroundColor: '{colors.edge-rest}'
|
||||
chat-form-edge-dark:
|
||||
backgroundColor: '{colors.edge-rest-side-dark}'
|
||||
backgroundColor: '{colors.edge-rest-dark}'
|
||||
chat-form-edge-focus:
|
||||
backgroundColor: '{colors.edge-focus-side}'
|
||||
backgroundColor: '{colors.edge-focus}'
|
||||
chat-form-edge-focus-dark:
|
||||
backgroundColor: '{colors.edge-focus-side-dark}'
|
||||
backgroundColor: '{colors.edge-focus-dark}'
|
||||
card:
|
||||
backgroundColor: '#f9f9f9'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.card}'
|
||||
rounded: '{rounded.xl}'
|
||||
padding: '24px'
|
||||
card-dark:
|
||||
backgroundColor: '#202020'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
card-edge:
|
||||
backgroundColor: '{colors.edge-rest-side}'
|
||||
backgroundColor: '{colors.edge-rest}'
|
||||
card-edge-dark:
|
||||
backgroundColor: '{colors.edge-rest-side-dark}'
|
||||
backgroundColor: '{colors.edge-rest-dark}'
|
||||
sidebar:
|
||||
backgroundColor: '#f9f9f9'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.container}'
|
||||
rounded: '{rounded.2xl}'
|
||||
sidebar-dark:
|
||||
backgroundColor: '#1c1c1c'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
sidebar-edge:
|
||||
backgroundColor: '{colors.edge-ambient-side}'
|
||||
backgroundColor: '{colors.edge-ambient}'
|
||||
sidebar-edge-dark:
|
||||
backgroundColor: '{colors.edge-ambient-side-dark}'
|
||||
backgroundColor: '{colors.edge-ambient-dark}'
|
||||
inset-group:
|
||||
backgroundColor: 'oklch(1 0 0 / 0.85)'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.card}'
|
||||
rounded: '{rounded.xl}'
|
||||
inset-group-dark:
|
||||
backgroundColor: 'oklch(0.985 0 0 / 0.03)'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
inset-group-edge:
|
||||
backgroundColor: '{colors.edge-ambient-side}'
|
||||
backgroundColor: '{colors.edge-ambient}'
|
||||
inset-group-edge-dark:
|
||||
backgroundColor: '{colors.edge-ambient-side-dark}'
|
||||
backgroundColor: '{colors.edge-ambient-dark}'
|
||||
selected-row:
|
||||
backgroundColor: 'oklch(0.145 0 0 / 0.05)'
|
||||
textColor: '{colors.fg-default}'
|
||||
@@ -348,19 +312,19 @@ components:
|
||||
user-bubble:
|
||||
backgroundColor: '#f3f3f3'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.surface}'
|
||||
rounded: '{rounded.2xl}'
|
||||
typography: '{typography.body}'
|
||||
user-bubble-dark:
|
||||
backgroundColor: '#181818'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
user-bubble-edge:
|
||||
backgroundColor: '{colors.edge-faint}'
|
||||
backgroundColor: '{colors.edge-ambient}'
|
||||
user-bubble-edge-dark:
|
||||
backgroundColor: '{colors.edge-faint-dark}'
|
||||
backgroundColor: '{colors.edge-ambient-dark}'
|
||||
floating-panel:
|
||||
backgroundColor: '#ffffff'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.panel}'
|
||||
rounded: '{rounded.lg}'
|
||||
typography: '{typography.body-sm}'
|
||||
floating-panel-dark:
|
||||
backgroundColor: '#161616'
|
||||
@@ -376,14 +340,14 @@ components:
|
||||
dialog:
|
||||
backgroundColor: '#ffffff'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.panel}'
|
||||
rounded: '{rounded.lg}'
|
||||
dialog-dark:
|
||||
backgroundColor: '#0d0d0d'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
tooltip:
|
||||
backgroundColor: '{colors.action-primary}'
|
||||
textColor: '{colors.fg-on-action}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.caption}'
|
||||
tooltip-dark:
|
||||
backgroundColor: '{colors.action-primary-dark}'
|
||||
@@ -391,7 +355,7 @@ components:
|
||||
button-primary:
|
||||
backgroundColor: '{colors.action-primary}'
|
||||
textColor: '{colors.fg-on-action}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label}'
|
||||
height: '36px'
|
||||
button-primary-dark:
|
||||
@@ -406,7 +370,7 @@ components:
|
||||
button-secondary:
|
||||
backgroundColor: '#f9f9f9'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label}'
|
||||
height: '36px'
|
||||
button-secondary-dark:
|
||||
@@ -425,7 +389,7 @@ components:
|
||||
button-tertiary:
|
||||
backgroundColor: '#fcfcfc'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label}'
|
||||
height: '36px'
|
||||
button-tertiary-dark:
|
||||
@@ -444,7 +408,7 @@ components:
|
||||
button-outline:
|
||||
backgroundColor: '{colors.field-background}'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label}'
|
||||
height: '36px'
|
||||
button-outline-dark:
|
||||
@@ -462,7 +426,7 @@ components:
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
button-ghost:
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label}'
|
||||
button-ghost-dark:
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
@@ -475,7 +439,7 @@ components:
|
||||
button-destructive:
|
||||
backgroundColor: '{colors.action-danger}'
|
||||
textColor: '{colors.fg-on-danger}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label}'
|
||||
height: '36px'
|
||||
button-destructive-dark:
|
||||
@@ -490,7 +454,7 @@ components:
|
||||
toggle-on:
|
||||
backgroundColor: '{colors.surface-selected}'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label}'
|
||||
height: '36px'
|
||||
toggle-on-dark:
|
||||
@@ -505,7 +469,7 @@ components:
|
||||
toggle-group:
|
||||
backgroundColor: '#f9f9f9'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label}'
|
||||
height: '32px'
|
||||
toggle-group-dark:
|
||||
@@ -533,7 +497,7 @@ components:
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
tabs-list:
|
||||
backgroundColor: '{colors.surface-muted}'
|
||||
rounded: '{rounded.panel}'
|
||||
rounded: '{rounded.lg}'
|
||||
height: '36px'
|
||||
padding: '2px'
|
||||
tabs-list-dark:
|
||||
@@ -541,7 +505,7 @@ components:
|
||||
tabs-trigger:
|
||||
backgroundColor: '{colors.surface-muted}'
|
||||
textColor: 'oklch(0.145 0 0 / 0.7)'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label}'
|
||||
tabs-trigger-dark:
|
||||
backgroundColor: '{colors.surface-muted-dark}'
|
||||
@@ -582,7 +546,7 @@ components:
|
||||
input:
|
||||
backgroundColor: '{colors.field-background}'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.body-sm}'
|
||||
height: '36px'
|
||||
input-dark:
|
||||
@@ -607,7 +571,7 @@ components:
|
||||
badge-default:
|
||||
backgroundColor: '{colors.action-primary}'
|
||||
textColor: '{colors.fg-on-action}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label-sm}'
|
||||
padding: '2px 8px'
|
||||
badge-default-dark:
|
||||
@@ -616,14 +580,14 @@ components:
|
||||
badge-secondary:
|
||||
backgroundColor: '#dadada'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label-sm}'
|
||||
badge-secondary-dark:
|
||||
backgroundColor: '#252525'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
badge-outline:
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label-sm}'
|
||||
badge-outline-dark:
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
@@ -634,7 +598,7 @@ components:
|
||||
badge-destructive:
|
||||
backgroundColor: '{colors.action-danger}'
|
||||
textColor: '{colors.fg-on-danger}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label-sm}'
|
||||
badge-destructive-dark:
|
||||
backgroundColor: '#952420'
|
||||
@@ -642,7 +606,7 @@ components:
|
||||
badge-success:
|
||||
backgroundColor: '{colors.surface-success}'
|
||||
textColor: '{colors.fg-success}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label-sm}'
|
||||
badge-success-dark:
|
||||
backgroundColor: '{colors.surface-success-dark}'
|
||||
@@ -650,7 +614,7 @@ components:
|
||||
badge-warning:
|
||||
backgroundColor: '{colors.surface-warning}'
|
||||
textColor: '{colors.fg-warning}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label-sm}'
|
||||
badge-warning-dark:
|
||||
backgroundColor: '{colors.surface-warning-dark}'
|
||||
@@ -658,7 +622,7 @@ components:
|
||||
badge-danger:
|
||||
backgroundColor: '{colors.surface-danger}'
|
||||
textColor: '{colors.fg-danger}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label-sm}'
|
||||
badge-danger-dark:
|
||||
backgroundColor: '{colors.surface-danger-dark}'
|
||||
@@ -666,7 +630,7 @@ components:
|
||||
badge-info:
|
||||
backgroundColor: '{colors.surface-info}'
|
||||
textColor: '{colors.fg-info}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
typography: '{typography.label-sm}'
|
||||
badge-info-dark:
|
||||
backgroundColor: '{colors.surface-info-dark}'
|
||||
@@ -674,7 +638,7 @@ components:
|
||||
code-block:
|
||||
backgroundColor: '{colors.surface-code}'
|
||||
textColor: '{colors.fg-code}'
|
||||
rounded: '{rounded.panel}'
|
||||
rounded: '{rounded.lg}'
|
||||
typography: '{typography.code}'
|
||||
code-block-dark:
|
||||
backgroundColor: '{colors.surface-code-dark}'
|
||||
@@ -684,21 +648,21 @@ components:
|
||||
list-row-selected:
|
||||
backgroundColor: '{colors.surface-selected}'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
list-row-selected-dark:
|
||||
backgroundColor: '{colors.surface-selected-dark}'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
panel-muted:
|
||||
backgroundColor: '{colors.surface-muted}'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.panel}'
|
||||
rounded: '{rounded.lg}'
|
||||
panel-muted-dark:
|
||||
backgroundColor: '{colors.surface-muted-dark}'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
chip-emphasis:
|
||||
backgroundColor: '{colors.surface-emphasis}'
|
||||
textColor: '{colors.fg-default}'
|
||||
rounded: '{rounded.control}'
|
||||
rounded: '{rounded.md}'
|
||||
chip-emphasis-dark:
|
||||
backgroundColor: '{colors.surface-emphasis-dark}'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
@@ -708,22 +672,6 @@ components:
|
||||
page-dark:
|
||||
backgroundColor: '{colors.surface-page-dark}'
|
||||
textColor: '{colors.fg-default-dark}'
|
||||
chat-form-edge-mid:
|
||||
backgroundColor: '{colors.edge-rest-mid}'
|
||||
chat-form-edge-mid-dark:
|
||||
backgroundColor: '{colors.edge-rest-mid-dark}'
|
||||
chat-form-edge-mid-focus:
|
||||
backgroundColor: '{colors.edge-focus-mid}'
|
||||
chat-form-edge-mid-focus-dark:
|
||||
backgroundColor: '{colors.edge-focus-mid-dark}'
|
||||
sidebar-edge-mid:
|
||||
backgroundColor: '{colors.edge-ambient-mid}'
|
||||
sidebar-edge-mid-dark:
|
||||
backgroundColor: '{colors.edge-ambient-mid-dark}'
|
||||
inset-group-edge-mid:
|
||||
backgroundColor: '{colors.edge-ambient-mid}'
|
||||
inset-group-edge-mid-dark:
|
||||
backgroundColor: '{colors.edge-ambient-mid-dark}'
|
||||
glass-highlight:
|
||||
backgroundColor: '{colors.highlight-inner}'
|
||||
glass-highlight-dark:
|
||||
@@ -734,33 +682,61 @@ components:
|
||||
backgroundColor: '{colors.sheen-start}'
|
||||
user-bubble-sheen-dark:
|
||||
backgroundColor: '{colors.sheen-start-dark}'
|
||||
field-shade:
|
||||
backgroundColor: '{colors.field-shade}'
|
||||
field-shade-dark:
|
||||
backgroundColor: '{colors.field-shade-dark}'
|
||||
status-lamp-danger-rim:
|
||||
backgroundColor: '{colors.status-danger-rim}'
|
||||
status-lamp-warning-rim:
|
||||
backgroundColor: '{colors.status-warning-rim}'
|
||||
status-lamp-success-rim:
|
||||
backgroundColor: '{colors.status-success-rim}'
|
||||
status-lamp-danger:
|
||||
backgroundColor: '{colors.status-danger}'
|
||||
textColor: '{colors.status-danger-glyph}'
|
||||
backgroundColor: '{colors.fill-danger}'
|
||||
rounded: '{rounded.full}'
|
||||
size: '8px'
|
||||
status-lamp-warning:
|
||||
backgroundColor: '{colors.status-warning}'
|
||||
textColor: '{colors.status-warning-glyph}'
|
||||
backgroundColor: '{colors.fill-warning}'
|
||||
rounded: '{rounded.full}'
|
||||
size: '8px'
|
||||
status-lamp-success:
|
||||
backgroundColor: '{colors.status-success}'
|
||||
textColor: '{colors.status-success-glyph}'
|
||||
backgroundColor: '{colors.fill-success}'
|
||||
rounded: '{rounded.full}'
|
||||
size: '8px'
|
||||
---
|
||||
|
||||
## In short
|
||||
|
||||
The rules most changes need. The sections below hold the detail and the reasons, and they
|
||||
win where this list is too short. Before adding a token, a size or a component, use what is
|
||||
here; if something really is missing, add it here first.
|
||||
|
||||
- **Components:** take base components from Llama UI (`@ggml-org/llama-ui/ui/<name>`); do not
|
||||
build a new one when an existing one fits. Style them through their variants
|
||||
(`variant="outline"`, `size="sm"`), not by overriding classes.
|
||||
- **Colour:** greys build the UI; colour is for meaning only (status, destructive actions,
|
||||
focus). Neutral colours go by shadcn's utility names (`bg-background`, `bg-muted`, `bg-card`,
|
||||
`text-foreground`, `text-muted-foreground`, `border-border`), status by `bg-surface-*`,
|
||||
`bg-fill-*`, `text-fg-*` and `border-line-*-soft` of `success`, `warning`, `danger` and
|
||||
`info`, and any other semantic token as `bg-(--surface-lifted)`. In CSS, read the semantic
|
||||
token (`var(--surface-page)`). No Tailwind palette classes, no hex.
|
||||
- **Type:** Llama Sans, and Llama Mono for code, through roles: `text-body` (16px) for chat
|
||||
messages and the chat input, `text-body-sm` (14px) for most text, `text-label` (14px, medium)
|
||||
for buttons and labels, `text-label-sm` and `text-caption` (12px) for badges and hints,
|
||||
`text-caption-sm` (10px) for tags and counts, `text-title` (18px) and `text-heading` (24px)
|
||||
for the rare heading, `text-display` (30px) for the biggest headline. Never Tailwind's own sizes (`text-sm`, `text-xs`) or a size in
|
||||
brackets.
|
||||
- **Shape:** one corner scale, `rounded-sm` to `rounded-4xl`: `rounded-md` (8px) for controls,
|
||||
fields and badges, `rounded-lg` (10px) for menus and dialogs, `rounded-xl` (14px) for cards,
|
||||
`rounded-2xl` (16px) and `rounded-3xl` (24px) for the larger surfaces, `rounded-full` for
|
||||
pills, avatars and lamps.
|
||||
- **Sizes:** Tailwind's 4px spacing scale. Icons are Lucide, `size-icon-md` (16px), or
|
||||
`size-icon-sm` (14px) in compact controls. Controls are `h-control-sm`, `h-control-md` or
|
||||
`h-control-lg` (32, 36, 40px).
|
||||
- **Surfaces:** one surface utility per element (`card-surface`, `matte-float`, `matte-key`,
|
||||
`matte-well`), never raw `shadow-*`, `border-*` and `backdrop-blur-*` combinations.
|
||||
- **Tokens:** read a semantic token directly. A component token is only for a value the
|
||||
component decides itself. A value that follows from another token is mixed from it, not
|
||||
picked again.
|
||||
- **No arbitrary values** (`text-[11px]`, `rounded-[1.125rem]`, `p-[7px]`, `z-[20]`): pick the
|
||||
nearest from the scale (`z-20`, `max-w-4/5`, `min-w-32`). Brackets are for what no scale can
|
||||
hold: a `calc()`, a grid template, a list of transition properties.
|
||||
- **Motion:** `ease-out-quint` for what enters or answers a press, `ease-sheet` for a sheet
|
||||
or a page that slides.
|
||||
- **Phones:** every dialog is full screen; only alerts stay small and centred.
|
||||
- **The conversation is the loudest thing on screen;** everything around it stays quiet.
|
||||
|
||||
## Overview
|
||||
|
||||
**Llama UI** is the design system and component library this file describes. **Llama Chat**,
|
||||
@@ -793,7 +769,7 @@ This file is the how, written for agents first. Its principles, as rules to appl
|
||||
- **Colour has one job.** Greys build everything; status colours show status and nothing else;
|
||||
art colours and cinder are for artwork and the odd brand detail, never for the UI's controls.
|
||||
- **Recognisable, easy to change.** Keep the character in the icon, the type and one
|
||||
accent, so an app built on Llama UI can restyle it through component tokens alone.
|
||||
accent, so an app built on Llama UI can restyle it through semantic and component tokens alone.
|
||||
- **Design lives in code.** The CSS is the source of truth; prefer what is generated or
|
||||
derived over hand-tuned values, and record the reason next to the value. Content pages are
|
||||
Markdown with Svelte components in them, as `.svx` (see `AGENTS.md`).
|
||||
@@ -802,18 +778,35 @@ This file is the how, written for agents first. Its principles, as rules to appl
|
||||
|
||||
Design tokens come in three tiers, each in its own file under `ui/lib/ui/src/lib/styles/tokens/`:
|
||||
|
||||
1. **Primitives** (`primitives.css`): raw values named by what they are, such as
|
||||
`neutral-900`, `cool-gray-200`, `red-500`, `white-a30`, `font-size-14` or `length-24`.
|
||||
Only semantic tokens point at them.
|
||||
1. **Primitives** (`primitives.css`): raw colours named by what they are, such as
|
||||
`neutral-900`, `cool-gray-200`, `red-550` or `white-a30`. Only semantic tokens point at
|
||||
them. Sizes are not primitives: a role holds its own value, and spacing is Tailwind's 4px
|
||||
grid.
|
||||
2. **Semantic tokens** (`semantic.css`): named by purpose, such as `surface-glass`,
|
||||
`fg-muted`, `line-field`, `edge-focus-side`, `action-primary` or `status-warning`. They
|
||||
point at primitives and are the only tier that changes between light and dark. The type,
|
||||
corner, icon size and control height roles live here too and are Tailwind utilities:
|
||||
`text-label`, `rounded-control`, `size-icon-md`, `h-control-md`.
|
||||
3. **Component tokens** (`components.css`): one group per component, named
|
||||
`[component]-[variant]-[property]-[state]`, such as `chat-form-edge-side-focus` or
|
||||
`button-secondary-background-hover`. They point at semantic tokens, and components read
|
||||
them as `bg-(--button-primary-background)` and similar.
|
||||
`fg-muted`, `line-field`, `edge-focus`, `action-primary` or `fill-warning`, and the only
|
||||
tier that changes between light and dark. Each is either a pick, which names a primitive
|
||||
per theme, or a derivation, which is mixed from another semantic token by a fixed rule and
|
||||
so follows it through every theme with a single declaration:
|
||||
- soft text is the text colour at 70% (`fg-soft`);
|
||||
- a hover fill is the fill at 90% (`action-primary-hover`);
|
||||
- a status surface is its fill mixed into the page, and a status line its fill mixed into
|
||||
the default line, by a share the theme sets (11% and 34% in light, 16% and 38% in dark);
|
||||
- a dark shadow is the light one, `elevation-strength` (1 in light, 5 in dark) times as
|
||||
dense;
|
||||
- the middle of a matte edge is its side at two thirds, and a lamp's rim and glyph are
|
||||
its fill mixed 30% towards white and towards black (both in `surfaces.css`).
|
||||
|
||||
The type, icon size and control height roles live here too and are Tailwind utilities:
|
||||
`text-label`, `size-icon-md`, `h-control-md`. Corners are Tailwind's own `rounded-sm` to
|
||||
`rounded-4xl`, computed from `--radius` in `theme.css`. shadcn's
|
||||
colour names (`background`, `muted-foreground`, `border` ...) exist as Tailwind utilities
|
||||
only, each mapped to a semantic token in `theme.css`.
|
||||
|
||||
3. **Component tokens** (`components.css`): only what a component decides itself, named
|
||||
`[component]-[variant]-[property]-[state]`, such as `button-secondary-background-hover` or
|
||||
`float-panel-background-modal`: a value no semantic token has, or one that only this
|
||||
component changes between themes. A component that takes a semantic token as it is reads
|
||||
the semantic token, as `bg-(--action-primary)` and similar, and gets no alias here.
|
||||
|
||||
The front matter's `colors`, `typography` and `rounded` are generated from the primitives, the
|
||||
semantic tokens and the font stacks by `npm run design:tokens` in `ui/apps/chat`, and CI fails
|
||||
@@ -860,16 +853,18 @@ the Surface switch in Storybook's toolbar, and only its surface tokens differ: `
|
||||
`surface-raised` for menus and dialogs, `surface-lifted` for a selection raised on a
|
||||
recessed track, `surface-pressed` for a key pressed in, `surface-glass` for the translucent matte fill, `surface-code` for code and
|
||||
`surface-overlay` behind dialogs.
|
||||
- **Foreground:** `fg-default` and `fg-muted` for text and icons, `fg-on-action` and
|
||||
- **Foreground:** `fg-default` and `fg-muted` for text and icons, `fg-soft` (the text colour
|
||||
at 70%) for the label of an option that is not the picked one, `fg-on-action` and
|
||||
`fg-on-danger` on filled buttons, `fg-code` for code, `fg-danger` for errors,
|
||||
`fg-success` for confirmations such as a copied check, `fg-warning` for cautions and
|
||||
`fg-info` for neutral notices.
|
||||
- **Lines:** `line-default` for dividers, `line-control` for outlined controls (soft in dark
|
||||
mode), `line-field` for inputs, `line-focus` for focus and `line-danger` for invalid fields.
|
||||
- **Edges:** the hairlines of matte surfaces, darker at the sides than in the middle.
|
||||
`edge-rest-*` at rest, `edge-focus-*` when focus is inside, `edge-ambient-*` for large
|
||||
quiet containers whose edge never changes, `edge-faint` for the user bubble and
|
||||
`edge-raised` for floating panels.
|
||||
- **Edges:** the hairlines of matte surfaces, darker at the sides than in the middle (the
|
||||
token is the side; the surface fades it to two thirds in the middle). `edge-rest` at rest,
|
||||
`edge-focus` when focus is inside, `edge-ambient` for large quiet containers whose edge
|
||||
never changes and, kept even all round, for the user bubble, and `edge-raised` for floating
|
||||
panels.
|
||||
- **Actions:** `action-primary` (near black in light mode, near white in dark mode) and its
|
||||
hover, `action-danger` and its hover, and `action-ghost-hover`.
|
||||
- **Status fills:** `fill-success`, `fill-warning`, `fill-danger` and `fill-info` are each
|
||||
@@ -880,9 +875,9 @@ the Surface switch in Storybook's toolbar, and only its surface tokens differ: `
|
||||
`surface-info` are soft tints of each status fill for alerts and soft badges, with
|
||||
`line-*-soft` hairlines to match. They are mixed in oklab so the hue holds over the page.
|
||||
Soft status badges are pills with a small dot in the status fill before the label.
|
||||
- **Status:** `status-danger`, `status-warning`, `status-success` and `status-info` are the
|
||||
lamp fills for error or stopped, loading or warning, ready or connected, and informational. They take the status
|
||||
fills, and each has a lighter `-rim` and a darker `-glyph`. Known gap: the glyph on the red lamp
|
||||
- **Status:** `fill-danger`, `fill-warning`, `fill-success` and `fill-info` are the
|
||||
lamp fills for error or stopped, loading or warning, ready or connected, and informational. A lamp adds
|
||||
a lighter rim and a darker glyph, both mixed from its fill. Known gap: the glyph on the red lamp
|
||||
reaches only about 2:1 and on the green lamp about 3.2:1, below WCAG AA, so the lamp colour
|
||||
must never be the only signal; pair it with a label or tooltip.
|
||||
|
||||
@@ -895,14 +890,21 @@ is one variable font with an optical size axis: the browser sets it from the fon
|
||||
looser Small one, with a blend in between. Nothing needs choosing per element; pin a point only to
|
||||
show it, with `font-variation-settings: 'opsz' 16` or `36`. Its line box is 1.25 at every size, centred on the
|
||||
cap height; large headings set `line-height: 1.15` themselves. Llama Mono keeps every character,
|
||||
its coding ligatures included, in one cell, so code and numbers line up in columns. Type is set through roles that fix size, line height and weight together:
|
||||
its coding ligatures included, in one cell, so code and numbers line up in columns. Type is set through roles that fix size and line height together, and for labels and headings the weight too:
|
||||
|
||||
- `body` (16/24, 400): chat messages and the chat input.
|
||||
- `body-sm` (14/20, 400): most text, fields and lists.
|
||||
- `body` (16/24): chat messages and the chat input.
|
||||
- `body-sm` (14/20): most text, fields and lists.
|
||||
- `label` (14/20, 500): buttons and field labels.
|
||||
- `label-sm` (12/16, 500): badges and compact labels.
|
||||
- `caption` (12/16, 400): tooltips, hints and metadata.
|
||||
- `title` (18/28, 600) and `heading` (24/32, 600): rare headings; there is no display size.
|
||||
- `caption` (12/16): tooltips, hints and metadata.
|
||||
- `caption-sm` (10/14): the smallest text, for tags, compact badges and counts.
|
||||
- `title` (18/28, 600) and `heading` (24/32, 600): rare headings.
|
||||
- `display` (30/36, 600): the biggest headline, such as the greeting on a new chat.
|
||||
|
||||
Body and caption text takes the weight around it, regular unless a parent says otherwise; add
|
||||
a weight class for anything else (`text-body-sm font-semibold`). The roles are the whole
|
||||
scale: no `text-sm` or `text-xs`, and no size in brackets. On a phone a row that needs larger
|
||||
text takes the next role up (`text-body-sm max-md:text-body`).
|
||||
|
||||
When a component lets callers override the size, keep an explicit weight class next to the
|
||||
role (`text-label font-medium`) so a size override does not drop the weight. Placeholders
|
||||
@@ -978,8 +980,8 @@ matches the role of the surface instead of combining raw shadows.
|
||||
- **`matte-float`** and **`matte-float-modal`:** menus, popovers, select lists, hover cards
|
||||
and drawers, and dialogs over the page colour. An 86% opaque panel with blur, a faint edge,
|
||||
a rim and a deeper shadow. The edge is a hairline ring baked into the shadow as its last
|
||||
layer (`float-panel-edge`). The panel's 1px border is its rim, the inner highlight
|
||||
(`float-panel-highlight`) right inside the ring; an inset shadow for the rim would sit inside
|
||||
layer (`edge-raised`). The panel's 1px border is its rim, the inner highlight
|
||||
(`highlight-inner`) right inside the ring; an inset shadow for the rim would sit inside
|
||||
the border instead, and the 1px between the two would draw a double edge. In light mode
|
||||
dialogs are solid white instead: over the dimmed page a translucent white turns grey.
|
||||
- **`matte-key`:** buttons, selects, toggles and tabs. The matte finish: on top of the
|
||||
@@ -991,12 +993,12 @@ matches the role of the surface instead of combining raw shadows.
|
||||
(`--key-sheen-solid`), the same blur, and an even 1px hairline in a shade of the fill drawn
|
||||
inside the button (`--key-edge`), so the width does not change. The danger key stays matte
|
||||
glass rather than metal: its sheen is almost none (`--button-danger-sheen`), and in dark mode
|
||||
it is a frosted, translucent red (`red-500` at 58%) whose edge is a soft tint of the red, never
|
||||
it is a frosted, translucent red (`fill-danger` at 58%) whose edge is a soft tint of the red, never
|
||||
a lighter rim.
|
||||
- **`elevated-control`**, **`elevated-surface`** and **`elevated-raised`:** cards, floating
|
||||
bars and thumbnails. An elevation token with a hairline ring baked in as its last layer, so
|
||||
the edge melts into the shadow and the shadow deepens in dark mode. The ring is
|
||||
`--elevation-ring` (black 5%, white 18% in dark) at `--elevation-ring-width` (1px). They
|
||||
`--elevation-ring` (black 5%, white 18% in dark), 1px wide. They
|
||||
replace a border plus a shadow; never add a border to them.
|
||||
- **`matte-well`:** inputs, textareas and checkboxes. A shallow inset shade so
|
||||
fields read as recessed.
|
||||
@@ -1007,16 +1009,16 @@ matches the role of the surface instead of combining raw shadows.
|
||||
an even hairline, with no glow.
|
||||
|
||||
The elevation tokens are `elevation-surface`, `elevation-control`, `elevation-raised`,
|
||||
`elevation-inset` and `elevation-tooltip`. The drop shadows are smooth stacks: a few soft
|
||||
`elevation-inset` and `elevation-pressed`; a tooltip takes `elevation-surface`. The drop shadows are smooth stacks: a few soft
|
||||
layers instead of one hard one, the closest the darkest and smallest, each further layer about
|
||||
twice the offset and blur and fainter, the far ones pulled in with a negative spread, so the
|
||||
shadow fades out instead of ending in a visible edge. They stay as close as upstream's
|
||||
Tailwind shadows: `elevation-surface` reaches about 20px, like `shadow-lg`, `elevation-raised`
|
||||
about 38px, like `shadow-xl`, and `elevation-control` is three tight layers reaching no further
|
||||
than 4px, so buttons and other controls sit close to the page. Two softer steps sit below them: `elevation-soft` for the chat form,
|
||||
shadow fades out instead of ending in a visible edge. They are the only shadows: Tailwind's
|
||||
own `shadow-sm` to `shadow-2xl` do not follow the theme and are not used. `elevation-surface`
|
||||
reaches about 20px, `elevation-raised` about 38px, and `elevation-control` is three tight
|
||||
layers reaching no further than 4px, so buttons and other controls sit close to the page. Two softer steps sit below them: `elevation-soft` for the chat form,
|
||||
which floats only a little, and `elevation-faint` for the user message bubble, which barely
|
||||
lifts. The keys inside the chat form, the add key and the model selector, take `elevation-key`
|
||||
(`--chat-form-key-shadow`): a 0.5px hairline all round and a 1px drop, since the control elevation's soft
|
||||
lifts. The keys inside the chat form, the add key and the model selector, take `elevation-key`:
|
||||
a 0.5px hairline all round and a 1px drop, since the control elevation's soft
|
||||
spread blends into the white form; in dark it is the control elevation. Dark mode deepens the same stacks. Tailwind's own `shadow-xs` to `shadow-2xl` are
|
||||
built the same way (`tokens/semantic.css`), each reaching about as far as Tailwind's default for
|
||||
it. Every
|
||||
@@ -1025,11 +1027,12 @@ with a 2px blur.
|
||||
|
||||
## Shapes
|
||||
|
||||
Corners are soft and consistent, set through roles: `control` (8px) for buttons, fields and
|
||||
badges, `panel` (10px) for menus and dialogs, `card` (14px) for cards, `container` (16px) for
|
||||
the sidebar, and `surface` (24px) for the chat form and message bubbles, rising to
|
||||
`surface-lg` (32px) for the chat form on small screens. Status lamps, avatars and the round
|
||||
icon buttons in the chat form are fully round.
|
||||
Corners are soft and consistent, on one scale that is computed from a single base radius
|
||||
(`--radius`, 10px, in `theme.css`), so changing the base moves every corner with it: `sm`
|
||||
(6px) for small marks and chips, `md` (8px) for buttons, fields and badges, `lg` (10px) for
|
||||
menus and dialogs, `xl` (14px) for cards, `2xl` (16px) for the sidebar and message bubbles,
|
||||
and `3xl` (24px) for the chat form, rising to `4xl` (32px) for the chat form on small
|
||||
screens. Status lamps, avatars and the round icon buttons in the chat form are fully round.
|
||||
|
||||
## Brand
|
||||
|
||||
@@ -1071,15 +1074,15 @@ icon buttons in the chat form are fully round.
|
||||
- **Toggles:** the same corners, type, heights, padding and icon size as buttons, with
|
||||
square `icon-sm`, `icon` and `icon-lg` sizes for icon-only toggles. `default` has no fill
|
||||
until hovered; `outline` borrows the outline button. Pressed toggles take
|
||||
`toggle-background-on`.
|
||||
`surface-selected`.
|
||||
- **Button groups:** joined buttons share one shadow, drawn by the group, and one border at
|
||||
each seam. A group separator replaces the seam border. Filled buttons draw a seam in their
|
||||
own text colour (`button-primary-seam`, `button-danger-seam`) instead.
|
||||
own text colour at 25% instead.
|
||||
- **Selection on a track:** a choice that moves along a track is a recessed track with the
|
||||
selection raised on it, never a row of outlined buttons. The track is `surface-muted` with
|
||||
the inset shade (`elevation-inset`); the selection is a `surface-lifted` chip with
|
||||
`elevation-control`, and unselected options are softened text with no fill. Tabs use the
|
||||
same track for their list, with the active tab raised (`tabs-*`); a `line` variant
|
||||
`elevation-control`, and unselected options are softened text (`fg-soft`) with no fill. Tabs use the
|
||||
same track for their list, with the active tab raised; a `line` variant
|
||||
underlines the active tab instead. The chip or underline slides between tabs in 300ms on a
|
||||
plain ease-out, with a stretch of at most 5% along the move that is gone by the time it
|
||||
lands; with reduced motion it jumps instead. The switch is the same track with a raised
|
||||
@@ -1095,7 +1098,7 @@ icon buttons in the chat form are fully round.
|
||||
- **Chat form:** one `chat-form-surface` holding the input, attachments and actions. Its fill
|
||||
is the muted grey at 60% in light mode and 75% in dark mode.
|
||||
- **User message bubble:** the primary colour at 5% with `matte-sheen` and the very faint
|
||||
`edge-faint` hairline, so it separates from the page without a visible border.
|
||||
`edge-ambient` hairline, so it separates from the page without a visible border.
|
||||
- **Sidebar:** `sidebar-surface`, the muted fill at 60% with no inner highlight and the
|
||||
ambient edge. On small screens it keeps a plain `shadow-md` instead.
|
||||
- **Inset groups:** `inset-group-surface` gathers rows inside a glass panel, like the
|
||||
@@ -1151,6 +1154,12 @@ icon buttons in the chat form are fully round.
|
||||
(`--sidebar-reveal-x`), taking no taps while the page is aside. The page keeps room under its
|
||||
last row (`max-md:pb-safe-24`) so the key never covers it. One per page, only for its main
|
||||
action; from `md` up the action stays a button in the header.
|
||||
- **Voice clips:** a recorded clip is a round primary play key, its waveform and the time in
|
||||
`caption`: bars in the muted foreground at 40%, the played part in the primary colour, so
|
||||
the clip stays neutral in both modes. The live waveform while recording is as tall as the
|
||||
input's line (24px), the newest level on the right, and holds still with reduced motion. A
|
||||
voice message's transcript opens under the clip on hover, keyboard focus or a tap, and
|
||||
stays in the DOM for screen readers while closed.
|
||||
- **Copy feedback:** a copy action turns its icon into a `fg-success` check for 1.5s
|
||||
(`COPY_FEEDBACK_RESET_MS`), only when the copy succeeded, then back. The icon pops in with a
|
||||
150ms fade and scale, skipped on first render and with reduced motion.
|
||||
@@ -1168,8 +1177,8 @@ icon buttons in the chat form are fully round.
|
||||
lifting the surface.
|
||||
- Do use the status colours only for status. Buttons keep their neutral colours, and the
|
||||
submit button stays black in light mode and white in dark mode.
|
||||
- Do read component tokens in components, semantic tokens in shared styles, and primitives
|
||||
only in semantic tokens.
|
||||
- Do read a semantic token directly wherever a component takes it as it is. Add a component
|
||||
token only for a value the component decides itself, never as an alias of a semantic token.
|
||||
- Do add a new colour as a primitive first, then give it a semantic name before any
|
||||
component uses it.
|
||||
- Do give motion a job: show where something went or what changed, like a selection sliding
|
||||
|
||||
@@ -89,6 +89,7 @@ The app imports the library as `@ggml-org/llama-ui/ui/<name>` and compiles its s
|
||||
| Routes | `src/routes` | `/`, `/chat/[id]`, `/models`, `/mcp-servers`, `/settings`, `/search` |
|
||||
| App components | `src/lib/components/app` | Chat, navigation, models, MCP, settings and dialogs, grouped by area |
|
||||
| UI components | `ui/lib/ui` | shadcn-svelte on bits-ui, from Llama UI |
|
||||
| Voice | `ui/lib/voice` | Microphone capture, transcription and dictation, from Llama Voice (`@ggml-org/llama-voice`) |
|
||||
| Hooks | `src/lib/hooks` | View logic between components and stores: scroll, drag and drop, pickers, keyboard |
|
||||
| Stores | `src/lib/stores` | Application state as Svelte 5 runes: chat, conversations, the agentic loop, tools, models, settings |
|
||||
| Services | `src/lib/services` | Stateless I/O: the llama-server API, IndexedDB, MCP, the Hugging Face Hub, the tool sandbox |
|
||||
|
||||
@@ -115,7 +115,7 @@ Records every `scripts/docs/*.demo.ts` from the storage target and uploads `vide
|
||||
|
||||
## Writing a demo
|
||||
|
||||
Scripts get `test` and `expect` from `helpers.ts` without importing them. `demo.click`, `demo.hover` and `demo.type` glide a visible cursor to the target before acting, with timing varied like a person's (seeded per demo, so re-takes match); `demo.scroll` turns the mouse wheel over a target; `demo.zoom` pinches in on a control or a point to show a detail too small to read in the frame, holds, and pinches back out (with the fingertips drawn on a touch device); `demo.caption` shows a caption at the top of the frame. Use `test.use({ settings, startPath })` to seed other settings or start on another route.
|
||||
Scripts get `test` and `expect` from `helpers.ts` without importing them. `demo.click`, `demo.hover` and `demo.type` glide a visible cursor to the target before acting, with timing varied like a person's (seeded per demo, so re-takes match); `demo.scroll` turns the mouse wheel over a target; `demo.zoom` pinches in on a control or a point to show a detail too small to read in the frame, holds, and pinches back out (with the fingertips drawn on a touch device); `demo.caption` shows a caption at the top of the frame. For voice input, `demo.microphone()` gives the page a microphone that hears nothing but `demo.speak(text)`, which reads the text in a synthetic voice (macOS `say`) and shows it as a caption, since the video has no sound. Use `test.use({ settings, startPath })` to seed other settings or start on another route.
|
||||
|
||||
## Conversations
|
||||
|
||||
|
||||
@@ -301,9 +301,39 @@ function agenticDebugging(): Trace {
|
||||
return trace;
|
||||
}
|
||||
|
||||
/** A reply with a diagram, for diagram preview demos. */
|
||||
function diagrams(): Trace {
|
||||
const trace = new Trace('How a request flows through llama-server');
|
||||
|
||||
trace.user('Can you draw how a chat request flows through llama-server?');
|
||||
trace.assistant(
|
||||
[
|
||||
'Here is the path a request takes:',
|
||||
'',
|
||||
'```mermaid',
|
||||
'flowchart LR',
|
||||
' U[Browser] -->|POST /v1/chat/completions| S(llama-server)',
|
||||
' S --> Q{Slot free?}',
|
||||
' Q -->|yes| P[Prompt processing]',
|
||||
' Q -->|no| W[Queue]',
|
||||
' W --> P',
|
||||
' P --> G[Sample token]',
|
||||
' G -->|more| G',
|
||||
' G -->|SSE tokens| U',
|
||||
' click S href "https://github.com/ggml-org/llama.cpp" "llama.cpp on GitHub" _blank',
|
||||
'```',
|
||||
'',
|
||||
'Requests wait in the queue until a slot is free, then tokens stream back as they are sampled.'
|
||||
].join('\n')
|
||||
);
|
||||
|
||||
return trace;
|
||||
}
|
||||
|
||||
/** Built-in traces, by name. */
|
||||
export const DEMO_TRACES: Record<string, () => Trace> = {
|
||||
'agentic-debugging': agenticDebugging,
|
||||
diagrams,
|
||||
'long-chat': longChat
|
||||
};
|
||||
|
||||
|
||||
+117
-13
@@ -3,7 +3,15 @@ import { generateTrace } from './fixtures/traces.ts';
|
||||
import { ScreencastRecorder } from './recorder.ts';
|
||||
import { type CDPSession, type Locator, type Page, test as base } from '@playwright/test';
|
||||
import { execFileSync } from 'node:child_process';
|
||||
import { appendFileSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs';
|
||||
import {
|
||||
appendFileSync,
|
||||
mkdirSync,
|
||||
mkdtempSync,
|
||||
readFileSync,
|
||||
rmSync,
|
||||
writeFileSync
|
||||
} from 'node:fs';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { basename, join, resolve } from 'node:path';
|
||||
|
||||
const VIDEOS_DIR = resolve(import.meta.dirname, 'videos');
|
||||
@@ -112,6 +120,68 @@ function seedSettings(config: Record<string, unknown>): void {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Swaps the page's microphone for one that hears only what `window.demoSpeak` plays into it,
|
||||
* silence otherwise. Chromium's fake capture device crashes the page, so voice input is
|
||||
* recorded with this instead. Runs in the page.
|
||||
*/
|
||||
function installFakeMicrophone(): void {
|
||||
const context = new AudioContext();
|
||||
const output = context.createMediaStreamDestination();
|
||||
|
||||
navigator.mediaDevices.getUserMedia = async (constraints) => {
|
||||
if (!constraints?.audio || constraints.video) {
|
||||
throw new DOMException('demo: only the microphone is faked', 'NotSupportedError');
|
||||
}
|
||||
|
||||
await context.resume();
|
||||
|
||||
// each opening gets its own tracks, so a recording that stops them leaves the source on
|
||||
return new MediaStream(output.stream.getAudioTracks().map((track) => track.clone()));
|
||||
};
|
||||
|
||||
Object.assign(window, {
|
||||
demoSpeak: async (wavBase64: string) => {
|
||||
const bytes = Uint8Array.from(atob(wavBase64), (c) => c.charCodeAt(0));
|
||||
const source = context.createBufferSource();
|
||||
|
||||
source.buffer = await context.decodeAudioData(bytes.buffer);
|
||||
source.connect(output);
|
||||
await context.resume();
|
||||
await new Promise((done) => {
|
||||
source.onended = done;
|
||||
source.start();
|
||||
});
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
/** `text` read by a synthetic voice, as a base64 WAV. Uses macOS `say`. */
|
||||
function synthesizeSpeech(text: string, voice: string): string {
|
||||
const dir = mkdtempSync(join(tmpdir(), 'demo-speech-'));
|
||||
const file = join(dir, 'speech.wav');
|
||||
|
||||
try {
|
||||
execFileSync('say', [
|
||||
'-v',
|
||||
voice,
|
||||
'-o',
|
||||
file,
|
||||
'--file-format=WAVE',
|
||||
'--data-format=LEI16@24000',
|
||||
text
|
||||
]);
|
||||
|
||||
return readFileSync(file).toString('base64');
|
||||
} catch (error) {
|
||||
throw new Error(`demo: speak() needs macOS \`say\` with the voice ${voice}`, {
|
||||
cause: error
|
||||
});
|
||||
} finally {
|
||||
rmSync(dir, { force: true, recursive: true });
|
||||
}
|
||||
}
|
||||
|
||||
/** Seeded randomness, so a demo moves the same way on every recording. */
|
||||
function createRandom(seed: string): () => number {
|
||||
let state = [...seed].reduce((h, c) => Math.imul(h ^ c.charCodeAt(0), 2654435761), 1);
|
||||
@@ -143,19 +213,9 @@ export class Demo {
|
||||
|
||||
/** Shows a caption at the top of the frame for `ms`, clear of the chat form. */
|
||||
async caption(text: string, ms = 2200): Promise<void> {
|
||||
await this.page.evaluate((t) => {
|
||||
const el = document.getElementById('demo-caption');
|
||||
|
||||
if (!el) return;
|
||||
|
||||
el.textContent = t;
|
||||
el.classList.add('visible');
|
||||
}, text);
|
||||
await this.showCaption(text);
|
||||
await this.page.waitForTimeout(ms);
|
||||
await this.page.evaluate(() =>
|
||||
document.getElementById('demo-caption')?.classList.remove('visible')
|
||||
);
|
||||
await this.page.waitForTimeout(250);
|
||||
await this.hideCaption();
|
||||
}
|
||||
|
||||
async click(target: Locator, ms = 400): Promise<void> {
|
||||
@@ -182,6 +242,15 @@ export class Demo {
|
||||
await this.pause(ms);
|
||||
}
|
||||
|
||||
/**
|
||||
* Gives the page a microphone that hears only what `speak` says, and allows the page to
|
||||
* use it. Call it before the microphone is first used.
|
||||
*/
|
||||
async microphone(): Promise<void> {
|
||||
await this.page.context().grantPermissions(['microphone']);
|
||||
await this.page.evaluate(installFakeMicrophone);
|
||||
}
|
||||
|
||||
/** Glides the cursor to a point near the center of `target`. */
|
||||
async moveTo(target: Locator): Promise<void> {
|
||||
await target.scrollIntoViewIfNeeded();
|
||||
@@ -240,6 +309,23 @@ export class Demo {
|
||||
await this.pause(ms);
|
||||
}
|
||||
|
||||
/**
|
||||
* Says `text` into the microphone from `microphone` in a synthetic voice (macOS `say`), and
|
||||
* returns once it is said. The words show as a caption, since the video has no sound.
|
||||
*/
|
||||
async speak(text: string, voice = 'Samantha', ms = 400): Promise<void> {
|
||||
const wav = synthesizeSpeech(text, voice);
|
||||
|
||||
await this.showCaption(`“${text}”`);
|
||||
await this.page.evaluate(
|
||||
(base64) =>
|
||||
(window as unknown as { demoSpeak(wav: string): Promise<void> }).demoSpeak(base64),
|
||||
wav
|
||||
);
|
||||
await this.hideCaption();
|
||||
await this.pause(ms);
|
||||
}
|
||||
|
||||
/** Types quickly with uneven key timing, a little slower after spaces and punctuation. */
|
||||
async type(target: Locator, text: string, ms = 500): Promise<void> {
|
||||
await this.click(target, 200);
|
||||
@@ -305,6 +391,13 @@ export class Demo {
|
||||
return { x: box.x + box.width / 2, y: box.y + box.height / 2 };
|
||||
}
|
||||
|
||||
private async hideCaption(): Promise<void> {
|
||||
await this.page.evaluate(() =>
|
||||
document.getElementById('demo-caption')?.classList.remove('visible')
|
||||
);
|
||||
await this.page.waitForTimeout(250);
|
||||
}
|
||||
|
||||
/** A pinch that reaches the screen's edge can end without its last touchend reaching the page. */
|
||||
private async liftFingers(): Promise<void> {
|
||||
await this.page.evaluate(() =>
|
||||
@@ -340,6 +433,17 @@ export class Demo {
|
||||
|
||||
return this.cdp;
|
||||
}
|
||||
|
||||
private async showCaption(text: string): Promise<void> {
|
||||
await this.page.evaluate((t) => {
|
||||
const el = document.getElementById('demo-caption');
|
||||
|
||||
if (!el) return;
|
||||
|
||||
el.textContent = t;
|
||||
el.classList.add('visible');
|
||||
}, text);
|
||||
}
|
||||
}
|
||||
|
||||
interface DemoOptions {
|
||||
|
||||
@@ -34,9 +34,11 @@ const THEMES = [
|
||||
];
|
||||
// the type roles, by the @theme names Tailwind turns into text-body, text-label-sm, ...: a size with a line height
|
||||
const TYPE_ROLE = /^--text-([a-z]+(?:-[a-z]+)*)$/;
|
||||
// body and caption text takes the weight around it, which is regular unless a parent says otherwise
|
||||
const DEFAULT_WEIGHT = '400';
|
||||
// code takes the body-sm role in the mono stack (see `:where(code, pre, kbd, samp)` in theme.css)
|
||||
const CODE_ROLE = 'body-sm';
|
||||
// Tailwind's own `rounded-full`, for lamps, avatars and round buttons; the other corners are roles in semantic.css
|
||||
// Tailwind's own `rounded-full`, for lamps, avatars and round buttons; the other corners are the scale in theme.css
|
||||
const ROUNDED_FULL = '9999px';
|
||||
// the sections this script owns, in the order they appear in the front matter; the next one is written by hand
|
||||
const SECTIONS = ['colors', 'typography', 'rounded'];
|
||||
@@ -104,6 +106,8 @@ const isColorLiteral = (value) =>
|
||||
/^(oklch|oklab|rgb|hsl)\([^()]*\)$/.test(value);
|
||||
/** @param {string} value */
|
||||
const isColorMix = (value) => /^color-mix\(.*\)$/.test(value) && !/\)\s*,/.test(value);
|
||||
/** a share a theme sets for a derivation, e.g. `--status-surface-share: 11%` @param {string} value */
|
||||
const isShare = (value) => /^\d+(?:\.\d+)?%$/.test(value);
|
||||
/** @param {string} value */
|
||||
const varName = (value) => /^var\(--([\w-]+)\)$/.exec(value)?.[1];
|
||||
|
||||
@@ -136,7 +140,19 @@ function build() {
|
||||
|
||||
return next !== undefined && isColor(next, scope);
|
||||
};
|
||||
const semanticColors = [...semantic].filter(([, value]) => isColor(value, semantic));
|
||||
/**
|
||||
* A value with the shares it reads written out, as the theme whose declarations are `scope` sets them, so a
|
||||
* derivation reads as the mix it is: `color-mix(in oklab, var(--fill-danger) 11%, var(--surface-page))`.
|
||||
* @param {string} value
|
||||
* @param {Map<string, string>} [scope]
|
||||
*/
|
||||
const withShares = (value, scope) =>
|
||||
value.replace(/var\((--[\w-]+)\)/g, (reference, name) => {
|
||||
const share = scope?.get(name) ?? semantic.get(name) ?? '';
|
||||
|
||||
return isShare(share) ? share : reference;
|
||||
});
|
||||
const semanticColors = [...semantic].filter(([, value]) => isColor(withShares(value), semantic));
|
||||
const semanticNames = new Set(semanticColors.map(([name]) => name.slice(2)));
|
||||
/**
|
||||
* A token's value as the front matter writes it: a reference to another token, a literal, or a mix of them. A
|
||||
@@ -166,7 +182,7 @@ function build() {
|
||||
const base = new Map();
|
||||
|
||||
for (const [name, value] of semanticColors) {
|
||||
const rendered = render(value, (n) => n);
|
||||
const rendered = render(withShares(value), (n) => n);
|
||||
|
||||
base.set(name, rendered);
|
||||
colors.push([name.slice(2), rendered]);
|
||||
@@ -190,7 +206,9 @@ function build() {
|
||||
if (semanticNames.has(ref)) resolve(`--${ref}`);
|
||||
}
|
||||
|
||||
const result = render(value, (n) => (twins.has(n) ? `${n}${suffix}` : n));
|
||||
const result = render(withShares(value, overrides), (n) =>
|
||||
twins.has(n) ? `${n}${suffix}` : n
|
||||
);
|
||||
|
||||
rendered.set(name, result);
|
||||
|
||||
@@ -217,6 +235,13 @@ function build() {
|
||||
|
||||
return (name && primitives.get(`--${name}`)) ?? value ?? '';
|
||||
};
|
||||
// a line height is written as the line over the size, `calc(1.25 / 0.875)`: the line, in rem
|
||||
/** @param {string | undefined} value */
|
||||
const lineHeight = (value) => {
|
||||
const ratio = /^calc\(([\d.]+) \/ [\d.]+\)$/.exec(value ?? '');
|
||||
|
||||
return ratio ? `${ratio[1]}rem` : length(value);
|
||||
};
|
||||
/** @type {[string, Record<string, string>][]} */
|
||||
const typography = [];
|
||||
|
||||
@@ -230,8 +255,8 @@ function build() {
|
||||
{
|
||||
fontFamily: sans,
|
||||
fontSize: length(value),
|
||||
fontWeight: length(inline.get(`${name}--font-weight`)),
|
||||
lineHeight: length(inline.get(`${name}--line-height`))
|
||||
fontWeight: inline.get(`${name}--font-weight`) ?? DEFAULT_WEIGHT,
|
||||
lineHeight: lineHeight(inline.get(`${name}--line-height`))
|
||||
}
|
||||
]);
|
||||
}
|
||||
@@ -242,11 +267,17 @@ function build() {
|
||||
|
||||
/** @type {[string, string][]} */
|
||||
const rounded = [];
|
||||
// the corner scale is computed from --radius: `calc(var(--radius) + 4px)`, with 1rem as 16px
|
||||
const baseRadius = parseFloat(theme.get(':root')?.get('--radius') ?? '') * 16;
|
||||
|
||||
for (const [name, value] of inline) {
|
||||
const role = /^--radius-([a-z-]+)$/.exec(name)?.[1];
|
||||
for (const [name, value] of theme.get('@theme inline') ?? []) {
|
||||
const step = /^--radius-([a-z0-9]+)$/.exec(name)?.[1];
|
||||
const offset = /^calc\(var\(--radius\) ([+-]) ([\d.]+)px\)$/.exec(value);
|
||||
|
||||
if (role) rounded.push([role, length(value)]);
|
||||
if (!step) continue;
|
||||
|
||||
if (offset) rounded.push([step, `${baseRadius + Number(offset[1] + offset[2])}px`]);
|
||||
else if (value === 'var(--radius)') rounded.push([step, `${baseRadius}px`]);
|
||||
}
|
||||
|
||||
rounded.push(['full', ROUNDED_FULL]);
|
||||
|
||||
@@ -26,6 +26,7 @@ const LLAMA_UI_EXPORTS = [
|
||||
['@ggml-org/llama-ui/enums', `${source}/enums/index.ts`],
|
||||
['@ggml-org/llama-ui/code', `${source}/utils/index.ts`],
|
||||
['@ggml-org/llama-ui/utils', `${source}/components/ui/utils.ts`],
|
||||
['@ggml-org/llama-ui/voice', `${source}/components/voice/index.ts`],
|
||||
['@ggml-org/llama-ui/styles/*', `${source}/styles/*`],
|
||||
['@ggml-org/llama-ui/theme.css', `${source}/styles/theme.css`],
|
||||
['@ggml-org/llama-ui/tokens.css', `${source}/styles/tokens.css`],
|
||||
|
||||
+28
-32
@@ -30,7 +30,7 @@
|
||||
/* phone sidebar width, which the page slides aside to reveal */
|
||||
--sidebar-reveal: min(80dvw, 20rem);
|
||||
/* the desktop sidebar's muted/60 over the page, made opaque so the slid page's corners can match it */
|
||||
--sidebar-reveal-tint: color-mix(in oklab, var(--muted) 60%, var(--background));
|
||||
--sidebar-reveal-tint: color-mix(in oklab, var(--surface-muted) 60%, var(--surface-page));
|
||||
/* how far the phone sidebar is open, 0 to 1, stepped every frame by useSidebarReveal */
|
||||
--sidebar-reveal-progress: 0;
|
||||
/* the same on a log curve: the sidebar's contents hold on until the page nearly covers them */
|
||||
@@ -39,7 +39,7 @@
|
||||
--sidebar-reveal-bg: color-mix(
|
||||
in oklab,
|
||||
var(--sidebar-reveal-tint) calc(var(--sidebar-reveal-progress) * 100%),
|
||||
var(--background)
|
||||
var(--surface-page)
|
||||
);
|
||||
--layer-popover: 1000000;
|
||||
|
||||
@@ -63,7 +63,7 @@
|
||||
/* the chat form's corners while its text and actions share one row */
|
||||
--chat-form-single-row-radius: 1.25rem;
|
||||
/* the card's translucent fill over the page, made opaque: the phone sheet, and the page and Safari's bars around it */
|
||||
--chat-form-sheet-fill: color-mix(in oklab, var(--muted) 60%, var(--background));
|
||||
--chat-form-sheet-fill: color-mix(in oklab, var(--surface-muted) 60%, var(--surface-page));
|
||||
--max-message-height: max(24rem, min(80dvh, calc(100dvh - var(--chat-form-area-height) - 12rem)));
|
||||
}
|
||||
|
||||
@@ -91,7 +91,7 @@
|
||||
}
|
||||
|
||||
.dark {
|
||||
--chat-form-sheet-fill: color-mix(in oklab, var(--muted) 75%, var(--background));
|
||||
--chat-form-sheet-fill: color-mix(in oklab, var(--surface-muted) 75%, var(--surface-page));
|
||||
}
|
||||
|
||||
@layer base {
|
||||
@@ -202,9 +202,9 @@
|
||||
.chat-top-fade {
|
||||
background: linear-gradient(
|
||||
to bottom,
|
||||
color-mix(in srgb, var(--background) 100%, transparent) 25%,
|
||||
color-mix(in srgb, var(--background) 80%, transparent) 50%,
|
||||
color-mix(in srgb, var(--background) 40%, transparent) 75%,
|
||||
color-mix(in srgb, var(--surface-page) 100%, transparent) 25%,
|
||||
color-mix(in srgb, var(--surface-page) 80%, transparent) 50%,
|
||||
color-mix(in srgb, var(--surface-page) 40%, transparent) 75%,
|
||||
transparent 100%
|
||||
);
|
||||
}
|
||||
@@ -219,8 +219,8 @@
|
||||
height: var(--page-top);
|
||||
background: linear-gradient(
|
||||
to bottom,
|
||||
var(--background) calc(var(--corner-control-top) + 1.25rem),
|
||||
color-mix(in srgb, var(--background) 55%, transparent)
|
||||
var(--surface-page) calc(var(--corner-control-top) + 1.25rem),
|
||||
color-mix(in srgb, var(--surface-page) 55%, transparent)
|
||||
calc(var(--corner-control-top) + 2.5rem),
|
||||
transparent 100%
|
||||
);
|
||||
@@ -234,14 +234,14 @@
|
||||
10px Safari ignores; what it covers sits under the fade's solid part anyway */
|
||||
.status-bar-edge {
|
||||
height: 0.75rem;
|
||||
background-color: var(--background);
|
||||
background-color: var(--surface-page);
|
||||
}
|
||||
|
||||
/* The bottom edge's counterpart, which Safari takes for its bottom toolbar the same way:
|
||||
without it, it finds the chat form there and takes the form's colour */
|
||||
.screen-bottom-edge {
|
||||
height: 0.75rem;
|
||||
background-color: var(--background);
|
||||
background-color: var(--surface-page);
|
||||
}
|
||||
|
||||
/* The same fade at the bottom of a phone's screen: solid behind the home indicator and
|
||||
@@ -251,8 +251,9 @@
|
||||
height: calc(var(--safe-area-bottom) + 3rem);
|
||||
background: linear-gradient(
|
||||
to top,
|
||||
var(--background) var(--safe-area-bottom),
|
||||
color-mix(in srgb, var(--background) 60%, transparent) calc(var(--safe-area-bottom) + 1.5rem),
|
||||
var(--surface-page) var(--safe-area-bottom),
|
||||
color-mix(in srgb, var(--surface-page) 60%, transparent)
|
||||
calc(var(--safe-area-bottom) + 1.5rem),
|
||||
transparent 100%
|
||||
);
|
||||
}
|
||||
@@ -261,7 +262,7 @@
|
||||
panel's translucent muted tint, and a fade above it, like the one under
|
||||
the tab bar, so the rows scrolling beneath end softly */
|
||||
.sidebar-show-more {
|
||||
--sidebar-surface: color-mix(in oklab, var(--muted) 60%, var(--background));
|
||||
--sidebar-surface: color-mix(in oklab, var(--surface-muted) 60%, var(--surface-page));
|
||||
background: var(--sidebar-surface);
|
||||
|
||||
&::before {
|
||||
@@ -284,14 +285,14 @@
|
||||
over the other sections while dragged */
|
||||
.sidebar-drag-surface,
|
||||
.sidebar-drag-overlay {
|
||||
background: color-mix(in oklab, var(--muted) 60%, var(--background));
|
||||
background: color-mix(in oklab, var(--surface-muted) 60%, var(--surface-page));
|
||||
}
|
||||
|
||||
/* the copy of a chat row that follows the pointer, raised above the page */
|
||||
.sidebar-drag-overlay {
|
||||
box-shadow:
|
||||
0 10px 30px -10px rgb(0 0 0 / 0.35),
|
||||
0 0 0 1px color-mix(in srgb, var(--foreground) 12%, transparent);
|
||||
0 0 0 1px color-mix(in srgb, var(--fg-default) 12%, transparent);
|
||||
}
|
||||
|
||||
/* While something is dragged, what it passes over takes no hover: only the
|
||||
@@ -329,12 +330,7 @@
|
||||
}
|
||||
|
||||
.shimmer-text {
|
||||
background: linear-gradient(
|
||||
90deg,
|
||||
var(--muted-foreground),
|
||||
var(--foreground),
|
||||
var(--muted-foreground)
|
||||
);
|
||||
background: linear-gradient(90deg, var(--fg-muted), var(--fg-default), var(--fg-muted));
|
||||
background-size: 200% 100%;
|
||||
background-clip: text;
|
||||
-webkit-background-clip: text;
|
||||
@@ -361,16 +357,16 @@
|
||||
* so the svg also inherits them inside the preview dialog's shadow root, and follow the theme.
|
||||
*/
|
||||
:root {
|
||||
--pele-bg: var(--code-background);
|
||||
--pele-fg: var(--code-foreground);
|
||||
--pele-muted: var(--muted-foreground);
|
||||
--pele-line: var(--muted-foreground);
|
||||
--pele-surface: var(--background);
|
||||
--pele-surface-alt: var(--muted);
|
||||
--pele-border: var(--border);
|
||||
--pele-accent: var(--primary);
|
||||
--pele-critical: var(--destructive);
|
||||
--pele-error: var(--destructive);
|
||||
--pele-bg: var(--surface-code);
|
||||
--pele-fg: var(--fg-code);
|
||||
--pele-muted: var(--fg-muted);
|
||||
--pele-line: var(--fg-muted);
|
||||
--pele-surface: var(--surface-page);
|
||||
--pele-surface-alt: var(--surface-muted);
|
||||
--pele-border: var(--line-default);
|
||||
--pele-accent: var(--action-primary);
|
||||
--pele-critical: var(--fg-danger);
|
||||
--pele-error: var(--fg-danger);
|
||||
--pele-radius: calc(var(--radius) - 4px);
|
||||
}
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@
|
||||
{@const ModalityIcon = MODALITY_ICONS[modality]}
|
||||
<span
|
||||
class={[
|
||||
'inline-flex items-center gap-1 rounded-md bg-muted px-2 py-1 text-xs font-medium',
|
||||
'inline-flex items-center gap-1 rounded-md bg-muted px-2 py-1 text-caption font-medium',
|
||||
className
|
||||
]}
|
||||
>
|
||||
|
||||
+14
-3
@@ -1,9 +1,11 @@
|
||||
<script lang="ts">
|
||||
import { VoiceWaveformSize } from '@ggml-org/llama-ui/voice';
|
||||
import {
|
||||
ChatAttachmentsListItemMcpPrompt,
|
||||
ChatAttachmentsListItemMcpResource,
|
||||
ChatAttachmentsListItemThumbnailFile,
|
||||
ChatAttachmentsListItemThumbnailImage
|
||||
ChatAttachmentsListItemThumbnailImage,
|
||||
ChatAttachmentsListItemVoice
|
||||
} from '#lib/components/app/index.ts';
|
||||
import { AttachmentType } from '#lib/enums/index.ts';
|
||||
import type {
|
||||
@@ -12,7 +14,7 @@
|
||||
DatabaseMessageExtraMcpResource,
|
||||
MCPResourceAttachment
|
||||
} from '#lib/types/index.ts';
|
||||
import { isMcpPrompt, isMcpResource, isPdfFile } from '#lib/utils/index.ts';
|
||||
import { isAudioFile, isMcpPrompt, isMcpResource, isPdfFile } from '#lib/utils/index.ts';
|
||||
|
||||
interface Props {
|
||||
class?: string;
|
||||
@@ -77,7 +79,7 @@
|
||||
: null}
|
||||
{#if mcpPrompt}
|
||||
<ChatAttachmentsListItemMcpPrompt
|
||||
class="max-w-[300px] min-w-[200px] flex-shrink-0 {className} {scrollClasses}"
|
||||
class="max-w-75 min-w-50 flex-shrink-0 {className} {scrollClasses}"
|
||||
isLoading={item.isLoading}
|
||||
loadError={item.loadError}
|
||||
onRemove={onFileRemove ? () => onFileRemove(item.id) : undefined}
|
||||
@@ -93,6 +95,15 @@
|
||||
class="flex-shrink-0 {className} {scrollClasses}"
|
||||
onclick={() => onMcpResourcePreview?.(mcpResource)}
|
||||
/>
|
||||
{:else if isAudioFile(item.attachment, item.uploadedFile)}
|
||||
<!-- a clip plays where it is: the waveform takes the presses a chip would -->
|
||||
<ChatAttachmentsListItemVoice
|
||||
class="{layoutClasses} {className} {scrollClasses}"
|
||||
{item}
|
||||
onRemove={onFileRemove}
|
||||
{readonly}
|
||||
size={readonly ? VoiceWaveformSize.MD : VoiceWaveformSize.SM}
|
||||
/>
|
||||
{:else if item.isImage && item.preview}
|
||||
<ChatAttachmentsListItemThumbnailImage
|
||||
class="{layoutClasses} cursor-pointer {className} {scrollClasses}"
|
||||
|
||||
+3
-3
@@ -35,7 +35,7 @@
|
||||
<Tooltip.Trigger>
|
||||
<button
|
||||
class={[
|
||||
'flex flex-shrink-0 items-center gap-1.5 rounded-md border px-2 py-0.75 text-sm transition-colors',
|
||||
'flex flex-shrink-0 items-center gap-1.5 rounded-md border px-2 py-0.75 text-body-sm transition-colors',
|
||||
getStatusClass(attachment),
|
||||
onclick && 'cursor-pointer hover:bg-muted/50',
|
||||
className
|
||||
@@ -52,7 +52,7 @@
|
||||
<ResourceIcon class="size-icon-xs text-muted-foreground" />
|
||||
{/if}
|
||||
|
||||
<span class="max-w-[150px] truncate text-xs">
|
||||
<span class="max-w-37.5 truncate text-caption">
|
||||
{getResourceDisplayName(attachment.resource)}
|
||||
</span>
|
||||
|
||||
@@ -70,7 +70,7 @@
|
||||
</Tooltip.Trigger>
|
||||
|
||||
<Tooltip.Content>
|
||||
<div class="flex items-center gap-1 text-xs">
|
||||
<div class="flex items-center gap-1 text-caption">
|
||||
{#if favicon}
|
||||
<img
|
||||
alt={attachment.resource.serverName}
|
||||
|
||||
+6
-6
@@ -80,7 +80,7 @@
|
||||
{#snippet textPreview(content: string)}
|
||||
<div class="relative">
|
||||
<div
|
||||
class="font-mono text-xs leading-relaxed break-words whitespace-pre-wrap text-muted-foreground {!readonly
|
||||
class="font-mono text-caption leading-relaxed break-words whitespace-pre-wrap text-muted-foreground {!readonly
|
||||
? 'max-h-3rem line-height-1.2'
|
||||
: ''}"
|
||||
>
|
||||
@@ -107,7 +107,7 @@
|
||||
|
||||
{#snippet fileIcon()}
|
||||
<div
|
||||
class="flex size-8 items-center justify-center rounded bg-primary/10 text-xs font-medium text-primary"
|
||||
class="flex size-8 items-center justify-center rounded bg-primary/10 text-label-sm text-primary"
|
||||
>
|
||||
{#if isAudio}
|
||||
<Music class="{ICON_CLASS_DEFAULT} text-white/70" />
|
||||
@@ -121,7 +121,7 @@
|
||||
|
||||
{#snippet info(text: string | undefined)}
|
||||
{#if text}
|
||||
<span class="text-xs text-muted-foreground">{text}</span>
|
||||
<span class="text-caption text-muted-foreground">{text}</span>
|
||||
{/if}
|
||||
{/snippet}
|
||||
|
||||
@@ -142,7 +142,7 @@
|
||||
{#if readonly}
|
||||
<div class="flex items-start gap-3">
|
||||
<div class="flex min-w-0 flex-1 flex-col items-start text-left">
|
||||
<span class="w-full truncate text-sm font-medium text-foreground">{name}</span>
|
||||
<span class="w-full truncate text-label text-foreground">{name}</span>
|
||||
|
||||
{@render info(pdfProcessingMode || (size ? formatFileSize(size) : undefined))}
|
||||
|
||||
@@ -152,7 +152,7 @@
|
||||
</div>
|
||||
</div>
|
||||
{:else}
|
||||
<span class="mb-3 block truncate text-sm font-medium text-foreground">{name}</span>
|
||||
<span class="mb-3 block truncate text-label text-foreground">{name}</span>
|
||||
|
||||
{#if textContent}
|
||||
{@render textPreview(textContent)}
|
||||
@@ -170,7 +170,7 @@
|
||||
|
||||
<div class="flex flex-col items-start gap-0.5">
|
||||
<span
|
||||
class="max-w-24 truncate text-sm font-medium text-foreground {readonly
|
||||
class="max-w-24 truncate text-label text-foreground {readonly
|
||||
? ''
|
||||
: 'group-hover:pr-6'} md:max-w-32"
|
||||
>
|
||||
|
||||
+1
-1
@@ -51,7 +51,7 @@
|
||||
|
||||
{#if label}
|
||||
<span
|
||||
class="pointer-events-none absolute bottom-1 left-1 rounded-md bg-black/40 px-1.5 py-0.5 text-[10px] font-medium text-white matte-chip backdrop-blur-md [--badge-highlight:rgb(255_255_255/0.18)]"
|
||||
class="pointer-events-none absolute bottom-1 left-1 rounded-md bg-black/40 px-1.5 py-0.5 text-caption-sm font-medium text-white matte-chip backdrop-blur-md [--badge-highlight:rgb(255_255_255/0.18)]"
|
||||
>
|
||||
{label}
|
||||
</span>
|
||||
|
||||
+126
@@ -0,0 +1,126 @@
|
||||
<!--
|
||||
An audio attachment drawn as a clip: a playable waveform, and for a voice message its transcript under it, open while
|
||||
it comes in and after, unless the Collapse transcripts setting folds it (then it opens on hover, keyboard focus or a
|
||||
tap). `sm` is the chip in the chat form, `md` the clip in a sent message. A clip
|
||||
stored without peaks (an older message, an uploaded file) gets them computed from its audio.
|
||||
-->
|
||||
<script lang="ts">
|
||||
import {
|
||||
spokenLength,
|
||||
VoiceTranscriptReveal,
|
||||
VoiceWaveform,
|
||||
VoiceWaveformSize
|
||||
} from '@ggml-org/llama-ui/voice';
|
||||
import { X } from '@lucide/svelte';
|
||||
import { ActionIcon } from '#lib/components/app/index.ts';
|
||||
import { SETTINGS_KEYS, VOICE_MESSAGE_LABEL } from '#lib/constants/index.ts';
|
||||
import { settingsStore, voiceTranscriptsStore } from '#lib/stores/index.ts';
|
||||
import type { ChatAttachmentDisplayItem } from '#lib/types/index.ts';
|
||||
import { audioUrl, lazyPeaks, voiceAttachmentSource } from '#lib/utils/voice-attachment.ts';
|
||||
|
||||
interface Props {
|
||||
class?: string;
|
||||
item: ChatAttachmentDisplayItem;
|
||||
onRemove?: (id: string) => void;
|
||||
readonly?: boolean;
|
||||
size?: VoiceWaveformSize;
|
||||
}
|
||||
|
||||
let {
|
||||
class: className = '',
|
||||
item,
|
||||
onRemove,
|
||||
readonly = false,
|
||||
size = VoiceWaveformSize.MD
|
||||
}: Props = $props();
|
||||
|
||||
let source = $derived(voiceAttachmentSource(item));
|
||||
let computedPeaks = $state<number[] | null>(null);
|
||||
let src = $state<string | undefined>();
|
||||
|
||||
let peaks = $derived(source.peaks ?? computedPeaks ?? []);
|
||||
let shown = $derived(voiceTranscriptsStore.shown(source.name, source.transcript));
|
||||
let transcript = $derived(shown.transcript);
|
||||
let status = $derived(shown.status);
|
||||
let errorReason = $derived(shown.errorReason);
|
||||
let label = $derived(source.voice ? VOICE_MESSAGE_LABEL : source.name);
|
||||
// the transcript lights up word by word as the clip plays, and stays lit
|
||||
let playbackMs = $state<number | null>(null);
|
||||
let spoken = $derived(
|
||||
transcript && playbackMs !== null && source.durationMs
|
||||
? spokenLength(transcript, peaks, source.durationMs, playbackMs)
|
||||
: null
|
||||
);
|
||||
let collapsed = $derived(settingsStore.config[SETTINGS_KEYS.VOICE_COLLAPSE_TRANSCRIPTS] === true);
|
||||
|
||||
// an object URL lives as long as the clip is on screen
|
||||
$effect(() => {
|
||||
const audio = source.audio;
|
||||
|
||||
if (!audio) {
|
||||
src = undefined;
|
||||
|
||||
return;
|
||||
}
|
||||
|
||||
const playable = audioUrl(audio, source.mimeType);
|
||||
|
||||
src = playable?.url;
|
||||
|
||||
return () => {
|
||||
if (playable?.revoke) URL.revokeObjectURL(playable.url);
|
||||
};
|
||||
});
|
||||
|
||||
$effect(() => {
|
||||
const { audio, name, peaks: stored } = source;
|
||||
|
||||
computedPeaks = null;
|
||||
|
||||
if (stored || !audio) return;
|
||||
|
||||
let cancelled = false;
|
||||
|
||||
lazyPeaks(name, audio).then((value) => {
|
||||
if (!cancelled) computedPeaks = value;
|
||||
});
|
||||
|
||||
return () => {
|
||||
cancelled = true;
|
||||
};
|
||||
});
|
||||
</script>
|
||||
|
||||
<div
|
||||
class={[
|
||||
'group relative min-w-0',
|
||||
size === VoiceWaveformSize.SM
|
||||
? 'w-60 max-w-[calc(100vw-4rem)] rounded-lg border border-border bg-muted py-2 pr-9 pl-2'
|
||||
: 'w-80 max-w-full rounded-2xl matte-sheen bg-(--user-bubble-background) px-3 py-2.5 backdrop-blur-md dark:bg-primary/15',
|
||||
className
|
||||
]}
|
||||
data-slot="chat-attachment-voice"
|
||||
data-voice={source.voice || undefined}
|
||||
>
|
||||
{#key collapsed}
|
||||
<VoiceTranscriptReveal defaultOpen={!collapsed} {errorReason} {spoken} {status} {transcript}>
|
||||
<VoiceWaveform bind:playbackMs durationMs={source.durationMs} {label} {peaks} {size} {src} />
|
||||
</VoiceTranscriptReveal>
|
||||
{/key}
|
||||
|
||||
{#if !source.voice}
|
||||
<p class="mt-1 truncate px-1 text-caption text-muted-foreground">{source.name}</p>
|
||||
{/if}
|
||||
|
||||
{#if !readonly && onRemove}
|
||||
<div class="absolute top-1/2 right-1 -translate-y-1/2">
|
||||
<ActionIcon
|
||||
ariaLabel={source.voice ? 'Remove voice message' : `Remove ${source.name}`}
|
||||
icon={X}
|
||||
onclick={() => onRemove?.(item.id)}
|
||||
stopPropagationOnClick
|
||||
tooltip="Remove"
|
||||
/>
|
||||
</div>
|
||||
{/if}
|
||||
</div>
|
||||
+26
-2
@@ -1,12 +1,23 @@
|
||||
<script lang="ts">
|
||||
import { VoiceTranscriptStatus } from '@ggml-org/llama-ui/voice';
|
||||
import { Music } from '@lucide/svelte';
|
||||
import { VOICE_MESSAGE_LABEL } from '#lib/constants/index.ts';
|
||||
import { voiceTranscriptsStore } from '#lib/stores/index.ts';
|
||||
import type { ChatAttachmentDisplayItem } from '#lib/types/index.ts';
|
||||
import { voiceAttachmentSource } from '#lib/utils/voice-attachment.ts';
|
||||
|
||||
interface Props {
|
||||
currentItem: { name?: string } | null;
|
||||
currentItem: ChatAttachmentDisplayItem | null;
|
||||
audioSrc: string | null;
|
||||
}
|
||||
|
||||
let { audioSrc, currentItem }: Props = $props();
|
||||
|
||||
let source = $derived(currentItem ? voiceAttachmentSource(currentItem) : null);
|
||||
// a voice message's transcript, from the message or still on its way
|
||||
let shown = $derived(source ? voiceTranscriptsStore.shown(source.name, source.transcript) : null);
|
||||
let transcript = $derived(shown?.transcript);
|
||||
let transcribing = $derived(shown?.status === VoiceTranscriptStatus.TRANSCRIBING);
|
||||
</script>
|
||||
|
||||
<div class="flex flex-1 items-center justify-center p-8">
|
||||
@@ -21,6 +32,19 @@
|
||||
<p class="mb-4 text-white/70">Audio preview not available</p>
|
||||
{/if}
|
||||
|
||||
<p class="text-sm text-white/50">{currentItem?.name || 'Audio'}</p>
|
||||
<p class="text-body-sm text-white/50">
|
||||
{source?.voice ? VOICE_MESSAGE_LABEL : currentItem?.name || 'Audio'}
|
||||
</p>
|
||||
|
||||
{#if transcript}
|
||||
<p
|
||||
class="mt-6 max-h-[40vh] overflow-y-auto text-left text-body-sm whitespace-pre-wrap text-white/80"
|
||||
data-slot="voice-preview-transcript"
|
||||
>
|
||||
<span class="sr-only">Transcript: </span>{transcript}
|
||||
</p>
|
||||
{:else if transcribing}
|
||||
<p class="mt-6 text-caption text-white/50">Transcribing...</p>
|
||||
{/if}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
+2
-2
@@ -206,7 +206,7 @@
|
||||
{@render status('Failed to load PDF images', pdfImagesError)}
|
||||
{:else if pdfImages.length > 0}
|
||||
{#each pdfImages as image, index (index)}
|
||||
<p class="mb-2 text-sm text-white/50">Page {index + 1}</p>
|
||||
<p class="mb-2 text-body-sm text-white/50">Page {index + 1}</p>
|
||||
|
||||
<img
|
||||
alt="PDF Page {index + 1}"
|
||||
@@ -240,7 +240,7 @@
|
||||
<p class={['text-white/70', detail && 'mb-4']}>{message}</p>
|
||||
|
||||
{#if detail}
|
||||
<p class="text-sm text-white/50">{detail}</p>
|
||||
<p class="text-body-sm text-white/50">{detail}</p>
|
||||
{/if}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
+1
-1
@@ -22,6 +22,6 @@
|
||||
<p class="mb-4 text-white/70">Video preview not available</p>
|
||||
{/if}
|
||||
|
||||
<p class="text-sm text-white/50">{currentItem?.name || 'Video'}</p>
|
||||
<p class="text-body-sm text-white/50">{currentItem?.name || 'Video'}</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
+2
-2
@@ -7,10 +7,10 @@
|
||||
let { displayName, fileSize }: Props = $props();
|
||||
</script>
|
||||
|
||||
<div class="sticky top-0 z-[20] mb-4 rounded-lg bg-black/5 px-4 py-2 text-center backdrop-blur-md">
|
||||
<div class="sticky top-0 z-20 mb-4 rounded-lg bg-black/5 px-4 py-2 text-center backdrop-blur-md">
|
||||
<p class="font-medium text-white">{displayName}</p>
|
||||
|
||||
{#if fileSize}
|
||||
<p class="text-xs text-white/60">{fileSize}</p>
|
||||
<p class="text-caption text-white/60">{fileSize}</p>
|
||||
{/if}
|
||||
</div>
|
||||
|
||||
+3
-1
@@ -61,7 +61,9 @@
|
||||
<FileText class="{ICON_CLASS_DEFAULT} text-white/70" />
|
||||
{/if}
|
||||
|
||||
<span class="font-mono text-[9px] text-white/60">{getFileExtension(item.name)}</span>
|
||||
<span class="font-mono text-caption-sm text-white/60"
|
||||
>{getFileExtension(item.name)}</span
|
||||
>
|
||||
</div>
|
||||
{/if}
|
||||
</button>
|
||||
|
||||
@@ -1,10 +1,13 @@
|
||||
<script lang="ts">
|
||||
import ContextGaugePopup from './ChatFormContextGauge/ContextGaugePopup.svelte';
|
||||
import { microphoneUnavailableReason, warmUpVoiceCapture } from '@ggml-org/llama-voice';
|
||||
import { VoiceRecorder } from '@ggml-org/llama-voice/svelte';
|
||||
import { Maximize, Minimize } from '@lucide/svelte';
|
||||
import {
|
||||
ActionIcon,
|
||||
ChatAttachmentsList,
|
||||
ChatFormActions,
|
||||
ChatFormActionsRecording,
|
||||
ChatFormCurrentWorkingDirectory,
|
||||
ChatFormInput,
|
||||
ChatFormInputFileInputInvisible,
|
||||
@@ -18,7 +21,8 @@
|
||||
ICON_CLASS_DEFAULT,
|
||||
INITIAL_FILE_SIZE,
|
||||
PROMPT_CONTENT_SEPARATOR,
|
||||
SETTING_CONFIG_DEFAULT
|
||||
SETTING_CONFIG_DEFAULT,
|
||||
VOICE_EDITOR_SELECTOR
|
||||
} from '#lib/constants/index.ts';
|
||||
import {
|
||||
ContentPartType,
|
||||
@@ -30,6 +34,10 @@
|
||||
} from '#lib/enums/index.ts';
|
||||
import { useChatFormExpansion } from '#lib/hooks/use-chat-form-expansion.svelte.ts';
|
||||
import { useChatFormPickers } from '#lib/hooks/use-chat-form-pickers.svelte.ts';
|
||||
import {
|
||||
useChatFormVoice,
|
||||
type VoiceRecorderLike
|
||||
} from '#lib/hooks/use-chat-form-voice.svelte.ts';
|
||||
import {
|
||||
chatStore,
|
||||
conversationsStore,
|
||||
@@ -39,7 +47,8 @@
|
||||
serverStore,
|
||||
settingsStore,
|
||||
toolsStore,
|
||||
uiStore
|
||||
uiStore,
|
||||
voiceTranscriptsStore
|
||||
} from '#lib/stores/index.ts';
|
||||
import type {
|
||||
FileMentionEntry,
|
||||
@@ -48,14 +57,6 @@
|
||||
MCPResourceInfo,
|
||||
PromptMessage
|
||||
} from '#lib/types/index.ts';
|
||||
import {
|
||||
AudioRecorder,
|
||||
convertToWav,
|
||||
createAudioFile,
|
||||
describeMicrophoneError,
|
||||
isAudioRecordingSupported,
|
||||
microphoneUnavailableReason
|
||||
} from '#lib/utils/browser-only.ts';
|
||||
import {
|
||||
buildMentionInsertion,
|
||||
findCommandToken,
|
||||
@@ -65,7 +66,7 @@
|
||||
parseClipboardContent,
|
||||
uuid
|
||||
} from '#lib/utils/index.ts';
|
||||
import { onMount, untrack } from 'svelte';
|
||||
import { onMount, tick, untrack } from 'svelte';
|
||||
import type { ClassValue } from 'svelte/elements';
|
||||
import { toast } from 'svelte-sonner';
|
||||
|
||||
@@ -96,6 +97,9 @@
|
||||
onUploadedFileRemove?: (fileId: string) => void;
|
||||
onUploadedFilesChange?: (files: ChatUploadedFile[]) => void;
|
||||
onValueChange?: (value: string) => void;
|
||||
|
||||
/** Records voice input; tests and stories pass a fake, the app a VoiceRecorder. */
|
||||
voiceRecorder?: VoiceRecorderLike;
|
||||
}
|
||||
|
||||
let {
|
||||
@@ -117,21 +121,20 @@
|
||||
showModelSelector = true,
|
||||
singleRow = false,
|
||||
uploadedFiles = $bindable([]),
|
||||
value = $bindable('')
|
||||
value = $bindable(''),
|
||||
voiceRecorder
|
||||
}: Props = $props();
|
||||
|
||||
// Component References
|
||||
|
||||
let audioRecorder: AudioRecorder | undefined;
|
||||
let chatFormActionsRef: ChatFormActions | undefined = $state(undefined);
|
||||
let fileInputRef: ChatFormInputFileInputInvisible | undefined = $state(undefined);
|
||||
let pickersRef: { handleKeydown: (event: KeyboardEvent) => boolean } | undefined =
|
||||
$state(undefined);
|
||||
let inputRef: ChatFormInput | undefined = $state(undefined);
|
||||
|
||||
// Audio Recording State
|
||||
let isRecording = $state(false);
|
||||
let recordingSupported = $state(false);
|
||||
// Voice input
|
||||
const recorder: VoiceRecorderLike = untrack(() => voiceRecorder) ?? new VoiceRecorder();
|
||||
/** Why this page can't record at all (no HTTPS, no recorder), which no tap fixes. */
|
||||
let micUnavailableReason = $state<string | null>(null);
|
||||
/** Why the last start failed (denied, no microphone, busy); the next tap tries again. */
|
||||
@@ -189,6 +192,25 @@
|
||||
}
|
||||
});
|
||||
|
||||
const voice = useChatFormVoice({
|
||||
addVoiceFile: (file) => {
|
||||
uploadedFiles = [...uploadedFiles, file];
|
||||
onUploadedFilesChange?.(uploadedFiles);
|
||||
},
|
||||
getCaretOffset: () => inputRef?.getCaretOffset() ?? value.length,
|
||||
getValue: () => value,
|
||||
onMicError: (message) => (micError = message),
|
||||
recorder,
|
||||
// on a phone placing the caret would open the keyboard
|
||||
setCaretOffset: (offset) => {
|
||||
if (!deviceStore.isMobile) inputRef?.setCaretOffset(offset);
|
||||
},
|
||||
setValue: (next) => {
|
||||
value = next;
|
||||
onValueChange?.(next);
|
||||
}
|
||||
});
|
||||
|
||||
async function handleWorkingDirectoryChange(newDir: string | null) {
|
||||
// Committing a directory consumes the `/cwd` token; the chip's
|
||||
// clear-X path has no token to consume.
|
||||
@@ -234,6 +256,14 @@
|
||||
(attachments && attachments.length > 0) || (uploadedFiles && uploadedFiles.length > 0)
|
||||
);
|
||||
let canSubmit = $derived(value.trim().length > 0 || hasAttachments);
|
||||
// while a voice message records, what is being said shows in the empty message box; once
|
||||
// it stops, the text goes with the clip, as its transcript
|
||||
let voicePlaceholder = $derived(
|
||||
voice.isActive && voice.liveCaption && !value.trim() ? voice.liveCaption : null
|
||||
);
|
||||
|
||||
// while a reply streams, sending what is recorded waits for its first words in the form
|
||||
let hasVoiceText = $derived(!!value.trim() || !!voice.liveCaption);
|
||||
|
||||
const EXPANDED_SHEET_FILL = 'max-md:bg-(--chat-form-sheet-fill)';
|
||||
|
||||
@@ -263,6 +293,7 @@
|
||||
singleRow &&
|
||||
!deviceStore.isMobile &&
|
||||
!isExpanded &&
|
||||
!voice.isActive &&
|
||||
!hasAttachments &&
|
||||
!mcpStore.resources.hasAttachments &&
|
||||
!value.includes('\n')
|
||||
@@ -327,9 +358,7 @@
|
||||
);
|
||||
|
||||
onMount(() => {
|
||||
recordingSupported = isAudioRecordingSupported();
|
||||
micUnavailableReason = microphoneUnavailableReason();
|
||||
audioRecorder = new AudioRecorder();
|
||||
});
|
||||
|
||||
/** Expands for the message as it stands, e.g. one put back after a send failed. */
|
||||
@@ -375,6 +404,10 @@
|
||||
onAttachmentRemove?.(index);
|
||||
}
|
||||
} else {
|
||||
const removed = uploadedFiles.find((file) => file.id === fileId);
|
||||
|
||||
if (removed?.voice) voiceTranscriptsStore.forget(removed.name);
|
||||
|
||||
onUploadedFileRemove?.(fileId);
|
||||
}
|
||||
}
|
||||
@@ -399,9 +432,7 @@
|
||||
|
||||
event.preventDefault();
|
||||
|
||||
if (!canSubmit || disabled || hasLoadingAttachments) return;
|
||||
|
||||
onSubmit?.();
|
||||
void submit();
|
||||
}
|
||||
}
|
||||
|
||||
@@ -586,7 +617,7 @@
|
||||
inputRef?.replaceText(built.newValue, built.caretOffset);
|
||||
}
|
||||
|
||||
async function handleMicClick() {
|
||||
function handleMicClick() {
|
||||
// a phone shows no tooltip on a tap, so the reason comes as a toast
|
||||
if (micUnavailableReason) {
|
||||
toast.error(micUnavailableReason);
|
||||
@@ -594,36 +625,61 @@
|
||||
return;
|
||||
}
|
||||
|
||||
if (!audioRecorder || !recordingSupported) {
|
||||
console.warn('Audio recording not supported');
|
||||
void voice.start();
|
||||
}
|
||||
|
||||
return;
|
||||
}
|
||||
// the audio set-up takes a moment, so it is made while the message is being written;
|
||||
// it asks for no microphone, so the browser shows no recording indicator
|
||||
function handleFocusIn(event: FocusEvent) {
|
||||
if (voice.showButton && !voice.isActive) warmUpVoiceCapture();
|
||||
|
||||
if (isRecording) {
|
||||
isRecording = false;
|
||||
try {
|
||||
const audioBlob = await audioRecorder.stopRecording();
|
||||
const wavBlob = await convertToWav(audioBlob);
|
||||
const audioFile = createAudioFile(wavBlob);
|
||||
|
||||
onFilesAdd?.([audioFile]);
|
||||
} catch (error) {
|
||||
console.error('Failed to stop recording:', error);
|
||||
}
|
||||
} else {
|
||||
try {
|
||||
await audioRecorder.startRecording();
|
||||
isRecording = true;
|
||||
micError = null;
|
||||
} catch (error) {
|
||||
micError = describeMicrophoneError(error);
|
||||
toast.error(micError);
|
||||
}
|
||||
// the voice message's live text shown as the placeholder turns into text to edit
|
||||
if (voicePlaceholder && (event.target as Element | null)?.closest(VOICE_EDITOR_SELECTOR)) {
|
||||
voice.adoptLiveText();
|
||||
}
|
||||
}
|
||||
|
||||
// a send asked for while the dictated text is still being refined waits for it
|
||||
let isSendWaiting = $state(false);
|
||||
|
||||
/** Sends the message; dictated text that is still being refined is sent refined. */
|
||||
async function submit() {
|
||||
if (!canSubmit || disabled || hasLoadingAttachments || isSendWaiting) return;
|
||||
|
||||
if (voice.isRefining) {
|
||||
isSendWaiting = true;
|
||||
|
||||
try {
|
||||
await voice.settled();
|
||||
await tick();
|
||||
} finally {
|
||||
isSendWaiting = false;
|
||||
}
|
||||
|
||||
if (!canSubmit || disabled || hasLoadingAttachments) return;
|
||||
}
|
||||
|
||||
onSubmit?.();
|
||||
}
|
||||
|
||||
/** Stops the recording and sends the message once its text or clip is in the form. */
|
||||
async function handleStopAndSend() {
|
||||
await voice.stop();
|
||||
await tick();
|
||||
await submit();
|
||||
}
|
||||
|
||||
// Escape drops a recording, wherever the focus is
|
||||
function handleWindowKeydown(event: KeyboardEvent) {
|
||||
if (event.key !== KeyboardKey.ESCAPE || !voice.isActive || event.defaultPrevented) return;
|
||||
|
||||
event.preventDefault();
|
||||
voice.cancel();
|
||||
}
|
||||
</script>
|
||||
|
||||
<svelte:window onkeydown={handleWindowKeydown} />
|
||||
|
||||
<ChatFormInputFileInputInvisible bind:this={fileInputRef} onFileSelect={handleFileSelect} />
|
||||
|
||||
<form
|
||||
@@ -636,12 +692,10 @@
|
||||
'max-h-[calc(100dvh-var(--chat-tabs-offset,0px)-var(--chat-form-padding-top)-2rem)] max-md:max-h-dvh',
|
||||
className
|
||||
]}
|
||||
onfocusin={handleFocusIn}
|
||||
onsubmit={(event) => {
|
||||
event.preventDefault();
|
||||
|
||||
if (!canSubmit || disabled || hasLoadingAttachments) return;
|
||||
|
||||
onSubmit?.();
|
||||
void submit();
|
||||
}}
|
||||
>
|
||||
<!-- the pickers' own triggers fill this box, so all of them share the anchor -->
|
||||
@@ -678,9 +732,7 @@
|
||||
bind:this={cardEl}
|
||||
class={[
|
||||
'chat-form-surface group/chat-form relative flex shrink flex-col overflow-hidden outline-none transition-[min-height,padding,border-radius,border-color,background-color] duration-400 ease-[var(--chat-form-resize-ease,cubic-bezier(0.3,1.12,0.5,1))] motion-reduce:transition-none',
|
||||
isSingleRow
|
||||
? 'rounded-(--chat-form-single-row-radius)'
|
||||
: 'rounded-(--chat-form-radius-compact) md:rounded-(--chat-form-radius)',
|
||||
isSingleRow ? 'rounded-(--chat-form-single-row-radius)' : 'rounded-4xl md:rounded-3xl',
|
||||
// on a phone the sheet's animation moves it (see useChatFormExpansion): only its
|
||||
// border, hidden on the sheet, fades back in after
|
||||
'max-md:transition-[border-color] max-md:duration-200',
|
||||
@@ -702,7 +754,7 @@
|
||||
'max-md:pt-safe',
|
||||
// no rim, ring or visible border along the screen's edges; the border stays
|
||||
// transparent so nothing inside shifts by its width
|
||||
'max-md:[--glass-edge-side:transparent] max-md:[--glass-edge-mid:transparent] max-md:[--glass-edge-side-focus:transparent] max-md:[--glass-edge-mid-focus:transparent] max-md:[--glass-highlight:transparent]',
|
||||
'max-md:[--glass-edge:transparent] max-md:[--glass-edge-focus:transparent] max-md:[--glass-highlight:transparent]',
|
||||
'max-md:border-transparent max-md:focus-within:border-transparent max-md:dark:border-transparent max-md:dark:focus-within:border-transparent',
|
||||
EXPANDED_SHEET_FILL
|
||||
],
|
||||
@@ -734,7 +786,7 @@
|
||||
|
||||
<div
|
||||
class={[
|
||||
'relative flex flex-1 shadow-sm transition-shadow focus-within:shadow-md',
|
||||
'relative flex flex-1 shadow-(--elevation-control) transition-shadow focus-within:shadow-(--elevation-surface)',
|
||||
// the add button, the text and the rest of the actions, or the text above them
|
||||
isSingleRow
|
||||
? 'items-center gap-2 rounded-(--chat-form-single-row-radius) px-3 py-2.5'
|
||||
@@ -755,13 +807,14 @@
|
||||
{disabled}
|
||||
expanded={isExpanded}
|
||||
onInput={() => {
|
||||
voice.handleUserInput();
|
||||
expansion.handleInput();
|
||||
pickers.handleInput();
|
||||
onValueChange?.(value);
|
||||
}}
|
||||
onKeydown={handleKeydown}
|
||||
onPaste={handlePaste}
|
||||
{placeholder}
|
||||
placeholder={voicePlaceholder ?? placeholder}
|
||||
/>
|
||||
|
||||
{#if mcpStore.resources.hasAttachments}
|
||||
@@ -776,29 +829,55 @@
|
||||
|
||||
<!-- its own box, so the phone sheet can hold it by the bottom edge while it moves -->
|
||||
<div bind:this={actionsEl} class={isSingleRow ? 'contents' : 'relative mt-auto'}>
|
||||
<ChatFormActions
|
||||
bind:this={chatFormActionsRef}
|
||||
canSend={canSubmit}
|
||||
class={isSingleRow ? undefined : 'px-3'}
|
||||
{disabled}
|
||||
inline={isSingleRow}
|
||||
{isLoading}
|
||||
isReasoning={chatStore.isReasoning}
|
||||
{isRecording}
|
||||
micWarning={micUnavailableReason ?? micError}
|
||||
onFileUpload={handleFileUpload}
|
||||
onMicClick={handleMicClick}
|
||||
{onStop}
|
||||
onSystemPromptClick={() =>
|
||||
onSystemPromptClick?.({ files: uploadedFiles, message: value })}
|
||||
onWorkingDirectoryClick={isWorkingDirectoryInAddMenu
|
||||
? pickers.handleWorkingDirectoryOpen
|
||||
: undefined}
|
||||
{showAddButton}
|
||||
{showModelSelector}
|
||||
{uploadedFiles}
|
||||
workingDirectory={cwd}
|
||||
/>
|
||||
{#if voice.isActive}
|
||||
<ChatFormActionsRecording
|
||||
class="px-3"
|
||||
elapsedMs={voice.elapsedMs}
|
||||
levels={voice.levels}
|
||||
liveCaption={voicePlaceholder ? '' : voice.liveCaption}
|
||||
mode={voice.mode}
|
||||
onCancel={voice.cancel}
|
||||
onSend={isLoading && !hasVoiceText ? undefined : () => void handleStopAndSend()}
|
||||
onStop={() => void voice.stop()}
|
||||
quiet={voice.quiet}
|
||||
state={voice.state}
|
||||
/>
|
||||
{/if}
|
||||
|
||||
<!-- kept while recording, so its selector and menus keep their state -->
|
||||
<div class={voice.isActive ? 'hidden' : 'contents'}>
|
||||
<ChatFormActions
|
||||
bind:this={chatFormActionsRef}
|
||||
canSend={canSubmit}
|
||||
class={isSingleRow ? undefined : 'px-3'}
|
||||
{disabled}
|
||||
inline={isSingleRow}
|
||||
{isLoading}
|
||||
isReasoning={chatStore.isReasoning}
|
||||
{isSendWaiting}
|
||||
isVoiceRefining={voice.isRefining}
|
||||
micWarning={micUnavailableReason ?? micError}
|
||||
onFileUpload={handleFileUpload}
|
||||
onMicClick={handleMicClick}
|
||||
{onStop}
|
||||
onSystemPromptClick={() =>
|
||||
onSystemPromptClick?.({ files: uploadedFiles, message: value })}
|
||||
onWorkingDirectoryClick={isWorkingDirectoryInAddMenu
|
||||
? pickers.handleWorkingDirectoryOpen
|
||||
: undefined}
|
||||
{showAddButton}
|
||||
{showModelSelector}
|
||||
voice={{
|
||||
action: voice.label,
|
||||
hint: voice.hint,
|
||||
prepare: () => void voice.prepare(),
|
||||
show: voice.showButton,
|
||||
unavailableReason: voice.unavailableReason,
|
||||
unprepare: voice.unprepare
|
||||
}}
|
||||
workingDirectory={cwd}
|
||||
/>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
+1
-1
@@ -15,7 +15,7 @@
|
||||
<Tooltip.Root>
|
||||
<Tooltip.Trigger class="w-full">
|
||||
<Button
|
||||
class="file-upload-button bg-background size-9 rounded-full p-0 shadow-(--chat-form-key-shadow) md:size-8 dark:bg-muted-foreground/15"
|
||||
class="file-upload-button bg-background size-9 rounded-full p-0 shadow-(--elevation-key) md:size-8 dark:bg-muted-foreground/15"
|
||||
{disabled}
|
||||
{onclick}
|
||||
type="button"
|
||||
|
||||
+13
-14
@@ -8,24 +8,23 @@
|
||||
ChevronRight,
|
||||
File,
|
||||
Folder,
|
||||
Image,
|
||||
MessageSquare,
|
||||
Mic,
|
||||
PencilRuler,
|
||||
Video
|
||||
PencilRuler
|
||||
} from '@lucide/svelte';
|
||||
import {
|
||||
ATTACHMENT_FILE_ITEMS,
|
||||
ATTACHMENT_MENU_TEXT,
|
||||
ATTACHMENT_MODALITY_TEXT,
|
||||
ICON_CLASS_DEFAULT
|
||||
ICON_CLASS_DEFAULT,
|
||||
MODALITY_ICONS
|
||||
} from '#lib/constants/index.ts';
|
||||
import { getChatFormActionsContext } from '#lib/contexts/index.ts';
|
||||
import { AttachmentAction, AttachmentItemEnabledWhen } from '#lib/enums/attachment.enums.ts';
|
||||
import { ModelModality } from '#lib/enums/index.ts';
|
||||
import { useAttachmentMenu } from '#lib/hooks/use-attachment-menu.svelte.ts';
|
||||
import { useToolsPanel } from '#lib/hooks/use-tools-panel.svelte.ts';
|
||||
import type { ToolGroup } from '#lib/types/index.ts';
|
||||
import type { Snippet } from 'svelte';
|
||||
import type { Component, Snippet } from 'svelte';
|
||||
|
||||
interface Props {
|
||||
class?: string;
|
||||
@@ -54,17 +53,17 @@
|
||||
}
|
||||
);
|
||||
|
||||
const FILE_MODALITY_ICONS: Record<string, { icon: typeof Image; label: string }> = {
|
||||
const FILE_MODALITY_ICONS: Record<string, { icon: Component; label: string }> = {
|
||||
[AttachmentItemEnabledWhen.HAS_AUDIO_MODALITY]: {
|
||||
icon: Mic,
|
||||
icon: MODALITY_ICONS[ModelModality.AUDIO],
|
||||
label: ATTACHMENT_MODALITY_TEXT[AttachmentItemEnabledWhen.HAS_AUDIO_MODALITY]
|
||||
},
|
||||
[AttachmentItemEnabledWhen.HAS_VIDEO_MODALITY]: {
|
||||
icon: Video,
|
||||
icon: MODALITY_ICONS[ModelModality.VIDEO],
|
||||
label: ATTACHMENT_MODALITY_TEXT[AttachmentItemEnabledWhen.HAS_VIDEO_MODALITY]
|
||||
},
|
||||
[AttachmentItemEnabledWhen.HAS_VISION_MODALITY]: {
|
||||
icon: Image,
|
||||
icon: MODALITY_ICONS[ModelModality.VISION],
|
||||
label: ATTACHMENT_MODALITY_TEXT[AttachmentItemEnabledWhen.HAS_VISION_MODALITY]
|
||||
}
|
||||
};
|
||||
@@ -78,10 +77,10 @@
|
||||
const toolsPanel = useToolsPanel();
|
||||
|
||||
const itemClass =
|
||||
'flex w-full items-center gap-3 rounded-md px-3 py-2.5 text-left text-sm transition-colors hover:bg-accent active:bg-accent disabled:cursor-not-allowed disabled:opacity-50';
|
||||
'flex w-full items-center gap-3 rounded-md px-3 py-2.5 text-left text-body-sm transition-colors hover:bg-accent active:bg-accent disabled:cursor-not-allowed disabled:opacity-50';
|
||||
|
||||
const itemRowClass =
|
||||
'flex w-full items-center justify-between gap-2 rounded-md px-3 py-2 text-left text-sm transition-colors hover:bg-accent';
|
||||
'flex w-full items-center justify-between gap-2 rounded-md px-3 py-2 text-left text-body-sm transition-colors hover:bg-accent';
|
||||
</script>
|
||||
|
||||
<div class="flex items-center gap-1 {className}">
|
||||
@@ -205,9 +204,9 @@
|
||||
/>
|
||||
{/if}
|
||||
|
||||
<span class="min-w-0 flex-1 truncate text-sm font-medium">{group.label}</span>
|
||||
<span class="min-w-0 flex-1 truncate text-label">{group.label}</span>
|
||||
|
||||
<span class="shrink-0 text-xs text-muted-foreground">
|
||||
<span class="shrink-0 text-caption text-muted-foreground">
|
||||
{enabledCount}/{group.tools.length}
|
||||
</span>
|
||||
|
||||
|
||||
+10
-8
@@ -3,18 +3,20 @@
|
||||
import * as DropdownMenu from '@ggml-org/llama-ui/ui/dropdown-menu';
|
||||
import * as Tooltip from '@ggml-org/llama-ui/ui/tooltip';
|
||||
import { cn } from '@ggml-org/llama-ui/utils';
|
||||
import { File, Folder, Image, MessageSquare, Mic, Plus, Video } from '@lucide/svelte';
|
||||
import { File, Folder, MessageSquare, Plus } from '@lucide/svelte';
|
||||
import { ChatFormActionAddToolsSubmenu } from '#lib/components/app/index.ts';
|
||||
import {
|
||||
ATTACHMENT_FILE_ITEMS,
|
||||
ATTACHMENT_MENU_TEXT,
|
||||
ATTACHMENT_MODALITY_TEXT,
|
||||
ATTACHMENT_TOOLTIP_TEXT,
|
||||
ICON_CLASS_DEFAULT
|
||||
ICON_CLASS_DEFAULT,
|
||||
MODALITY_ICONS
|
||||
} from '#lib/constants/index.ts';
|
||||
import { getChatFormActionsContext } from '#lib/contexts/index.ts';
|
||||
import { AttachmentAction, AttachmentItemEnabledWhen } from '#lib/enums/index.ts';
|
||||
import { AttachmentAction, AttachmentItemEnabledWhen, ModelModality } from '#lib/enums/index.ts';
|
||||
import { useAttachmentMenu } from '#lib/hooks/use-attachment-menu.svelte.ts';
|
||||
import type { Component } from 'svelte';
|
||||
|
||||
interface Props {
|
||||
class?: string;
|
||||
@@ -44,17 +46,17 @@
|
||||
}
|
||||
);
|
||||
|
||||
const FILE_MODALITY_ICONS: Record<string, { icon: typeof Image; label: string }> = {
|
||||
const FILE_MODALITY_ICONS: Record<string, { icon: Component; label: string }> = {
|
||||
[AttachmentItemEnabledWhen.HAS_AUDIO_MODALITY]: {
|
||||
icon: Mic,
|
||||
icon: MODALITY_ICONS[ModelModality.AUDIO],
|
||||
label: ATTACHMENT_MODALITY_TEXT[AttachmentItemEnabledWhen.HAS_AUDIO_MODALITY]
|
||||
},
|
||||
[AttachmentItemEnabledWhen.HAS_VIDEO_MODALITY]: {
|
||||
icon: Video,
|
||||
icon: MODALITY_ICONS[ModelModality.VIDEO],
|
||||
label: ATTACHMENT_MODALITY_TEXT[AttachmentItemEnabledWhen.HAS_VIDEO_MODALITY]
|
||||
},
|
||||
[AttachmentItemEnabledWhen.HAS_VISION_MODALITY]: {
|
||||
icon: Image,
|
||||
icon: MODALITY_ICONS[ModelModality.VISION],
|
||||
label: ATTACHMENT_MODALITY_TEXT[AttachmentItemEnabledWhen.HAS_VISION_MODALITY]
|
||||
}
|
||||
};
|
||||
@@ -78,7 +80,7 @@
|
||||
class={cn(
|
||||
// ghost brings no fill of its own for the muted composer surface to fight over
|
||||
buttonVariants({ variant: 'ghost' }),
|
||||
'file-upload-button matte-key size-8 [--button-shadow:var(--chat-form-key-shadow)] cursor-pointer rounded-full bg-background p-0 dark:bg-muted-foreground/15'
|
||||
'file-upload-button matte-key size-8 [--button-shadow:var(--elevation-key)] cursor-pointer rounded-full bg-background p-0 dark:bg-muted-foreground/15'
|
||||
)}
|
||||
disabled={chatFormActions.disabled}
|
||||
>
|
||||
|
||||
+13
-9
@@ -23,13 +23,13 @@
|
||||
<DropdownMenu.SubContent class="w-72 p-0">
|
||||
{#if toolsPanel.totalToolCount === 0}
|
||||
{#if toolsStore.loading}
|
||||
<div class="px-3 py-4 text-center text-sm text-muted-foreground">
|
||||
<div class="px-3 py-4 text-center text-body-sm text-muted-foreground">
|
||||
<Loader2 class="mx-auto mb-1 {ICON_CLASS_DEFAULT} animate-spin" />
|
||||
|
||||
Loading tools...
|
||||
</div>
|
||||
{:else if toolsStore.isToolsEndpointUnreachable}
|
||||
<div class="grid gap-2.5 px-3 py-4 text-sm text-muted-foreground">
|
||||
<div class="grid gap-2.5 px-3 py-4 text-body-sm text-muted-foreground">
|
||||
<span class="flex gap-2">
|
||||
<Info class="mt-0.5 {ICON_CLASS_DEFAULT} shrink-0" />
|
||||
|
||||
@@ -54,15 +54,19 @@
|
||||
{/if}
|
||||
</div>
|
||||
{:else if toolsStore.error}
|
||||
<div class="px-3 py-4 text-center text-sm text-muted-foreground">Failed to load tools</div>
|
||||
<div class="px-3 py-4 text-center text-body-sm text-muted-foreground">
|
||||
Failed to load tools
|
||||
</div>
|
||||
{:else if toolsPanel.noToolsInfoMessage}
|
||||
<div class="flex gap-2 px-3 py-4 text-sm text-muted-foreground">
|
||||
<div class="flex gap-2 px-3 py-4 text-body-sm text-muted-foreground">
|
||||
<Info class="mt-0.5 {ICON_CLASS_DEFAULT} shrink-0" />
|
||||
|
||||
<span>{toolsPanel.noToolsInfoMessage}</span>
|
||||
</div>
|
||||
{:else}
|
||||
<div class="px-3 py-4 text-center text-sm text-muted-foreground">No tools available</div>
|
||||
<div class="px-3 py-4 text-center text-body-sm text-muted-foreground">
|
||||
No tools available
|
||||
</div>
|
||||
{/if}
|
||||
{:else}
|
||||
<div class="max-h-80 overflow-y-auto p-2 pr-1">
|
||||
@@ -90,7 +94,7 @@
|
||||
>
|
||||
<div class="flex items-center gap-1 {groupDisabled ? 'pointer-events-none opacity-50' : ''}">
|
||||
<Collapsible.Trigger
|
||||
class="flex min-w-0 flex-1 items-center gap-2 rounded px-2 py-1.5 text-sm hover:bg-muted/50"
|
||||
class="flex min-w-0 flex-1 items-center gap-2 rounded px-2 py-1.5 text-body-sm hover:bg-muted/50"
|
||||
>
|
||||
{#if isExpanded}
|
||||
<ChevronDown class="size-icon-sm shrink-0" />
|
||||
@@ -113,7 +117,7 @@
|
||||
<span class="truncate">{group.label}</span>
|
||||
</span>
|
||||
|
||||
<span class="ml-auto shrink-0 text-xs text-muted-foreground">
|
||||
<span class="ml-auto shrink-0 text-caption text-muted-foreground">
|
||||
{toolsPanel.getEnabledToolCount(group)}/{group.tools.length}
|
||||
</span>
|
||||
</Collapsible.Trigger>
|
||||
@@ -146,7 +150,7 @@
|
||||
{@const enabled = toolsPanel.isToolEnabled(entry)}
|
||||
{@const parentDisabled = toolsPanel.isToolParentDisabled(entry)}
|
||||
<button
|
||||
class="flex w-full items-center gap-2 rounded px-2 py-1.5 text-left text-sm transition-colors hover:bg-muted/50 {parentDisabled
|
||||
class="flex w-full items-center gap-2 rounded px-2 py-1.5 text-left text-body-sm transition-colors hover:bg-muted/50 {parentDisabled
|
||||
? 'opacity-50'
|
||||
: ''}"
|
||||
onclick={() => toolsPanel.toggleTool(entry)}
|
||||
@@ -162,7 +166,7 @@
|
||||
{/if}
|
||||
</span>
|
||||
|
||||
<span class="min-w-0 flex-1 truncate font-mono text-[12px]">
|
||||
<span class="min-w-0 flex-1 truncate font-mono text-caption">
|
||||
{entry.definition.function.name}
|
||||
</span>
|
||||
</button>
|
||||
|
||||
+5
-5
@@ -46,7 +46,7 @@
|
||||
|
||||
<button
|
||||
aria-pressed={reasoning.isSelected(level)}
|
||||
class="flex min-h-11 w-full cursor-pointer items-center gap-3 rounded-md px-3 text-left text-sm transition-colors hover:bg-accent"
|
||||
class="flex min-h-11 w-full cursor-pointer items-center gap-3 rounded-md px-3 text-left text-body-sm transition-colors hover:bg-accent"
|
||||
onclick={() => select(level)}
|
||||
type="button"
|
||||
>
|
||||
@@ -59,7 +59,7 @@
|
||||
<span class="min-w-0 flex-1 truncate">{level.label}</span>
|
||||
|
||||
{#if tokenLabel}
|
||||
<span class="shrink-0 text-[11px] text-muted-foreground opacity-60">{tokenLabel}</span>
|
||||
<span class="shrink-0 text-caption text-muted-foreground opacity-60">{tokenLabel}</span>
|
||||
{/if}
|
||||
|
||||
{#if level.hasInfo}
|
||||
@@ -75,7 +75,7 @@
|
||||
aria-label="Reasoning effort"
|
||||
class="h-auto gap-1 rounded-sm bg-transparent! backdrop-blur-none! {isDefault
|
||||
? 'px-1'
|
||||
: 'px-1.75!'} py-1 text-xs max-md:h-8"
|
||||
: 'px-1.75!'} py-1 text-caption max-md:h-8"
|
||||
onclick={() => (isOpen = true)}
|
||||
variant="ghost"
|
||||
>
|
||||
@@ -104,7 +104,7 @@
|
||||
aria-label="Reasoning effort"
|
||||
class="-mr-px h-6 min-w-6 gap-1 rounded-sm bg-transparent backdrop-blur-none! {isDefault
|
||||
? 'px-1'
|
||||
: 'px-1.75!'} py-0 text-xs hover:bg-muted-foreground/15 data-[state=open]:bg-muted-foreground/15"
|
||||
: 'px-1.75!'} py-0 text-caption hover:bg-muted-foreground/15 data-[state=open]:bg-muted-foreground/15"
|
||||
variant="ghost"
|
||||
>
|
||||
{@render triggerLabel()}
|
||||
@@ -126,7 +126,7 @@
|
||||
<span class="min-w-0 flex-1 truncate">{level.label}</span>
|
||||
|
||||
{#if tokenLabel}
|
||||
<span class="shrink-0 text-[11px] text-muted-foreground opacity-60">{tokenLabel}</span>
|
||||
<span class="shrink-0 text-caption text-muted-foreground opacity-60">{tokenLabel}</span>
|
||||
{/if}
|
||||
|
||||
{#if level.hasInfo}
|
||||
|
||||
+88
-14
@@ -2,34 +2,95 @@
|
||||
import { Button } from '@ggml-org/llama-ui/ui/button';
|
||||
import * as Tooltip from '@ggml-org/llama-ui/ui/tooltip';
|
||||
import { Mic, MicOff, Square } from '@lucide/svelte';
|
||||
import { ICON_CLASS_DEFAULT } from '#lib/constants/index.ts';
|
||||
import {
|
||||
ICON_CLASS_DEFAULT,
|
||||
VOICE_MODE_MESSAGE,
|
||||
VOICE_PRESS_CLICK_MS
|
||||
} from '#lib/constants/index.ts';
|
||||
import { MouseButton, PointerType } from '#lib/enums/index.ts';
|
||||
|
||||
interface Props {
|
||||
/** What a press does: send a voice message or dictate. */
|
||||
action?: string;
|
||||
class?: string;
|
||||
disabled?: boolean;
|
||||
hasAudioModality?: boolean;
|
||||
/** Said after the action in the tooltip, e.g. that another model may be loaded. */
|
||||
hint?: string | null;
|
||||
isLoading?: boolean;
|
||||
isRecording?: boolean;
|
||||
/** Why the microphone can't record (no HTTPS, access denied...), shown on the button. */
|
||||
micWarning?: string | null;
|
||||
/** Why no model can take the recording; disables the button. */
|
||||
unavailableReason?: string | null;
|
||||
/** A quieter (tertiary) button, beside the main one: send or stop. */
|
||||
secondary?: boolean;
|
||||
/** With `secondary`: filled like the stop button it stands beside, not bare. */
|
||||
filled?: boolean;
|
||||
onMicClick?: () => void;
|
||||
/** A mouse or the focus came to the button: a press may follow, the microphone can open. */
|
||||
onPrepare?: () => void;
|
||||
/** It left again without a press. */
|
||||
onPrepareEnd?: () => void;
|
||||
}
|
||||
|
||||
let {
|
||||
action = VOICE_MODE_MESSAGE.voiceMessage,
|
||||
class: className = '',
|
||||
disabled = false,
|
||||
hasAudioModality = false,
|
||||
filled = false,
|
||||
hint = null,
|
||||
isLoading = false,
|
||||
isRecording = false,
|
||||
micWarning = null,
|
||||
onMicClick
|
||||
onMicClick,
|
||||
onPrepare,
|
||||
onPrepareEnd,
|
||||
secondary = false,
|
||||
unavailableReason = null
|
||||
}: Props = $props();
|
||||
|
||||
// a model without audio input disables the button; a microphone that can't record keeps it
|
||||
// no model to take the recording disables the button; a microphone that can't record keeps it
|
||||
// tappable, so a tap can say why
|
||||
const showWarning = $derived(hasAudioModality && !isRecording && !!micWarning);
|
||||
const showWarning = $derived(!unavailableReason && !isRecording && !!micWarning);
|
||||
// a mouse starts recording on press, not on release, so the first words are not lost;
|
||||
// a touch or a key goes through the click, which is when the browser allows it
|
||||
let pressedAt = -Infinity;
|
||||
|
||||
function handlePointerDown(event: PointerEvent) {
|
||||
if (isRecording || disabled || isLoading || unavailableReason) return;
|
||||
|
||||
if (event.pointerType !== PointerType.MOUSE || event.button !== MouseButton.PRIMARY) return;
|
||||
|
||||
pressedAt = performance.now();
|
||||
onMicClick?.();
|
||||
}
|
||||
|
||||
// a touch presses at once, so only a mouse, a pen or the keyboard come ahead of the press
|
||||
function handlePointerEnter(event: PointerEvent) {
|
||||
if (event.pointerType !== PointerType.TOUCH && !isRecording) onPrepare?.();
|
||||
}
|
||||
|
||||
function handlePointerLeave(event: PointerEvent) {
|
||||
if (event.pointerType !== PointerType.TOUCH) onPrepareEnd?.();
|
||||
}
|
||||
|
||||
function handleClick() {
|
||||
// the click that ends the press that already started it; the recording bar may have
|
||||
// taken the button's place meanwhile, so this one can also never come
|
||||
if (performance.now() - pressedAt < VOICE_PRESS_CLICK_MS) {
|
||||
pressedAt = -Infinity;
|
||||
|
||||
return;
|
||||
}
|
||||
|
||||
onMicClick?.();
|
||||
}
|
||||
|
||||
const tooltip = $derived(
|
||||
!hasAudioModality ? 'Current model does not support audio' : showWarning ? micWarning : null
|
||||
isRecording
|
||||
? null
|
||||
: (unavailableReason ??
|
||||
(showWarning ? micWarning : [action, hint].filter(Boolean).join('. ')))
|
||||
);
|
||||
</script>
|
||||
|
||||
@@ -37,28 +98,41 @@
|
||||
<Tooltip.Root>
|
||||
<Tooltip.Trigger>
|
||||
<Button
|
||||
class="size-8 max-md:size-9 rounded-full p-0 {isRecording
|
||||
? 'matte-orb orb-danger animate-pulse text-white! hover:bg-transparent'
|
||||
class="group size-8 max-md:size-9 rounded-full p-0 {isRecording
|
||||
? 'matte-orb orb-danger text-white! hover:bg-transparent'
|
||||
: showWarning
|
||||
? 'bg-surface-warning text-fg-warning hover:bg-surface-warning'
|
||||
: ''}"
|
||||
disabled={disabled || isLoading || !hasAudioModality}
|
||||
onclick={onMicClick}
|
||||
disabled={disabled || isLoading || !!unavailableReason}
|
||||
onblur={() => onPrepareEnd?.()}
|
||||
onclick={handleClick}
|
||||
onfocus={() => !isRecording && onPrepare?.()}
|
||||
onpointerdown={handlePointerDown}
|
||||
onpointerenter={handlePointerEnter}
|
||||
onpointerleave={handlePointerLeave}
|
||||
type="button"
|
||||
variant={isRecording || showWarning ? 'ghost' : 'default'}
|
||||
variant={isRecording || showWarning
|
||||
? 'ghost'
|
||||
: secondary
|
||||
? filled
|
||||
? 'secondary'
|
||||
: 'tertiary'
|
||||
: 'default'}
|
||||
>
|
||||
<span class="sr-only"
|
||||
>{isRecording
|
||||
? 'Stop recording'
|
||||
: showWarning
|
||||
? `Recording unavailable: ${micWarning}`
|
||||
: 'Start recording'}</span
|
||||
: action}</span
|
||||
>
|
||||
|
||||
{#if isRecording}
|
||||
<Square class="{ICON_CLASS_DEFAULT} animate-pulse fill-white" />
|
||||
<Square class="{ICON_CLASS_DEFAULT} fill-white" />
|
||||
{:else if showWarning}
|
||||
<MicOff class={ICON_CLASS_DEFAULT} />
|
||||
{:else if secondary}
|
||||
<Mic class="{ICON_CLASS_DEFAULT} stroke-muted-foreground group-hover:stroke-foreground" />
|
||||
{:else}
|
||||
<Mic class={ICON_CLASS_DEFAULT} />
|
||||
{/if}
|
||||
|
||||
+15
-3
@@ -1,16 +1,24 @@
|
||||
<script lang="ts">
|
||||
import { Button } from '@ggml-org/llama-ui/ui/button';
|
||||
import * as Tooltip from '@ggml-org/llama-ui/ui/tooltip';
|
||||
import { ArrowUp } from '@lucide/svelte';
|
||||
import { ArrowUp, LoaderCircle } from '@lucide/svelte';
|
||||
|
||||
interface Props {
|
||||
canSend?: boolean;
|
||||
disabled?: boolean;
|
||||
/** The send is on its way: it waits for something, e.g. dictated text being refined. */
|
||||
loading?: boolean;
|
||||
showErrorState?: boolean;
|
||||
tooltipLabel?: string;
|
||||
}
|
||||
|
||||
let { canSend = false, disabled = false, showErrorState = false, tooltipLabel }: Props = $props();
|
||||
let {
|
||||
canSend = false,
|
||||
disabled = false,
|
||||
loading = false,
|
||||
showErrorState = false,
|
||||
tooltipLabel
|
||||
}: Props = $props();
|
||||
|
||||
let isDisabled = $derived(!canSend || disabled);
|
||||
</script>
|
||||
@@ -28,7 +36,11 @@
|
||||
>
|
||||
<span class="sr-only">Send</span>
|
||||
|
||||
<ArrowUp class="size-icon-md" />
|
||||
{#if loading}
|
||||
<LoaderCircle class="size-icon-md animate-spin" />
|
||||
{:else}
|
||||
<ArrowUp class="size-icon-md" />
|
||||
{/if}
|
||||
</Button>
|
||||
{/snippet}
|
||||
|
||||
|
||||
+76
-27
@@ -1,22 +1,24 @@
|
||||
<script lang="ts">
|
||||
import { Button } from '@ggml-org/llama-ui/ui/button';
|
||||
import { SkipForward, Square } from '@lucide/svelte';
|
||||
import { LoaderCircle, SkipForward, Square } from '@lucide/svelte';
|
||||
import {
|
||||
ChatFormActionReasoning,
|
||||
ChatFormActionRecord,
|
||||
ChatFormActionsAdd,
|
||||
ChatFormActionSubmit,
|
||||
ChatFormContextGauge,
|
||||
ModelsSelector
|
||||
} from '#lib/components/app/index.ts';
|
||||
import { ICON_CLASS_DEFAULT, SET_WORKING_DIRECTORY_LABEL } from '#lib/constants/index.ts';
|
||||
import {
|
||||
ICON_CLASS_DEFAULT,
|
||||
SET_WORKING_DIRECTORY_LABEL,
|
||||
VOICE_MODE_MESSAGE
|
||||
} from '#lib/constants/index.ts';
|
||||
import { setChatFormActionsContext } from '#lib/contexts/index.ts';
|
||||
import { FileTypeCategory } from '#lib/enums/index.ts';
|
||||
import { useChatFormModel } from '#lib/hooks/use-chat-form-model.svelte.ts';
|
||||
import { useShowContextGauge } from '#lib/hooks/use-context-gauge.svelte.ts';
|
||||
import { ChatService } from '#lib/services/index.ts';
|
||||
import { conversationsStore, deviceStore, settingsStore, toolsStore } from '#lib/stores/index.ts';
|
||||
import { abbreviateWorkingDir, getFileTypeCategory } from '#lib/utils/index.ts';
|
||||
import { abbreviateWorkingDir } from '#lib/utils/index.ts';
|
||||
|
||||
interface Props {
|
||||
canSend?: boolean;
|
||||
@@ -26,12 +28,25 @@
|
||||
inline?: boolean;
|
||||
isLoading?: boolean;
|
||||
isReasoning?: boolean;
|
||||
isRecording?: boolean;
|
||||
/** A send was asked for and waits for the dictated text to be refined. */
|
||||
isSendWaiting?: boolean;
|
||||
/** The dictated text in the message is still being refined. */
|
||||
isVoiceRefining?: boolean;
|
||||
/** Why the microphone can't record, shown on its button. */
|
||||
micWarning?: string | null;
|
||||
/** Voice input: whether the microphone shows, what it does, and why it can't. */
|
||||
voice?: {
|
||||
action: string;
|
||||
hint: string | null;
|
||||
show: boolean;
|
||||
unavailableReason: string | null;
|
||||
/** The pointer or the focus came to the microphone button, a press may follow */
|
||||
prepare?: () => void;
|
||||
/** It left without a press */
|
||||
unprepare?: () => void;
|
||||
};
|
||||
showAddButton?: boolean;
|
||||
showModelSelector?: boolean;
|
||||
uploadedFiles?: ChatUploadedFile[];
|
||||
/** The chat's working directory, which the + menu names. */
|
||||
workingDirectory?: string | null;
|
||||
onFileUpload?: () => void;
|
||||
@@ -48,7 +63,8 @@
|
||||
inline = false,
|
||||
isLoading = false,
|
||||
isReasoning = false,
|
||||
isRecording = false,
|
||||
isSendWaiting = false,
|
||||
isVoiceRefining = false,
|
||||
micWarning = null,
|
||||
onFileUpload,
|
||||
onMicClick,
|
||||
@@ -57,7 +73,7 @@
|
||||
onWorkingDirectoryClick,
|
||||
showAddButton = true,
|
||||
showModelSelector = true,
|
||||
uploadedFiles = [],
|
||||
voice,
|
||||
workingDirectory = null
|
||||
}: Props = $props();
|
||||
|
||||
@@ -78,12 +94,17 @@
|
||||
return '';
|
||||
});
|
||||
|
||||
let hasAudioAttachments = $derived(
|
||||
uploadedFiles.some((file) => getFileTypeCategory(file.type) === FileTypeCategory.AUDIO)
|
||||
);
|
||||
let shouldShowRecordButton = $derived(
|
||||
hasAudioModality && !canSend && !hasAudioAttachments && currentConfig.autoMicOnEmpty
|
||||
);
|
||||
// the microphone sits beside the send or stop button: on an empty message when the setting
|
||||
// asks for it (disabled, saying why, when no model can take a recording), and while a reply
|
||||
// streams or the message has text or a recording, so more can be said without clearing it
|
||||
let showStop = $derived(isLoading && !canSend);
|
||||
let showRecord = $derived.by(() => {
|
||||
if (!voice?.show) return false;
|
||||
|
||||
if (showStop || canSend) return !voice.unavailableReason;
|
||||
|
||||
return currentConfig.autoMicOnEmpty;
|
||||
});
|
||||
|
||||
let selectorModelRef: ModelsSelector | undefined = $state(undefined);
|
||||
|
||||
@@ -149,17 +170,29 @@
|
||||
{/if}
|
||||
|
||||
{#if showModelSelector}
|
||||
<ChatFormActionReasoning />
|
||||
|
||||
<!-- the reasoning effort sits in the model picker, under the models -->
|
||||
<ModelsSelector
|
||||
bind:this={selectorModelRef}
|
||||
{disabled}
|
||||
forceForegroundText
|
||||
showReasoning
|
||||
useGlobalSelection
|
||||
/>
|
||||
{/if}
|
||||
</div>
|
||||
|
||||
{#if isVoiceRefining}
|
||||
<span
|
||||
class="flex items-center gap-1.5 text-caption whitespace-nowrap text-muted-foreground"
|
||||
data-slot="voice-refining"
|
||||
role="status"
|
||||
>
|
||||
<LoaderCircle class="size-icon-sm animate-spin" />
|
||||
|
||||
{isSendWaiting ? VOICE_MODE_MESSAGE.sendAfterRefining : VOICE_MODE_MESSAGE.refining}
|
||||
</span>
|
||||
{/if}
|
||||
|
||||
{#if isReasoning && !canSend}
|
||||
<Button
|
||||
class="group size-8 rounded-full p-0 max-md:size-9"
|
||||
@@ -177,7 +210,26 @@
|
||||
</Button>
|
||||
{/if}
|
||||
|
||||
{#if isLoading && !canSend}
|
||||
{#snippet record(filled: boolean)}
|
||||
<ChatFormActionRecord
|
||||
action={voice?.action}
|
||||
{disabled}
|
||||
{filled}
|
||||
hint={voice?.hint}
|
||||
{micWarning}
|
||||
{onMicClick}
|
||||
onPrepare={voice?.prepare}
|
||||
onPrepareEnd={voice?.unprepare}
|
||||
secondary
|
||||
unavailableReason={voice?.unavailableReason}
|
||||
/>
|
||||
{/snippet}
|
||||
|
||||
{#if showRecord && !showStop}
|
||||
{@render record(false)}
|
||||
{/if}
|
||||
|
||||
{#if showStop}
|
||||
<Button
|
||||
class="group size-8 rounded-full p-0 max-md:size-9 hover:bg-destructive/10!"
|
||||
onclick={onStop}
|
||||
@@ -190,21 +242,18 @@
|
||||
class="size-icon-md fill-muted-foreground stroke-muted-foreground group-hover:fill-destructive group-hover:stroke-destructive hover:fill-destructive hover:stroke-destructive"
|
||||
/>
|
||||
</Button>
|
||||
{:else if shouldShowRecordButton}
|
||||
<ChatFormActionRecord
|
||||
{disabled}
|
||||
{hasAudioModality}
|
||||
{isLoading}
|
||||
{isRecording}
|
||||
{micWarning}
|
||||
{onMicClick}
|
||||
/>
|
||||
{:else}
|
||||
<ChatFormActionSubmit
|
||||
canSend={canSend && (showModelSelector ? hasModelSelected && isSelectedModelInCache : true)}
|
||||
{disabled}
|
||||
loading={isSendWaiting}
|
||||
showErrorState={showModelSelector && hasModelSelected && !isSelectedModelInCache}
|
||||
tooltipLabel={submitTooltip}
|
||||
/>
|
||||
{/if}
|
||||
|
||||
<!-- while a reply streams, the microphone is the last button, filled like stop -->
|
||||
{#if showRecord && showStop}
|
||||
{@render record(true)}
|
||||
{/if}
|
||||
</div>
|
||||
|
||||
+63
@@ -0,0 +1,63 @@
|
||||
<!--
|
||||
The chat form's actions row while it records: Llama UI's VoiceRecordingBar with the form's labels and its
|
||||
microphone button as the stop button. A voice message's text, when the model streams it, runs under the waveform;
|
||||
dictated text goes into the message instead. After a dictation that streamed nothing, it waits for the text in
|
||||
place of the waveform. Speech that stays too quiet even boosted is said inside the row, with the advice in a tooltip above it, so the form does not jump.
|
||||
-->
|
||||
<script lang="ts">
|
||||
import { VoiceRecordingBar } from '@ggml-org/llama-ui/voice';
|
||||
import { ChatFormActionRecord } from '#lib/components/app/index.ts';
|
||||
import { VOICE_MODE_MESSAGE, VOICE_RECORDING_BAR_STATUS } from '#lib/constants/index.ts';
|
||||
import { type ChatFormVoiceState, VoiceMode } from '#lib/enums/index.ts';
|
||||
|
||||
interface Props {
|
||||
class?: string;
|
||||
elapsedMs: number;
|
||||
levels: number[];
|
||||
/** Text streaming while a voice message is recorded. */
|
||||
liveCaption?: string;
|
||||
mode: VoiceMode;
|
||||
/** The speech is too quiet even at the highest gain: the row says so, without changing its height. */
|
||||
quiet?: boolean;
|
||||
state: ChatFormVoiceState;
|
||||
onCancel: () => void;
|
||||
onStop: () => void;
|
||||
/** Stops and sends; left out, there is no send button. */
|
||||
onSend?: () => void;
|
||||
}
|
||||
|
||||
let {
|
||||
class: className = '',
|
||||
elapsedMs,
|
||||
levels,
|
||||
liveCaption = '',
|
||||
mode,
|
||||
onCancel,
|
||||
onSend,
|
||||
onStop,
|
||||
quiet = false,
|
||||
state
|
||||
}: Props = $props();
|
||||
|
||||
const LABELS = {
|
||||
starting: VOICE_MODE_MESSAGE.starting,
|
||||
waiting: VOICE_MODE_MESSAGE.transcribing
|
||||
};
|
||||
</script>
|
||||
|
||||
<VoiceRecordingBar
|
||||
caption={liveCaption}
|
||||
class={className}
|
||||
{elapsedMs}
|
||||
label={mode === VoiceMode.DICTATION ? VOICE_MODE_MESSAGE.dictating : VOICE_MODE_MESSAGE.recording}
|
||||
labels={LABELS}
|
||||
{levels}
|
||||
{onCancel}
|
||||
{onSend}
|
||||
status={VOICE_RECORDING_BAR_STATUS[state]}
|
||||
warning={quiet ? VOICE_MODE_MESSAGE.tooQuiet : null}
|
||||
>
|
||||
{#snippet stop({ disabled })}
|
||||
<ChatFormActionRecord class="shrink-0" {disabled} isRecording onMicClick={onStop} />
|
||||
{/snippet}
|
||||
</VoiceRecordingBar>
|
||||
+1
-1
@@ -16,7 +16,7 @@
|
||||
</div>
|
||||
|
||||
{#if subtitle}
|
||||
<div class="text-[10px] leading-tight text-muted-foreground/70 max-md:text-[11px]">
|
||||
<div class="text-caption-sm leading-tight text-muted-foreground/70 max-md:text-caption">
|
||||
{subtitle}
|
||||
</div>
|
||||
{/if}
|
||||
|
||||
+4
-4
@@ -33,13 +33,13 @@
|
||||
</script>
|
||||
|
||||
<div class="mt-3 border-t border-border/50 pt-4">
|
||||
<p class="text-xs text-muted-foreground max-md:text-[13px]">Token usage details</p>
|
||||
<p class="text-caption text-muted-foreground max-md:text-body-sm">Token usage details</p>
|
||||
|
||||
<div class="flex flex-col gap-4 pt-4 text-xs max-md:gap-5 max-md:text-[13px]">
|
||||
<div class="flex flex-col gap-4 pt-4 text-caption max-md:gap-5 max-md:text-body-sm">
|
||||
{#if hasCumulative}
|
||||
<div>
|
||||
<h3
|
||||
class="text-[11px] font-medium uppercase tracking-wide text-muted-foreground/70 mb-2 max-md:text-xs"
|
||||
class="text-label-sm uppercase tracking-wide text-muted-foreground/70 mb-2 max-md:text-caption"
|
||||
>
|
||||
Across all turns
|
||||
</h3>
|
||||
@@ -68,7 +68,7 @@
|
||||
{#if hasCurrent}
|
||||
<div>
|
||||
<h3
|
||||
class="text-[11px] font-medium uppercase tracking-wide text-muted-foreground/70 mb-2 max-md:text-xs"
|
||||
class="text-label-sm uppercase tracking-wide text-muted-foreground/70 mb-2 max-md:text-caption"
|
||||
>
|
||||
This turn · KV cache
|
||||
</h3>
|
||||
|
||||
+6
-2
@@ -12,13 +12,17 @@
|
||||
</script>
|
||||
|
||||
{#if modelId !== null && !isLoading}
|
||||
<div class="flex flex-col gap-2 border-t border-border/50 pt-2 text-xs text-muted-foreground">
|
||||
<div
|
||||
class="flex flex-col gap-2 border-t border-border/50 pt-2 text-caption text-muted-foreground"
|
||||
>
|
||||
<span>Available context size is only visible once the model is loaded.</span>
|
||||
|
||||
<Button class="self-start" onclick={onLoad} size="sm" variant="outline">Load model</Button>
|
||||
</div>
|
||||
{:else if isLoading}
|
||||
<div class="flex items-center gap-2 border-t border-border/50 pt-2 text-xs text-muted-foreground">
|
||||
<div
|
||||
class="flex items-center gap-2 border-t border-border/50 pt-2 text-caption text-muted-foreground"
|
||||
>
|
||||
<Loader2 class="size-icon-sm animate-spin" />
|
||||
|
||||
<span>Loading model...</span>
|
||||
|
||||
+3
-3
@@ -120,7 +120,7 @@
|
||||
></div>
|
||||
</div>
|
||||
|
||||
<div class="flex justify-between text-xs text-muted-foreground max-md:text-[13px]">
|
||||
<div class="flex justify-between text-caption text-muted-foreground max-md:text-body-sm">
|
||||
<span>
|
||||
<span class={colorLevelTextClass(gauge.colorLevel)}>{gauge.contextPercent}%</span> used
|
||||
</span>
|
||||
@@ -130,7 +130,7 @@
|
||||
</span>
|
||||
</div>
|
||||
{:else}
|
||||
<div class="text-xs text-muted-foreground">No context info available</div>
|
||||
<div class="text-caption text-muted-foreground">No context info available</div>
|
||||
{/if}
|
||||
|
||||
{#if gauge.hasAnyUsage}
|
||||
@@ -172,7 +172,7 @@
|
||||
{:else if gaugePopup.open}
|
||||
<div
|
||||
bind:this={cardEl}
|
||||
class="absolute z-50 w-64 -translate-x-1/2 rounded-xl border matte-float p-1.5 text-sm"
|
||||
class="absolute z-50 w-64 -translate-x-1/2 rounded-xl border matte-float p-1.5 text-body-sm"
|
||||
onpointerenter={gaugeCardEnter}
|
||||
onpointerleave={gaugeCardLeave}
|
||||
role="status"
|
||||
|
||||
+8
-6
@@ -339,7 +339,7 @@
|
||||
/>
|
||||
|
||||
{#if !fileSearchEnabled}
|
||||
<div class="px-2 py-1.5 text-sm text-muted-foreground">{searchUnavailableMessage}</div>
|
||||
<div class="px-2 py-1.5 text-body-sm text-muted-foreground">{searchUnavailableMessage}</div>
|
||||
{:else if query.trim() && (search.isSearching || queryResults.length > 0 || searchError)}
|
||||
<ChatFormCurrentWorkingDirectoryResultsList
|
||||
bind:container={listContainer}
|
||||
@@ -358,8 +358,8 @@
|
||||
class={[
|
||||
'flex cursor-pointer items-center outline-hidden select-none hover:bg-accent hover:text-accent-foreground',
|
||||
inDrawer
|
||||
? 'mt-1 gap-2 rounded-lg px-2 py-2.5 text-[15px]'
|
||||
: '-mt-1 gap-2 rounded-sm px-2 py-1.5 text-sm'
|
||||
? 'mt-1 gap-2 rounded-lg px-2 py-2.5 text-body'
|
||||
: '-mt-1 gap-2 rounded-sm px-2 py-1.5 text-body-sm'
|
||||
]}
|
||||
onclick={browseNative}
|
||||
type="button"
|
||||
@@ -375,8 +375,8 @@
|
||||
class={[
|
||||
'flex cursor-pointer items-center outline-hidden select-none hover:bg-accent hover:text-accent-foreground',
|
||||
inDrawer
|
||||
? 'gap-2 rounded-lg px-2 py-2.5 text-[15px]'
|
||||
: 'gap-2 rounded-sm px-2 py-1.5 text-sm'
|
||||
? 'gap-2 rounded-lg px-2 py-2.5 text-body'
|
||||
: 'gap-2 rounded-sm px-2 py-1.5 text-body-sm'
|
||||
]}
|
||||
onclick={clearDirectory}
|
||||
type="button"
|
||||
@@ -393,7 +393,9 @@
|
||||
class={['h-px', inDrawer ? 'my-1 bg-border/60' : '-mx-2 my-2 bg-border/20']}
|
||||
></div>
|
||||
|
||||
<span class={['font-mono', inDrawer ? 'px-2 py-2 text-xs' : 'px-2 py-1.5 text-[10px]']}>
|
||||
<span
|
||||
class={['font-mono', inDrawer ? 'px-2 py-2 text-caption' : 'px-2 py-1.5 text-caption-sm']}
|
||||
>
|
||||
Searching in:
|
||||
|
||||
<span class="truncate text-muted-foreground/70" title={searchScope}
|
||||
|
||||
+1
-1
@@ -30,7 +30,7 @@
|
||||
|
||||
<span
|
||||
class={[
|
||||
'text-muted-foreground inline-flex items-center gap-1 text-xs group',
|
||||
'text-muted-foreground inline-flex items-center gap-1 text-caption group',
|
||||
directory && 'text-foreground'
|
||||
]}
|
||||
>
|
||||
|
||||
+4
-4
@@ -38,18 +38,18 @@
|
||||
class="max-h-48 overflow-y-auto py-2"
|
||||
>
|
||||
{#if isSearching && results.length === 0}
|
||||
<div class="px-2 py-1.5 text-sm text-muted-foreground">Searching...</div>
|
||||
<div class="px-2 py-1.5 text-body-sm text-muted-foreground">Searching...</div>
|
||||
{:else if error}
|
||||
<div class="px-2 py-1.5 text-sm text-destructive">{error}</div>
|
||||
<div class="px-2 py-1.5 text-body-sm text-destructive">{error}</div>
|
||||
{:else if results.length === 0}
|
||||
<div class="px-2 py-1.5 text-sm text-muted-foreground">No matching folders</div>
|
||||
<div class="px-2 py-1.5 text-body-sm text-muted-foreground">No matching folders</div>
|
||||
{:else}
|
||||
{#each results as path, index (path)}
|
||||
<button
|
||||
type="button"
|
||||
{...{ [UI_DATA_ATTRS.RESULT_INDEX]: index }}
|
||||
class={cn(
|
||||
'relative flex w-full cursor-pointer items-center gap-2 rounded-sm px-2 py-1.5 text-sm outline-hidden select-none data-highlighted:bg-accent data-highlighted:text-accent-foreground'
|
||||
'relative flex w-full cursor-pointer items-center gap-2 rounded-sm px-2 py-1.5 text-body-sm outline-hidden select-none data-highlighted:bg-accent data-highlighted:text-accent-foreground'
|
||||
)}
|
||||
data-highlighted={index === hoveredIndex ? '' : undefined}
|
||||
onclick={() => onCommit?.(path)}
|
||||
|
||||
+2
-2
@@ -18,7 +18,7 @@
|
||||
</script>
|
||||
|
||||
<div class="min-w-0 flex-1">
|
||||
<div class="mb-0.5 flex items-center gap-1.5 text-xs text-muted-foreground">
|
||||
<div class="mb-0.5 flex items-center gap-1.5 text-caption text-muted-foreground">
|
||||
{#if faviconUrl}
|
||||
<img
|
||||
alt=""
|
||||
@@ -44,7 +44,7 @@
|
||||
</div>
|
||||
|
||||
{#if description}
|
||||
<p class="mt-0.5 truncate text-sm text-muted-foreground">
|
||||
<p class="mt-0.5 truncate text-body-sm text-muted-foreground">
|
||||
{description}
|
||||
</p>
|
||||
{/if}
|
||||
|
||||
+1
-1
@@ -97,7 +97,7 @@
|
||||
{/if}
|
||||
{:else if items && items.length === 0}
|
||||
{#if emptyMessage}
|
||||
<div class="py-6 text-center text-sm text-muted-foreground">{emptyMessage}</div>
|
||||
<div class="py-6 text-center text-body-sm text-muted-foreground">{emptyMessage}</div>
|
||||
{/if}
|
||||
{:else}
|
||||
{#each items as itemData, index (itemKey(itemData, index))}
|
||||
|
||||
+2
-2
@@ -134,9 +134,9 @@
|
||||
<Icon class="mt-0.5 size-icon-md shrink-0 text-muted-foreground" />
|
||||
|
||||
<div class="flex min-w-0 flex-1 flex-col">
|
||||
<span class="font-mono text-sm font-medium">/{command.name}</span>
|
||||
<span class="font-mono text-label">/{command.name}</span>
|
||||
|
||||
<span class="min-w-0 flex-1 truncate text-left text-xs text-muted-foreground">
|
||||
<span class="min-w-0 flex-1 truncate text-left text-caption text-muted-foreground">
|
||||
{command.description}
|
||||
</span>
|
||||
</div>
|
||||
|
||||
+1
-1
@@ -57,7 +57,7 @@
|
||||
|
||||
{#if promptError}
|
||||
<div
|
||||
class="flex items-start gap-2 rounded-lg border border-destructive/50 bg-destructive/10 px-3 py-2 text-sm text-destructive"
|
||||
class="flex items-start gap-2 rounded-lg border border-destructive/50 bg-destructive/10 px-3 py-2 text-body-sm text-destructive"
|
||||
role="alert"
|
||||
>
|
||||
<span class="shrink-0">⚠</span>
|
||||
|
||||
+2
-2
@@ -46,7 +46,7 @@
|
||||
</span>
|
||||
|
||||
{#if isLoadingSuggestions}
|
||||
<span class="text-xs text-muted-foreground/50">...</span>
|
||||
<span class="text-caption text-muted-foreground/50">...</span>
|
||||
{/if}
|
||||
</Label>
|
||||
|
||||
@@ -70,7 +70,7 @@
|
||||
>
|
||||
{#each suggestions as suggestion, i (suggestion)}
|
||||
<button
|
||||
class="w-full px-3 py-1.5 text-left text-sm hover:bg-accent {i === autocompleteIndex
|
||||
class="w-full px-3 py-1.5 text-left text-body-sm hover:bg-accent {i === autocompleteIndex
|
||||
? 'bg-accent'
|
||||
: ''}"
|
||||
onmousedown={() => onSelectSuggestion(suggestion)}
|
||||
|
||||
+4
-4
@@ -258,7 +258,7 @@
|
||||
<Tooltip.Root>
|
||||
<Tooltip.Trigger>
|
||||
{#snippet child({ props })}
|
||||
<span {...props} class="truncate text-sm font-medium">{entry.name}</span>
|
||||
<span {...props} class="truncate text-label">{entry.name}</span>
|
||||
{/snippet}
|
||||
</Tooltip.Trigger>
|
||||
|
||||
@@ -267,17 +267,17 @@
|
||||
</Tooltip.Content>
|
||||
</Tooltip.Root>
|
||||
{:else}
|
||||
<span class="truncate text-sm font-medium">{entry.name}</span>
|
||||
<span class="truncate text-label">{entry.name}</span>
|
||||
{/if}
|
||||
|
||||
<span
|
||||
class="shrink-0 rounded-full bg-muted px-1.5 py-0.5 font-mono text-[9px] uppercase tracking-wide text-muted-foreground"
|
||||
class="shrink-0 rounded-full bg-muted px-1.5 py-0.5 font-mono text-caption-sm uppercase tracking-wide text-muted-foreground"
|
||||
>
|
||||
{entry.type}
|
||||
</span>
|
||||
</div>
|
||||
|
||||
<span class="min-w-0 flex-1 truncate font-mono text-left text-xs">
|
||||
<span class="min-w-0 flex-1 truncate font-mono text-left text-caption">
|
||||
<HighlightedMatch query={trimmedQuery} text={abbreviateHome(entry.path, home)} />
|
||||
</span>
|
||||
</div>
|
||||
|
||||
+1
-1
@@ -199,7 +199,7 @@
|
||||
|
||||
{#if displayedModel}
|
||||
<div class="info my-6 grid gap-4 tabular-nums">
|
||||
<div class="inline-flex flex-wrap items-start gap-2 text-xs text-muted-foreground">
|
||||
<div class="inline-flex flex-wrap items-start gap-2 text-caption text-muted-foreground">
|
||||
<ChatMessageAssistantModel
|
||||
{displayedModel}
|
||||
isLoading={chatStore.isLoading}
|
||||
|
||||
+1
-1
@@ -15,7 +15,7 @@
|
||||
|
||||
<div in:fade class="{marginClass} w-full max-w-3xl">
|
||||
<div class="flex flex-col items-start gap-2">
|
||||
<span class="shimmer-text text-sm">
|
||||
<span class="shimmer-text text-body-sm">
|
||||
{modelLoadingText ??
|
||||
processingState.getPromptProgressText() ??
|
||||
processingState.getProcessingMessage() ??
|
||||
|
||||
+2
-2
@@ -24,8 +24,8 @@
|
||||
margin-top: 1.5rem;
|
||||
padding: 1rem 1.25rem;
|
||||
border-radius: 1rem;
|
||||
background: hsl(var(--muted) / 0.3);
|
||||
color: var(--foreground);
|
||||
background: hsl(var(--surface-muted) / 0.3);
|
||||
color: var(--fg-default);
|
||||
font-size: 0.875rem;
|
||||
line-height: 1.6;
|
||||
white-space: pre-wrap;
|
||||
|
||||
+3
-3
@@ -20,13 +20,13 @@
|
||||
{#if info.path === null}
|
||||
<FolderX class="text-muted-foreground/60 size-icon-sm shrink-0" />
|
||||
|
||||
<span class="text-foreground/80 text-sm font-medium">Working directory cleared</span>
|
||||
<span class="text-foreground/80 text-label">Working directory cleared</span>
|
||||
{:else}
|
||||
<Folder class="text-muted-foreground/60 h-3.5 w-3.5 shrink-0" />
|
||||
|
||||
<span class="text-foreground/80 text-sm font-medium">Set working directory to </span>
|
||||
<span class="text-foreground/80 text-label">Set working directory to </span>
|
||||
|
||||
<span class="font-mono text-foreground/90 text-sm break-all" title={info.path}>
|
||||
<span class="font-mono text-foreground/90 text-body-sm break-all" title={info.path}>
|
||||
{info.display}
|
||||
</span>
|
||||
{/if}
|
||||
|
||||
+2
-2
@@ -29,13 +29,13 @@
|
||||
<ChatMessageEditForm />
|
||||
{:else}
|
||||
<ChatMessageMcpPromptContent
|
||||
class="w-full max-w-[80%]"
|
||||
class="w-full max-w-4/5"
|
||||
prompt={mcpPrompt}
|
||||
variant={McpPromptVariant.MESSAGE}
|
||||
/>
|
||||
|
||||
{#if message.timestamp}
|
||||
<div class="max-w-[80%]">
|
||||
<div class="max-w-4/5">
|
||||
<ChatMessageActionIcons actionsPosition="right" justify="end" />
|
||||
</div>
|
||||
{/if}
|
||||
|
||||
+6
-6
@@ -82,7 +82,7 @@
|
||||
|
||||
let showArgBadges = $derived(hasArguments && !isLoading && !loadError);
|
||||
let isAttachment = $derived(variant === McpPromptVariant.ATTACHMENT);
|
||||
let textSizeClass = $derived(isAttachment ? 'text-xs' : 'text-md');
|
||||
let textSizeClass = $derived(isAttachment ? 'text-caption' : 'text-md');
|
||||
let paddingClass = $derived(isAttachment ? 'px-3 py-2' : 'px-3.75 py-2.5');
|
||||
let maxHeightStyle = $derived(
|
||||
isAttachment ? 'max-height: 6rem;' : 'max-height: var(--max-message-height);'
|
||||
@@ -94,7 +94,7 @@
|
||||
|
||||
<div class="flex flex-col gap-2 {className}">
|
||||
<div class="flex items-center justify-between gap-2">
|
||||
<div class="inline-flex flex-wrap items-center gap-1.25 text-xs text-muted-foreground">
|
||||
<div class="inline-flex flex-wrap items-center gap-1.25 text-caption text-muted-foreground">
|
||||
<Tooltip.Root>
|
||||
<Tooltip.Trigger>
|
||||
{#if serverFavicon}
|
||||
@@ -124,7 +124,7 @@
|
||||
<Tooltip.Trigger>
|
||||
<!-- svelte-ignore a11y_no_static_element_interactions -->
|
||||
<span
|
||||
class="rounded-sm bg-purple-200/60 px-1.5 py-0.5 text-[10px] leading-none text-purple-700 transition-opacity dark:bg-purple-800/40 dark:text-purple-300 {hoveredArgKey &&
|
||||
class="rounded-sm bg-purple-200/60 px-1.5 py-0.5 text-caption-sm leading-none text-purple-700 transition-opacity dark:bg-purple-800/40 dark:text-purple-300 {hoveredArgKey &&
|
||||
hoveredArgKey !== key
|
||||
? 'opacity-30'
|
||||
: ''}"
|
||||
@@ -146,7 +146,7 @@
|
||||
|
||||
{#if loadError}
|
||||
<Card
|
||||
class="relative overflow-hidden rounded-[1.125rem] border border-destructive/50 bg-destructive/10 backdrop-blur-md"
|
||||
class="relative overflow-hidden rounded-2xl border border-destructive/50 bg-destructive/10 backdrop-blur-md"
|
||||
>
|
||||
<div
|
||||
class="overflow-y-auto {paddingClass}"
|
||||
@@ -157,7 +157,7 @@
|
||||
</Card>
|
||||
{:else if isLoading}
|
||||
<Card
|
||||
class="relative overflow-hidden rounded-[1.125rem] border border-purple-200 bg-purple-500/10 px-1 py-2 backdrop-blur-md dark:border-purple-800 dark:bg-purple-500/20"
|
||||
class="relative overflow-hidden rounded-2xl border border-purple-200 bg-purple-500/10 px-1 py-2 backdrop-blur-md dark:border-purple-800 dark:bg-purple-500/20"
|
||||
>
|
||||
<div
|
||||
class="overflow-y-auto {paddingClass}"
|
||||
@@ -174,7 +174,7 @@
|
||||
</Card>
|
||||
{:else if hasContent}
|
||||
<Card
|
||||
class="relative overflow-hidden rounded-[1.125rem] border border-purple-200 bg-purple-500/10 py-0 text-foreground backdrop-blur-md dark:border-purple-800 dark:bg-purple-500/20"
|
||||
class="relative overflow-hidden rounded-2xl border border-purple-200 bg-purple-500/10 py-0 text-foreground backdrop-blur-md dark:border-purple-800 dark:bg-purple-500/20"
|
||||
>
|
||||
<div
|
||||
class="overflow-y-auto {paddingClass}"
|
||||
|
||||
+1
-1
@@ -19,5 +19,5 @@
|
||||
{#if isCwdChange}
|
||||
<ChatMessageCwdChange class={className} {message} />
|
||||
{:else}
|
||||
<span class="text-muted-foreground block text-sm {className}">{message.content}</span>
|
||||
<span class="text-muted-foreground block text-body-sm {className}">{message.content}</span>
|
||||
{/if}
|
||||
|
||||
+8
-8
@@ -81,10 +81,10 @@
|
||||
role="group"
|
||||
>
|
||||
{#if editCtx.isEditing}
|
||||
<div class="w-full max-w-[80%]">
|
||||
<div class="w-full max-w-4/5">
|
||||
<textarea
|
||||
bind:this={textareaElement}
|
||||
class="min-h-[60px] w-full resize-none rounded-2xl px-3 py-2 text-base md:text-sm {INPUT_CLASSES}"
|
||||
class="min-h-15 w-full resize-none rounded-2xl px-3 py-2 text-body md:text-body-sm {INPUT_CLASSES}"
|
||||
oninput={(e) => {
|
||||
autoResizeTextarea(e.currentTarget);
|
||||
editCtx.setContent(e.currentTarget.value);
|
||||
@@ -116,7 +116,7 @@
|
||||
</div>
|
||||
{:else}
|
||||
{#if message.content.trim()}
|
||||
<div class="relative max-w-[80%]">
|
||||
<div class="relative max-w-4/5">
|
||||
<button
|
||||
class="group/expand block w-full text-left {!isExpanded && showExpandButton
|
||||
? 'cursor-pointer'
|
||||
@@ -125,9 +125,9 @@
|
||||
type="button"
|
||||
>
|
||||
<Card
|
||||
class="overflow-y-auto rounded-[1.125rem] !border-2 !border-dashed !border-border/50 bg-muted px-3.75 py-1.5 data-[multiline]:py-2.5"
|
||||
class="overflow-y-auto rounded-2xl !border-2 !border-dashed !border-border/50 bg-muted px-3.75 py-1.5 data-[multiline]:py-2.5"
|
||||
data-multiline={isMultiline ? '' : undefined}
|
||||
style="border: 2px dashed hsl(var(--border)); max-height: var(--max-message-height); overflow-wrap: anywhere; word-break: break-word;"
|
||||
style="border: 2px dashed hsl(var(--line-default)); max-height: var(--max-message-height); overflow-wrap: anywhere; word-break: break-word;"
|
||||
>
|
||||
<div
|
||||
class="relative transition-all duration-300 {isExpanded
|
||||
@@ -159,7 +159,7 @@
|
||||
class="pointer-events-none absolute right-0 bottom-4 left-0 flex justify-center opacity-0 transition-opacity group-hover/expand:opacity-100"
|
||||
>
|
||||
<Button
|
||||
class="rounded-full px-4 py-1.5 text-xs shadow-(--elevation-surface)"
|
||||
class="rounded-full px-4 py-1.5 text-caption shadow-(--elevation-surface)"
|
||||
size="sm"
|
||||
variant="outline"
|
||||
>
|
||||
@@ -172,7 +172,7 @@
|
||||
{#if isExpanded && showExpandButton}
|
||||
<div class="mb-2 flex justify-center">
|
||||
<Button
|
||||
class="rounded-full px-4 py-1.5 text-xs"
|
||||
class="rounded-full px-4 py-1.5 text-caption"
|
||||
onclick={(e) => {
|
||||
e.stopPropagation();
|
||||
toggleExpand();
|
||||
@@ -190,7 +190,7 @@
|
||||
{/if}
|
||||
|
||||
{#if message.timestamp}
|
||||
<div class="max-w-[80%]">
|
||||
<div class="max-w-4/5">
|
||||
<ChatMessageActionIcons actionsPosition="right" justify="end" />
|
||||
</div>
|
||||
{/if}
|
||||
|
||||
+11
-9
@@ -37,7 +37,7 @@
|
||||
<ToolCallBlock {isStreaming} meta={null} {onToggle} {open} {section} {title}>
|
||||
{#snippet children(_meta, ctx)}
|
||||
{#if ctx.isStreamingCall}
|
||||
<div class="mb-2 flex items-center gap-2 text-xs text-muted-foreground/70">
|
||||
<div class="mb-2 flex items-center gap-2 text-caption text-muted-foreground/70">
|
||||
<span>Input</span>
|
||||
|
||||
{#if ctx.isStreaming}
|
||||
@@ -53,12 +53,12 @@
|
||||
streaming={ctx.isCodeStreaming}
|
||||
/>
|
||||
{:else if ctx.isStreaming}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
Receiving arguments...
|
||||
</div>
|
||||
{:else}
|
||||
<div
|
||||
class="rounded bg-yellow-500/10 p-2 text-xs text-yellow-600 italic dark:text-yellow-400"
|
||||
class="rounded bg-yellow-500/10 p-2 text-caption text-yellow-600 italic dark:text-yellow-400"
|
||||
>
|
||||
Response was truncated
|
||||
</div>
|
||||
@@ -66,7 +66,7 @@
|
||||
{:else}
|
||||
{@const showInput = Boolean(section.toolArgs)}
|
||||
{#if showInput}
|
||||
<div class="mb-1.5 flex items-center gap-2 text-xs text-muted-foreground/70">
|
||||
<div class="mb-1.5 flex items-center gap-2 text-caption text-muted-foreground/70">
|
||||
<span>Input</span>
|
||||
</div>
|
||||
|
||||
@@ -80,8 +80,8 @@
|
||||
|
||||
<div
|
||||
class={showInput
|
||||
? 'mt-4 mb-1.5 flex items-center gap-2 text-xs text-muted-foreground/70'
|
||||
: 'mb-1.5 flex items-center gap-2 text-xs text-muted-foreground/70'}
|
||||
? 'mt-4 mb-1.5 flex items-center gap-2 text-caption text-muted-foreground/70'
|
||||
: 'mb-1.5 flex items-center gap-2 text-caption text-muted-foreground/70'}
|
||||
>
|
||||
<span>Output</span>
|
||||
|
||||
@@ -91,7 +91,7 @@
|
||||
</div>
|
||||
|
||||
{#if ctx.isPending}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
Waiting for result...
|
||||
</div>
|
||||
{:else if section.toolResult}
|
||||
@@ -106,7 +106,7 @@
|
||||
{:else}
|
||||
<div class="overflow-auto">
|
||||
{#each parsedLines as line, i (i)}
|
||||
<div class="font-mono text-[11px] leading-relaxed whitespace-pre-wrap">
|
||||
<div class="font-mono text-caption leading-relaxed whitespace-pre-wrap">
|
||||
{line.text}
|
||||
</div>
|
||||
|
||||
@@ -135,7 +135,9 @@
|
||||
</div>
|
||||
{/if}
|
||||
{:else}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">No output</div>
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
No output
|
||||
</div>
|
||||
{/if}
|
||||
{/if}
|
||||
{/snippet}
|
||||
|
||||
+13
-11
@@ -45,7 +45,7 @@
|
||||
</span>
|
||||
|
||||
{#if editFileMeta?.errorMessage}
|
||||
<span class="shrink-0 text-xs italic text-muted-foreground/70">(failed)</span>
|
||||
<span class="shrink-0 text-caption italic text-muted-foreground/70">(failed)</span>
|
||||
{/if}
|
||||
</span>
|
||||
</span>
|
||||
@@ -54,7 +54,7 @@
|
||||
{#snippet children(_meta, ctx)}
|
||||
{#if editFileBody?.errorMessage}
|
||||
<div
|
||||
class="flex items-start gap-2 rounded bg-surface-danger p-2 text-xs text-fg-danger italic"
|
||||
class="flex items-start gap-2 rounded bg-surface-danger p-2 text-caption text-fg-danger italic"
|
||||
>
|
||||
<XCircle class="mt-0.5 size-icon-xs shrink-0" />
|
||||
|
||||
@@ -63,7 +63,7 @@
|
||||
{:else if editFileBody?.edits.length}
|
||||
{#each editDiffs as diffLines, ei (ei)}
|
||||
<div class={ei === 0 ? '' : 'mt-3'}>
|
||||
<div class="mb-1.5 text-xs text-muted-foreground/70 italic">
|
||||
<div class="mb-1.5 text-caption text-muted-foreground/70 italic">
|
||||
Edit {ei + 1} of {editFileBody.edits.length}
|
||||
</div>
|
||||
|
||||
@@ -85,7 +85,7 @@
|
||||
</div>
|
||||
{/each}
|
||||
|
||||
<div class="mt-1.5 text-xs text-muted-foreground/70 italic">
|
||||
<div class="mt-1.5 text-caption text-muted-foreground/70 italic">
|
||||
{#if editFileBody.resultMessage}
|
||||
{editFileBody.resultMessage}{editFileBody.editsApplied != null
|
||||
? RESULT_STAT_SEPARATOR
|
||||
@@ -105,11 +105,13 @@
|
||||
streaming={ctx.isCodeStreaming}
|
||||
/>
|
||||
{:else if ctx.isStreaming}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
Receiving arguments...
|
||||
</div>
|
||||
{:else}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">No edits</div>
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
No edits
|
||||
</div>
|
||||
{/if}
|
||||
{/snippet}
|
||||
</ToolCallBlock>
|
||||
@@ -119,13 +121,13 @@
|
||||
overflow: auto;
|
||||
border-radius: 0.75rem;
|
||||
border-width: 1px;
|
||||
border-color: color-mix(in oklch, var(--border) 30%, transparent);
|
||||
background: var(--code-background);
|
||||
border-color: color-mix(in oklch, var(--line-default) 30%, transparent);
|
||||
background: var(--surface-code);
|
||||
box-shadow: 0 1px 2px 0 rgb(0 0 0 / 0.05);
|
||||
}
|
||||
|
||||
:global(.dark) .diff-block {
|
||||
border-color: color-mix(in oklch, var(--border) 20%, transparent);
|
||||
border-color: color-mix(in oklch, var(--line-default) 20%, transparent);
|
||||
}
|
||||
|
||||
/* Each row is a 4-column grid: old-line#, marker, new-line#, text.
|
||||
@@ -144,13 +146,13 @@
|
||||
text-align: right;
|
||||
padding-right: 0.5rem;
|
||||
user-select: none;
|
||||
color: color-mix(in oklch, var(--muted-foreground) 70%, transparent);
|
||||
color: color-mix(in oklch, var(--fg-muted) 70%, transparent);
|
||||
font-variant-numeric: tabular-nums;
|
||||
}
|
||||
|
||||
.diff-marker {
|
||||
text-align: center;
|
||||
color: color-mix(in oklch, var(--muted-foreground) 70%, transparent);
|
||||
color: color-mix(in oklch, var(--fg-muted) 70%, transparent);
|
||||
user-select: none;
|
||||
}
|
||||
|
||||
|
||||
+7
-7
@@ -248,18 +248,18 @@
|
||||
|
||||
{#snippet children(_meta, ctx)}
|
||||
{#if (ctx.isPending && !commandStreaming) || (isLive && !section.toolResult)}
|
||||
<div class="flex items-start gap-2 text-xs text-muted-foreground/70">
|
||||
<div class="flex items-start gap-2 text-caption text-muted-foreground/70">
|
||||
<Loader2 class="size-icon-xs animate-spin" />
|
||||
Executing command...
|
||||
</div>
|
||||
{:else if ctx.isInterrupted}
|
||||
<div class="flex items-start gap-2 text-xs text-muted-foreground/70 italic">
|
||||
<div class="flex items-start gap-2 text-caption text-muted-foreground/70 italic">
|
||||
<CircleStop class="mt-0.5 h-3 w-3 shrink-0" />
|
||||
|
||||
<span>Command interrupted before it returned output</span>
|
||||
</div>
|
||||
{:else if execShellError}
|
||||
<div class="flex items-start gap-2 text-xs text-fg-danger italic">
|
||||
<div class="flex items-start gap-2 text-caption text-fg-danger italic">
|
||||
<XCircle class="mt-0.5 size-icon-xs shrink-0" />
|
||||
|
||||
<span>{execShellError}</span>
|
||||
@@ -271,7 +271,7 @@
|
||||
onscroll={handleScrollEvent}
|
||||
>
|
||||
{#each outputLines as line, i (i)}
|
||||
<div class="font-mono text-[11px] leading-relaxed whitespace-pre-wrap">{line.text}</div>
|
||||
<div class="font-mono text-caption leading-relaxed whitespace-pre-wrap">{line.text}</div>
|
||||
|
||||
{#if line.media?.type === AttachmentType.IMAGE}
|
||||
<img
|
||||
@@ -316,13 +316,13 @@
|
||||
|
||||
.exec-wd {
|
||||
font-family: var(--font-mono);
|
||||
color: var(--muted-foreground);
|
||||
color: var(--fg-muted);
|
||||
margin-right: var(--exec-wd-margin);
|
||||
}
|
||||
|
||||
.exec-prompt {
|
||||
font-family: var(--font-mono);
|
||||
color: var(--muted-foreground);
|
||||
color: var(--fg-muted);
|
||||
opacity: 0.55;
|
||||
margin-right: var(--exec-wd-margin);
|
||||
}
|
||||
@@ -333,7 +333,7 @@
|
||||
height: 1.05em;
|
||||
margin-left: 0.15rem;
|
||||
vertical-align: text-bottom;
|
||||
background: var(--foreground);
|
||||
background: var(--fg-default);
|
||||
animation: exec-cursor-blink 1.1s steps(1) infinite;
|
||||
}
|
||||
|
||||
|
||||
+6
-6
@@ -40,12 +40,12 @@
|
||||
|
||||
{#snippet children(meta, ctx)}
|
||||
{#if ctx.isPending}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
Searching...
|
||||
</div>
|
||||
{:else if meta?.errorMessage}
|
||||
<div
|
||||
class="flex items-start gap-2 rounded bg-surface-danger p-2 text-xs text-fg-danger italic"
|
||||
class="flex items-start gap-2 rounded bg-surface-danger p-2 text-caption text-fg-danger italic"
|
||||
>
|
||||
<XCircle class="mt-0.5 size-icon-xs shrink-0" />
|
||||
|
||||
@@ -54,17 +54,17 @@
|
||||
{:else if meta && meta.matches.length > 0}
|
||||
<div class="max-h-96 overflow-auto">
|
||||
{#each meta.matches as match, i (i)}
|
||||
<div class="font-mono text-[11px] leading-relaxed whitespace-pre-wrap">{match}</div>
|
||||
<div class="font-mono text-caption leading-relaxed whitespace-pre-wrap">{match}</div>
|
||||
{/each}
|
||||
</div>
|
||||
|
||||
<div class="mt-1.5 text-xs text-muted-foreground/70 italic">
|
||||
<div class="mt-1.5 text-caption text-muted-foreground/70 italic">
|
||||
Total matches: <span class="font-mono">{meta.totalMatches ?? meta.matches.length}</span>
|
||||
</div>
|
||||
{:else}
|
||||
<div class="text-xs text-muted-foreground/70 italic">No matches</div>
|
||||
<div class="text-caption text-muted-foreground/70 italic">No matches</div>
|
||||
|
||||
<div class="mt-1.5 text-xs text-muted-foreground/70 italic">
|
||||
<div class="mt-1.5 text-caption text-muted-foreground/70 italic">
|
||||
Total matches: <span class="font-mono">{meta?.totalMatches ?? 0}</span>
|
||||
</div>
|
||||
{/if}
|
||||
|
||||
+6
-6
@@ -46,18 +46,18 @@
|
||||
<Clock class="text-muted-foreground/60 size-icon-sm shrink-0" />
|
||||
|
||||
{#if showSpinner}
|
||||
<span class="text-foreground/80 text-sm font-medium">Current time</span>
|
||||
<span class="text-foreground/80 text-label">Current time</span>
|
||||
|
||||
<Loader2 class="text-muted-foreground/70 size-icon-xs animate-spin" />
|
||||
{:else if dateMeta.errorMessage}
|
||||
<span class="text-foreground/80 text-sm font-medium">Current time </span>
|
||||
<span class="text-foreground/80 text-label">Current time </span>
|
||||
|
||||
<span class="text-fg-danger text-xs italic">- {dateMeta.errorMessage}</span>
|
||||
<span class="text-fg-danger text-caption italic">- {dateMeta.errorMessage}</span>
|
||||
{:else if dateMeta.dateString}
|
||||
<span class="text-foreground/80 text-sm font-medium">Current time is </span>
|
||||
<span class="text-foreground/80 text-label">Current time is </span>
|
||||
|
||||
<span class="font-mono text-foreground/90 text-sm">{dateMeta.dateString}</span>
|
||||
<span class="font-mono text-foreground/90 text-body-sm">{dateMeta.dateString}</span>
|
||||
{:else}
|
||||
<span class="text-foreground/80 text-sm font-medium">Current time</span>
|
||||
<span class="text-foreground/80 text-label">Current time</span>
|
||||
{/if}
|
||||
</div>
|
||||
|
||||
+6
-6
@@ -60,14 +60,14 @@
|
||||
{#snippet children(meta, _ctx)}
|
||||
{#if meta?.errorMessage}
|
||||
<div
|
||||
class="flex items-start gap-2 rounded bg-surface-danger p-2 text-xs text-fg-danger italic"
|
||||
class="flex items-start gap-2 rounded bg-surface-danger p-2 text-caption text-fg-danger italic"
|
||||
>
|
||||
<XCircle class="mt-0.5 size-icon-xs shrink-0" />
|
||||
|
||||
<span>{meta.errorMessage}</span>
|
||||
</div>
|
||||
{:else if infoMeta.os || infoMeta.cwd}
|
||||
<table class="w-full table-fixed border-collapse text-sm">
|
||||
<table class="w-full table-fixed border-collapse text-body-sm">
|
||||
<colgroup>
|
||||
<col class="w-12" />
|
||||
|
||||
@@ -78,7 +78,7 @@
|
||||
{#if infoMeta.os}
|
||||
<tr>
|
||||
<th
|
||||
class="py-1 pr-3 text-left align-baseline text-[11px] font-medium tracking-wide text-muted-foreground/60 uppercase"
|
||||
class="py-1 pr-3 text-left align-baseline text-label-sm tracking-wide text-muted-foreground/60 uppercase"
|
||||
scope="row"
|
||||
>
|
||||
os
|
||||
@@ -95,7 +95,7 @@
|
||||
{#if infoMeta.cwd}
|
||||
<tr>
|
||||
<th
|
||||
class="py-1 pr-3 text-left align-baseline text-[11px] font-medium tracking-wide text-muted-foreground/60 uppercase"
|
||||
class="py-1 pr-3 text-left align-baseline text-label-sm tracking-wide text-muted-foreground/60 uppercase"
|
||||
scope="row"
|
||||
>
|
||||
cwd
|
||||
@@ -114,11 +114,11 @@
|
||||
</tbody>
|
||||
</table>
|
||||
{:else if section.toolResult}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
{section.toolResult}
|
||||
</div>
|
||||
{:else}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
Waiting for runtime info...
|
||||
</div>
|
||||
{/if}
|
||||
|
||||
+6
-6
@@ -34,12 +34,12 @@
|
||||
|
||||
{#snippet children(meta, ctx)}
|
||||
{#if ctx.isPending}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
Searching...
|
||||
</div>
|
||||
{:else if meta?.errorMessage}
|
||||
<div
|
||||
class="flex items-start gap-2 rounded bg-surface-danger p-2 text-xs text-fg-danger italic"
|
||||
class="flex items-start gap-2 rounded bg-surface-danger p-2 text-caption text-fg-danger italic"
|
||||
>
|
||||
<XCircle class="mt-0.5 size-icon-xs shrink-0" />
|
||||
|
||||
@@ -48,7 +48,7 @@
|
||||
{:else if meta && meta.matches.length > 0}
|
||||
<div class="max-h-96 overflow-auto">
|
||||
{#each meta.matches as match, mi (mi)}
|
||||
<div class="font-mono text-[11px] leading-relaxed">
|
||||
<div class="font-mono text-caption leading-relaxed">
|
||||
<span class="text-muted-foreground/70">{match.file}</span>
|
||||
|
||||
{#if meta.showLineNumbers && match.line != null}
|
||||
@@ -62,7 +62,7 @@
|
||||
{/each}
|
||||
</div>
|
||||
|
||||
<div class="mt-1.5 text-xs text-muted-foreground/70 italic">
|
||||
<div class="mt-1.5 text-caption text-muted-foreground/70 italic">
|
||||
Total matches: <span class="font-mono">{meta.totalMatches ?? meta.matches.length}</span>
|
||||
|
||||
{#if meta.showLineNumbers}
|
||||
@@ -70,9 +70,9 @@
|
||||
{/if}
|
||||
</div>
|
||||
{:else}
|
||||
<div class="text-xs text-muted-foreground/70 italic">No matches</div>
|
||||
<div class="text-caption text-muted-foreground/70 italic">No matches</div>
|
||||
|
||||
<div class="mt-1.5 text-xs text-muted-foreground/70 italic">
|
||||
<div class="mt-1.5 text-caption text-muted-foreground/70 italic">
|
||||
Total matches: <span class="font-mono">{meta?.totalMatches ?? 0}</span>
|
||||
</div>
|
||||
{/if}
|
||||
|
||||
+1
-1
@@ -42,7 +42,7 @@
|
||||
maxHeight={MAX_HEIGHT_CODE_BLOCK}
|
||||
/>
|
||||
{:else}
|
||||
<div class="rounded bg-muted/20 p-2 text-xs text-muted-foreground/70 italic">
|
||||
<div class="rounded bg-muted/20 p-2 text-caption text-muted-foreground/70 italic">
|
||||
Waiting for file content...
|
||||
</div>
|
||||
{/if}
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user